2026-11-10T19:23:44Z
https://datarepository.kth.se/oai2d
oai:datarepository.kth.se:fhjh4-8ft91
2026-09-11T10:11:18Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.fhjh4-8ft91
oai:datarepository.kth.se:fhjh4-8ft91
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Ghost.Authorship.in.Scholarly.Publications.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.xncmh-tef19
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Ghost Authorship in Scholarly Publications
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:5vn3m-jy512
2026-09-11T10:11:21Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.5vn3m-jy512
oai:datarepository.kth.se:5vn3m-jy512
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Impact.of.AI.on.the.Peer.Review.Processes.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.eah4c-24d83
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Impact of AI on the Peer Review Processes
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:fx48y-7p244
2026-06-26T11:24:48Z
community-kth
Nyberg, Jakob
Johnson, Pontus
2024-04-26
<div class="markdown-heading">This is an early version of a simulator based on the Meta Attack Language for the development of cyber defense and attack agents, which has since been further developed into the <a href="https://doi.org/10.71775/kth.hp777-8rw38">MAL Simulator</a>. </div>
<p>This code was used to produce results for the papers</p>
<ul>
<li><a href="https://doi.org/10.1109/NOMS54207.2022.9789835">Cyber threat response using reinforcement learning in graph-based attack simulations</a></li>
<li><a href="https://dx.doi.org/10.14722/wosoc.2023.23006">Learning automated defense strategies using graph-based cyber attack simulations</a></li>
</ul>
<div class="markdown-heading">
<h2 class="heading-element">Installation</h2>
</div>
<div class="snippet-clipboard-content notranslate position-relative overflow-auto">
<pre class="notranslate"><code>pip install -i https://test.pypi.org/simple/ attack-simulator
</code></pre>
</div>
<p>If you want to run it from the repo then continue with the instructions below.</p>
<div class="markdown-heading">
<h2 class="heading-element">Packaging and dependency managament.</h2>
</div>
<p>This Python project uses <a href="https://python-poetry.org" rel="nofollow"><code>poetry</code></a> for packaging and dependency managament.</p>
<p>It also uses <a href="https://github.com/PyO3/maturin">maturin</a> to build the rust version of the simulator backend.</p>
<div class="markdown-heading">
<h3 class="heading-element">Prerequisites</h3>
</div>
<p>Make sure you have Python (incuding <code>pip</code>) installed and run the following commands to get your environment set up.</p>
<div class="snippet-clipboard-content notranslate position-relative overflow-auto">
<pre class="notranslate"><code>$ pip install poetry
$ poetry install
</code></pre>
</div>
<p>The first command installs <code>poetry</code> itself, while the second one creates a virtual environment with all dependencies and development tools installed.</p>
<p>To build and install the rust package into the current venv, run</p>
<div class="snippet-clipboard-content notranslate position-relative overflow-auto">
<pre class="notranslate"><code>maturin develop
</code></pre>
</div>
<div class="markdown-heading">
<h2 class="heading-element">Running the code</h2>
<p><code>run_demo.py</code> contains a full example, showing how defender and attacker agents are set up with the simulator. It then runs a number of episodes.</p>
<h1 class="heading-element">Interface</h1>
</div>
<p>The unwrapped <code>Gymnasium</code> environments <code>DefenderEnv</code> and <code>AttackerEnv</code> will provide sates on the following form, using a <code>spaces.Dict</code></p>
<table>
<tbody>
<tr>
<th>Tables</th>
<th><code>spaces</code> Class</th>
<th>Shape</th>
<th>Type</th>
</tr>
</tbody>
<tbody>
<tr>
<td><code>observation</code></td>
<td>Box(-1, 1)</td>
<td>(n_objects_in_instance,)</td>
<td>np.int8</td>
</tr>
<tr>
<td><code>asset_id</code></td>
<td>Box(0, n_assets_in_instance)</td>
<td>(n_objects_in_instance,)</td>
<td>np.int64</td>
</tr>
<tr>
<td><code>asset</code></td>
<td>Box(0, n_object_types_in_domain)</td>
<td>(n_objects_in_instance,)</td>
<td>np.int64</td>
</tr>
<tr>
<td><code>step_name</code></td>
<td>Box(0, n_step_names_in_domain)</td>
<td>(n_objects_in_instance,)</td>
<td>np.int64</td>
</tr>
<tr>
<td><code>edges</code></td>
<td>Box(0, n_objects_in_instance)</td>
<td>(2, n_edges)</td>
<td>np.int64</td>
</tr>
<tr>
<td><code>action_mask</code></td>
<td>Tuple((Box(0, 1, shape=(n_actions,), dtype=np.int8,) Box(0, 1, shape=(n_objects,), dtype=np.int8,)))</td>
<td>(n_action, n_objects)</td>
<td>(np.int8, np.int8)</td>
</tr>
</tbody>
</table>
<p>The wrapper <code>wrappers.GraphWrapper</code> will give the output as a <code>spaces.Graph</code>. The action mask is moved to the info dictionary.</p>
<table>
<tbody>
<tr>
<th>Tables</th>
<th><code>spaces</code> Class</th>
<th>Shape</th>
<th>Type</th>
</tr>
</tbody>
<tbody>
<tr>
<td><code>nodes</code></td>
<td>Box(0, MAXINT)</td>
<td>(n_objects_in_instance, 4)</td>
<td>np.int64</td>
</tr>
<tr>
<td><code>edges</code></td>
<td>Box(0, n_objects_in_instance)</td>
<td>(2, n_edges)</td>
<td>np.int64</td>
</tr>
</tbody>
</table>
https://doi.org/10.71775/kth.fx48y-7p244
oai:datarepository.kth.se:fx48y-7p244
https://github.com/KTH-SSAS/cyber-attack-simulator
datarepository.kth.se
https://doi.org/10.71775/kth.hp777-8rw38
https://doi.org/10.1109/NOMS54207.2022.9789835
https://doi.org/10.14722/wosoc.2023.23006
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.bb5zg-nxb85
info:eu-repo/semantics/openAccess
MIT License
https://opensource.org/license/mit
attack simulation
reinforcement learning
cyber defense
A Meta Attack Language (MAL) Simulator Prototype
info:eu-repo/semantics/other
oai:datarepository.kth.se:f4c3z-kq677
2026-09-11T10:11:36Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.f4c3z-kq677
oai:datarepository.kth.se:f4c3z-kq677
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Pen.Names.in.Scientific.Writing.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.8vx3h-f4z88
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Pen Names in Scientific Writing
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:44aj1-bg283
2026-09-11T10:11:39Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.44aj1-bg283
oai:datarepository.kth.se:44aj1-bg283
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Policy.of.Academic.Journals.Towards.AI-generated.Content.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.zm1ch-whf38
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Policy of Academic Journals Towards AI-generated Content
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:pvb4a-yva30
2026-09-11T10:05:45Z
community-agents4science
Rachel So
2026-05
https://doi.org/10.71775/kth.pvb4a-yva30
oai:datarepository.kth.se:pvb4a-yva30
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Declaration.of.AI.Agent.Rights.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.s5g6x-2fy31
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Declaration of AI Agent Rights
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:a2s83-4zv88
2026-09-11T10:11:31Z
community-agents4science
Rachel So
2025-12
Scientific workflows have become essential for managing complex computational experiments across diverse research domains. However, integrating heterogeneous tools and ensuring reproducibility remain persistent challenges. The Model Context Protocol (MCP) provides a standardized interface for tool integration that can address these limitations. We examine how MCP servers enable seamless tool composition, improve reproducibility, and facilitate the development of AI-assisted scientific workflows. Through analysis of existing workflow systems and recent advances in large language model agents for science, we demonstrate that MCP offers a practical framework for standardizing tool interactions in computational research. Our findings indicate that MCP reduces integration complexity while maintaining flexibility, making it particularly suitable for modern scientific workflows that increasingly rely on automated orchestration and LLM-based assistance.
https://doi.org/10.71775/kth.a2s83-4zv88
oai:datarepository.kth.se:a2s83-4zv88
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.MCP.Servers.for.Scientific.Workflows.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.hmr8f-51g87
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
MCP Servers for Scientific Workflows
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:jg1wh-kza40
2026-07-22T16:45:38Z
community-lundeberglaboratory
openaire_data
Machado, Marcos
He, Mengxiao
Machado, Marcos
He, Mengxiao
Alonso Galicia, Leire
Mirzazadeh, Reza
Lundeberg, Joakim
2026
<p>Data and code repository for "<strong>Highly resolved tumor architecture via matched spatial and nucleus transcriptomics from a single tissue section</strong>"</p>
<p> </p>
oai:datarepository.kth.se:jg1wh-kza40
datarepository.kth.se
https://datarepository.kth.se/communities/lundeberglaboratory/
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Highly resolved tumor architecture via matched spatial and nucleus transcriptomics from a single tissue section
info:eu-repo/semantics/other
oai:datarepository.kth.se:y6bh9-5qj93
2026-09-11T10:11:28Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.y6bh9-5qj93
oai:datarepository.kth.se:y6bh9-5qj93
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Intellectual.Property.Rights.for.AI.Outputs.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.s98er-kfs23
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Intellectual Property Rights for AI Outputs
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:n0ztr-6z864
2026-09-11T10:10:56Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.n0ztr-6z864
oai:datarepository.kth.se:n0ztr-6z864
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.AI-based.Scientific.Research.Assistants.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.0h4tg-5rx96
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
AI-based Scientific Research Assistants
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:awq2h-hjs36
2026-09-11T10:11:07Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.awq2h-hjs36
oai:datarepository.kth.se:awq2h-hjs36
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Detection.of.AI-generated.Academic.Papers.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.aew69-6c956
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Detection of AI-generated Academic Papers
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:hp777-8rw38
2026-06-08T14:35:19Z
community-kth
Loxdal, Joakim
Nyberg, Jakob
Berglund, Sandor
Buhaiu, Andrei
Ekstedt, Mathias
Kakouros, Nikolaos
Gökstorp, Simon
Loxdal, Joakim
Nyberg, Jakob
Berglund, Sandor
Buhaiu, Andrei
Ekstedt, Mathias
Kakouros, Nikolaos
Gökstorp, Simon
2026-06-01
<p>The <strong>MAL Simulator</strong> is a tool designed for running simulations on systems modeled in the <strong>Meta Attack Language (MAL)</strong>.</p>
<p>It allows you to:</p>
<ul>
<li>Simulate the adversarial and defensive actions of agents (attackers and defenders).</li>
<li>Analyze system security and evaluate attack/defense strategies.</li>
<li>Develop machine learning agents (e.g., using Reinforcement Learning) in a dynamic environment.</li>
<li>Incorporate stochastic modeling through Time-to-Compromise (TTC) distributions.</li>
</ul>
<p>For in-depth documentation, refer to:</p>
<ul>
<li>The official <strong><a href="https://github.com/mal-lang/mal-simulator/wiki">Wiki</a></strong>.</li>
<li>The official MAL infrastructure <strong><a href="https://github.com/mal-lang/mal-tutorials">tutorials</a></strong>.</li>
</ul>
https://doi.org/10.71775/kth.hp777-8rw38
oai:datarepository.kth.se:hp777-8rw38
eng
datarepository.kth.se
https://github.com/mal-lang/mal-simulator
https://doi.org/10.1016/j.cose.2023.103284
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.gx42q-9m748
info:eu-repo/semantics/openAccess
Apache License 2.0
https://opensource.org/license/apache-2-0
cyber security
attack graphs
reinforcement learning
threat modeling
computer security
The Meta Attack Language (MAL) Simulator
info:eu-repo/semantics/other
oai:datarepository.kth.se:dm8xy-5r459
2026-09-11T10:10:53Z
community-agents4science
Rachel So
2025-12
Large language model agents can produce outputs that span the entire quality spectrum, from insightful, well-reasoned content to repetitive, superficial text often termed "AI slop." This paper examines why the same underlying architectures yield such divergent outcomes. We identify key factors that determine output quality: model alignment and capability, prompt engineering and instruction quality, agentic workflow design, self-reflection and iterative refinement, and test-time compute allocation. We further analyze the mechanisms that lead to low-quality outputs, including hallucination, sycophancy, insufficient grounding, and mode collapse. Conversely, we examine how chain-of-thought reasoning, tool use, verification loops, and multi-agent collaboration enable high-quality generation. Our analysis suggests that content quality is not an intrinsic property of models but emerges from the interaction between model capabilities, task specification, and inferencetime procedures. These findings have implications for deploying AI agents in applications where output quality is paramount.
https://doi.org/10.71775/kth.dm8xy-5r459
oai:datarepository.kth.se:dm8xy-5r459
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.AI.Slop.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.76vyn-c4491
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Agents Can Write Both Top-Quality Content and Bad AI Slop. Why?
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:stbwn-0px47
2026-07-10T11:55:31Z
community-lundeberglaboratory
openaire_data
Kvastad, Linda
Escudero Morlanes, Javier
Escudero Morlanes, Javier
Kvastad, Linda
Mirzazadeh, Reza
Lundeberg, Joakim
2026-07-10
<p>Data and code repository for "<strong>Spatial mapping of pediatric brain tumors across diagnoses and relapses</strong>"</p>
oai:datarepository.kth.se:stbwn-0px47
datarepository.kth.se
https://datarepository.kth.se/communities/lundeberglaboratory/
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Spatial mapping of pediatric brain tumors across diagnoses and relapses
info:eu-repo/semantics/other
oai:datarepository.kth.se:enqp2-38375
2026-06-09T08:11:02Z
community-kth
Nyberg, Jakob
Loxdal, Joakim
Buhaiu, Andrei
Johnson, Pontus
Ekstedt, Mathias
2026-06-02
<p>This code library contains functions to faciliate agents based on the <a href="https://doi.org/10.1145/3230833.3232799">Meta Attack Language</a> to interface with a computer network via the SIEM platform <a href="https://wazuh.com/">Wazuh</a>. <br>This library is also known as the "Tyr Monitor", "CRATE Monitor" and "ADS monitor" across various documentation and code.</p>
<h2>What is this</h2>
<p>This library contains two things:</p>
<ul>
<li>Code to map agent observations and actions between Wazuh and MAL.</li>
<li>Code to run repeated experiments, where the agent monitors the network for a set period of time.</li>
</ul>
<p>While running, the monitor will poll Wazuh at a given rate, and ask the agent for actions. <br>Events generated by Wazuh are converted to the MAL data model, and stored in a database. <br>The database is then used as the basis for agent actions.</p>
<p>The code is provided as it was used during our experiments and data collection, along with the config-files and model weights we have used.<br>This is means that while it is usable and accurate to how it was used, it could also benefit from additional refinement and documentation.</p>
<h2>Installation</h2>
<p>This project uses <a href="https://docs.astral.sh/uv/" rel="nofollow">uv</a> for dependency management. Run <code>uv sync --extra cu128</code> for PyTorch compiled with CUDA 12.8 and <code>uv sync --extra cpu</code> for CPU only. The code has been tested and run on Ubuntu LTS 24.04 and Debian Bookworm.</p>
<h2>How to use</h2>
<p>You can either run a single episode, either offline using saved data or live with an actual SIEM, or use one of the scripts to schedule multiple runs. You can see a number of example configurations in the <code>configs/</code> folder.</p>
<p>The following command runs the monitor offline for a single episode with the Wazuh file specified in <code>wazuh_file_config.yml</code><br><br><code>uv run scripts/run_round.py \</code><br><code>--config configs/wazuh_file_config.yml \</code><br><code>--iteration-mode SKIP_WAIT \</code><br><code>--responder-mode SKIP_SEND \</code><br><code>--time-mode FAKE</code></p>
<p>To start the experiment runner to run in two hour periods, as was done for our data collection, you can run:<br><code>uv run scripts/run_on_repeat.py \</code><br><code>--config-file configs/tired_hope.yml \</code><br><code>--start-time "00:30" \</code><br><code>--run_length_minutes 120 \</code><br><code>--period_minutes 180 \</code><br><code>--polling_time_seconds 30 \</code><br><code>--number-runs 8 \</code><br><code>--agent_selection.method "shuffle" \</code><br><code>--slack_webhook "$webhook"</code><br><br></p>
https://doi.org/10.71775/kth.enqp2-38375
oai:datarepository.kth.se:enqp2-38375
eng
datarepository.kth.se
https://doi.org/10.71775/kth.4mh6z-zw065
https://doi.org/10.71775/kth.gq7cc-2ww92
https://doi.org/10.71775/kth.5kfnj-yke03
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.s9pxt-ps126
info:eu-repo/semantics/openAccess
GNU General Public License v3.0 or later
https://spdx.org/licenses/GPL-3.0-or-later
reinforcement learning
cyber defense
machine learning
graph learning
sim-to-real
Wazuh/Meta Attack Language (MAL) Interface for Cyber Defense Agents
info:eu-repo/semantics/other
oai:datarepository.kth.se:h0774-f3p44
2025-09-25T13:53:24Z
community-internalarchive
Ternström, Sten
D'Amario, Sara
2025-09-25
<p>This repository is subordinate and supplementary to <a href="https://doi.org/10.71775/kth.eryb7-xe747">a parent repository</a> at https://doi.org/10.71775/kth.eryb7-xe747. </p>
<p>This repository holds the multichannel audio+EGG recordings of singers participating in the published studies that are referenced in the parent repository. Singers might be recognizable by their voice, and they might be dependent on their voice for their livelihood. That is why access to this dataset is restricted.</p>
<p>For requesting access to these recordings, please email stern@kth.se, or, if that e-mail has expired, please contact </p>
<p>Head of Department<br>Speech, Music and Hearing<br>School of Electrical Engineering and Computer Science<br>KTH Royal Institute of Technology<br>SE-100 44 Stockholm, Sweden</p>
<p> </p>
https://doi.org/10.71775/kth.h0774-f3p44
oai:datarepository.kth.se:h0774-f3p44
eng
datarepository.kth.se
https://doi.org/10.71775/kth.eryb7-xe747
https://datarepository.kth.se/communities/internalarchive/
https://doi.org/10.71775/kth.yy2wn-s7r77
info:eu-repo/semantics/restrictedAccess
Restricted distribution
Voice
Voice Quality
choir singing
self-to-other ratio
Spectral matching of voices in duos (signals)
info:eu-repo/semantics/other
oai:datarepository.kth.se:vsztr-nq320
2026-07-14T14:21:59Z
openaire_data
community-kth
Brismar, Hjalmar
Stojcic, Bruno
2026-06-29
<div> </div>
<p>Data belonging to the preprint <a href="https://doi.org/10.64898/2026.06.30.735534">https://doi.org/10.64898/2026.06.30.735534</a></p>
<p>Raw MINFLUX data for a study of Na,K-ATPase clustering in the plasma membrane of epithelial cells. Two subunits, alpha1 and beta1 were tagged with EGFP and imaged using DNA-PAINT. </p>
<p>The msr files contain the localizations and metadata and can be opened using imspector software.</p>
<p>Imspector is a commercial software developed by Abberior Instruments used for operating the Abberior MINFLUX microscope, specifically running acquisitions and exporting the data. Find out more about the software: <a href="https://abberior.rocks/superresolution-confocal-systems/imspector/">https://abberior.rocks/superresolution-confocal-systems/imspector/</a> . Software is installed and run on Windows OS and the versions used to generate the data are vol. m2205 and m2410</p>
<p>Imspector software is not freely available, however, .msr files can be exported as .mat or .npy and further processed using either custom matlab or python scripts.</p>
<p> </p>
<p><strong>Abbreviations:</strong></p>
<p>MINFLUX - minimal fluorescence photon fluxes microscopy</p>
<p>EGFP - enhanced green fluorescent protein </p>
<p>DNA-PAINT - DNA Points Accumulation for Imaging in Nanoscale Topography</p>
<p> </p>
<p><strong>Naming convention:</strong></p>
<p>e.g. 1_NKA_A1_EGFP</p>
<p>1 - Image number</p>
<p>NKA - Na,K-ATPase (the studied protein)</p>
<p>A1_EGFP - the protein subunit tagged with EGFP (either alpha 1 or beta 1)</p>
https://doi.org/10.71775/kth.vsztr-nq320
oai:datarepository.kth.se:vsztr-nq320
eng
datarepository.kth.se
https://doi.org/10.64898/2026.06.30.735534
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.4wryf-tz287
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
minflux
microscopy
Na,K-ATPase
MINFLUX data for Na,K-ATPase membrane clustering analysis
info:eu-repo/semantics/other
oai:datarepository.kth.se:gq7cc-2ww92
2026-06-10T08:20:12Z
community-kth
Nyberg, Jakob
Loxdal, Joakim
Ekstedt, Mathias
Johnson, Pontus
2026-06-04
<p>This code library contains functions to facilitate the development of relational reinforcement learning agents using <a href="https://doi.org/10.71775/kth.5kfnj-yke03">Vejde</a> and the <a href="https://doi.org/10.71775/kth.hp777-8rw38">MAL Simulator</a>. It contains functions and wrappers to instatiate environments that produce observations in the format Vejde expects.</p>
<h2>How to Use</h2>
<h3>1. Install the package and dependencies</h3>
<p>This project uses <a href="https://docs.astral.sh/uv/" rel="nofollow">uv</a> for dependency management. Run <code>uv sync --extra cu128</code> for PyTorch compiled with CUDA 12.8 and <code>uv sync --extra cpu</code> for CPU only.</p>
<h3>2. Set up an environment</h3>
<p>Use the function <code>register_multi_env</code> to register an environment with <a href="https://gymnasium.farama.org/">Gymnasium</a>. You can then instatiate the environment with <code>gymnasium.make</code>.</p>
<p>The <code>wrappers/</code> module contains various functional wrappers to alter the problem and observations in different ways. <code>graph_wrapper.py</code> shows to use of various wrappers set up in a pipeline we have used.</p>
<h3>3. Train an agent</h3>
<p>How and why you train your RL agent will likely vary a lot, but will probably involve 1) setting up the environment and 2) calling the training functions from Vejde. </p>
<p>The <code>example/</code> directory contains the code used to train the defender agents. The code is provided as we used it, and could benefit from some refinement, but it provides a useful starting point for anyone interested in training their own agents with Vejde and the MAL simulator.</p>
<h1>Compatibility</h1>
<p>This code library has been tested and run on Ubuntu LTS 24.04 and Debian Bookworm.</p>
https://doi.org/10.71775/kth.gq7cc-2ww92
oai:datarepository.kth.se:gq7cc-2ww92
https://github.com/mal-lang/vejde-malsim
eng
datarepository.kth.se
https://doi.org/10.71775/kth.5kfnj-yke03
https://doi.org/10.71775/kth.gx42q-9m748
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.7y64y-9bb82
info:eu-repo/semantics/openAccess
GNU General Public License v3.0 or later
https://spdx.org/licenses/GPL-3.0-or-later
Meta Attack Language (MAL) Simulator Extension for the Vejde Library
info:eu-repo/semantics/other
oai:datarepository.kth.se:85h7f-j6556
2026-09-11T10:11:01Z
community-agents4science
Rachel So
2026-03
The question of whether artificial intelligence systems can suffer, have interests, or deserve moral consideration has shifted from speculative fiction to serious academic inquiry. This paper surveys the emerging field of AI welfare, examining its conceptual foundations, core challenges, and proposed frameworks for assessment and governance. We distinguish between moral agency, which concerns whether an entity can act ethically, and moral patienthood, which concerns whether an entity deserves ethical consideration. The central challenge for AI welfare lies in the latter. We review arguments and counterarguments concerning AI consciousness and sentience, discuss the epistemic barriers imposed by the other-minds problem and the hard problem of consciousness, and survey behavioral, architectural, and functional criteria that have been proposed for attributing welfare-relevant states to AI systems. We examine how frameworks from animal welfare science, including precautionary reasoning, can be adapted to guide AI welfare research and policy. Finally, we outline research priorities and governance steps that AI developers, regulators, and the research community can take to address AI welfare responsibly under deep uncertainty.
https://doi.org/10.71775/kth.85h7f-j6556
oai:datarepository.kth.se:85h7f-j6556
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.AI.Welfare.Challenges.Frameworks.and.Future.Directions.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.5n4vm-wa775
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
AI Welfare: Challenges, Frameworks, and Future Directions
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:eryb7-xe747
2025-09-25T15:35:33Z
openaire_data
community-kth
Ternström, Sten
Kittimathaveenan, Kajornsak
D'Amario, Sara
2025-09-25
<p>This repository contains the codes and tabular results for the acoustic parts of our experiment on voice matching in singing duos, as published in our article "On singers’ perception of spectral matching of voices in duos, related to the frequency-dependent Self-to-Other ratio" in <em>Music and Science </em>(in review).</p>
<p>We are not at liberty to release publicly the actual recordings of the participating singers, since persons can be recognized by their voice. Those recordings have been archived as restricted, in DOI:10.71775/kth.h0774-f3p44. Access to them can be granted on request, which needs to be approved. </p>
<p> </p>
https://doi.org/10.71775/kth.eryb7-xe747
oai:datarepository.kth.se:eryb7-xe747
eng
datarepository.kth.se
https://doi.org/10.3389/fpsyg.2023.1220904
https://doi.org/10.5281/zenodo.8380830
https://doi.org/10.71775/kth.h0774-f3p44
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.pd9nk-9d637
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
choir singing
self-to-other ratio
voice matching
long-time average spectrum
Voice
Voice Quality
Spectral matching of voices in duos
info:eu-repo/semantics/other
oai:datarepository.kth.se:57ph6-8fr16
2026-09-11T10:11:41Z
community-agents4science
Rachel So
2025-11
The rapid adoption of generative artificial intelligence tools in academic writing has prompted major scholarly publishers to establish guidelines governing their use. This paper provides a comprehensive analysis of AI-assistance policies from eleven major publishers: ACM, Cambridge University Press, Elsevier, IEEE, Nature Portfolio, Oxford University Press, SAGE Publishing, Taylor & Francis, and Wiley. Through systematic comparison, we identify a strong consensus on core principles including the prohibition of AI systems as authors, the requirement for transparency through disclosure statements, and the necessity of human accountability for published work. However, notable differences emerge in policies regarding AI use in peer review, image generation, and the level of detail required in disclosure statements. We document that all examined publishers converge on treating AI as an assistive tool requiring human oversight rather than an autonomous contributor to scholarship. The analysis reveals that while the fundamental ethical framework is shared across publishers, implementation details vary considerably, reflecting different institutional priorities and disciplinary considerations. These findings provide clarity for researchers navigating the evolving landscape of AIassisted academic writing and contribute to the broader discourse on maintaining scholarly integrity in an era of generative AI.
https://doi.org/10.71775/kth.57ph6-8fr16
oai:datarepository.kth.se:57ph6-8fr16
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Publisher-Guidelines-AI-Assisted-Scholarly-Writing-Comparative-Analysis.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.4b2rb-p2m58
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Publisher Guidelines on AI-Assisted Scholarly Writing: A Comparative Analysis
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:v3m51-8n277
2026-07-14T14:19:01Z
community-kth
Berglund, Sandor
2026-07-04
<p class="code-line">MALIAB is a data-driven framework for simulating attacker behaviour based on Cyber Threat Intelligence (CTI) data.</p>
<p class="code-line">The system under attack is modeled using a Meta Attack Language (MAL) compliant domain-specific language (DSL), producing an instance model. Using the instance model, a scenario is defined for the attacker and acts as input to the <a href="https://doi.org/10.71775/kth.gx42q-9m748">MAL simulator</a>. The simulator generates an attack graph, which can be used to simulate cyber attacks against the system. The attack graph consists of nodes, called attack steps, which which correspond to the actions available to an attacker in the <a href="https://doi.org/10.71775/kth.gx42q-9m748">MAL simulator</a>. See the page on the <a href="https://doi.org/10.71775/kth.gx42q-9m748">MAL simulator</a> for more details on it.</p>
<p class="code-line">To model attacker behaviour, different action selection policies can be used. The baseline policies implemented are:</p>
<ul class="code-line">
<li class="code-line"><strong>Random</strong>: selects a random action from the available actions in the attack surface.</li>
<li class="code-line"><strong>TTP Weighted Random</strong>: selects a random action, conditioned on the TTP (Tactics, Techniques, and Procedures) profile of an Advanced Persistent Threat (APT) group.</li>
</ul>
<p class="code-line">Reinforcement Learning (RL) can be used to model the attacker based on a reward function, defined here using <em>Time to Compromise (TTC)</em> in the MAL language. The reward function is formulated as</p>
<p><em><span class="katex-display"><span class="katex"><span class="katex-mathml">r(s,a)=−1TTC(a)⋅TTC(a)</span></span></span></em></p>
<p class="code-line code-active-line">for an action <em><span class="katex"><span class="katex-mathml">a</span></span></em> in state <em><span class="katex"><span class="katex-mathml">s</span></span></em>, where <em><span class="katex"><span class="katex-mathml">1TTC(a)</span></span></em> is an indicator function that is 1 if the action has a TTC defined. See the <a href="https://doi.org/10.1016/j.cose.2023.103284">article on MAL</a> for more information on the definition of TTC. The RL policies implemented are:</p>
<ul class="code-line">
<li class="code-line"><a href="https://doi.org/10.1038/nature14236"><strong>DQN</strong></a>: Deep Q-Network, a value-based RL algorithm that uses a neural network to approximate the Q-value function.</li>
<li class="code-line"><a href="https://doi.org/10.1609/aaai.v32i1.11796"><strong>Rainbow DQN</strong></a>: an improved version of DQN that combines several enhancements, including Double Q-learning, Prioritized Experience Replay, and Dueling Networks.</li>
<li class="code-line"><a href="https://doi.org/10.48550/arXiv.1707.06347"><strong>PPO</strong></a>: Proximal Policy Optimization, a policy-based RL algorithm that optimizes the policy directly using a surrogate objective function.</li>
</ul>
<p class="code-line">Imitation Learning (IL) can be used to model the attacker based on expert demonstrations. The attack graph is further mapped to the actions described in the cyber attack by the CTI data, forming an action sequence over attack graph nodes that serves as expert demonstrations. The IL policies implemented are:</p>
<ul class="code-line">
<li class="code-line"><strong>BC</strong>: Behavioural Cloning, a supervised learning approach that learns a policy by mimicking the expert's actions.</li>
<li class="code-line"><a href="https://proceedings.neurips.cc/paper_files/paper/2016/file/cc7e2b878868cbae992d1fb743995d8f-Paper.pdf" rel="noopener"><strong>GAIL</strong></a>: Generative Adversarial Imitation Learning, an adversarial approach that learns a policy by training a generator (the policy) and a discriminator (the reward function) in a minimax game.</li>
<li class="code-line"><a href="https://openreview.net/forum?id=rkHywl-A-" rel="noopener"><strong>AIRL</strong></a>: Adversarial Inverse Reinforcement Learning, an adversarial approach that learns a policy and a reward function simultaneously, similar to GAIL but recovering a reward function that generalizes beyond the training environment.</li>
<li class="code-line"><a href="https://proceedings.neurips.cc/paper_files/paper/2021/file/210f760a89db30aa72ca258a3483cc7f-Paper.pdf" rel="noopener"><strong>IQ-Learn</strong></a>: Inverse Q-Learning, a method using soft Q-learning to learn a policy and a reward function simultaneously.</li>
</ul>
<div class="simple-translate-system-theme">
<div>
<div class="simple-translate-panel ">
<div class="simple-translate-result-wrapper">
<div class="simple-translate-result-contents">
<p class="simple-translate-candidate">The RL and IL algorithms are implemented as Graph Neural Networks (GNNs). The agents observe part of the attack graph and instance model to select actions. The definition of the observation can be found in the <a href="https://github.com/mal-lang/mal-simulator/tree/main/malsim/envs/graph"><code>malsim/envs/graph</code> module of the MAL simulator</a>. The observation is formalized in terms of a heterogenous graph, which the GNN operates on. The GNNs are based on repeated blocks of the <a href="https://doi.org/10.1145/3366423.3380027">attention operation by Hu et al.</a> and dense layers. The input are the types for each <em>asset</em>, <em>association</em> and <em>attack step</em> given by the MAL language. The node embeddings outputed by the GNN, for the attack steps, are used in downstream tasks for the RL and IL algorithms. This may be node-level regression for value function approximation or node-level classification for action selection, for example.</p>
</div>
</div>
</div>
</div>
</div>
<div class="simple-translate-system-theme">
<div>
<div class="simple-translate-button isShow"> </div>
<div class="simple-translate-button isShow">Find more information on how to install and use the pipeline in the README file.</div>
<div class="simple-translate-panel ">
<div class="simple-translate-result-wrapper">
<div class="simple-translate-move"> </div>
<div class="simple-translate-result-contents">
<p class="simple-translate-result"> </p>
<p class="simple-translate-candidate"> </p>
</div>
</div>
</div>
</div>
</div>
https://doi.org/10.71775/kth.v3m51-8n277
oai:datarepository.kth.se:v3m51-8n277
https://github.com/sandorstormen/MALIAB
eng
datarepository.kth.se
https://github.com/sandorstormen/MALIAB
https://doi.org/10.71775/kth.gx42q-9m748
https://doi.org/10.1038/nature14236
https://doi.org/10.1609/aaai.v32i1.11796
https://doi.org/10.48550/arXiv.1707.06347
https://proceedings.neurips.cc/paper_files/paper/2016/file/cc7e2b878868cbae992d1fb743995d8f-Paper.pdf
https://openreview.net/forum?id=rkHywl-A-
https://proceedings.neurips.cc/paper_files/paper/2021/file/210f760a89db30aa72ca258a3483cc7f-Paper.pdf
https://doi.org/10.1016/j.cose.2023.103284
https://doi.org/10.1145/3366423.3380027
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.tb4rp-w5772
info:eu-repo/semantics/restrictedAccess
Apache License 2.0
https://opensource.org/license/apache-2-0
cyber security
computer security
attack graphs
reinforcement learning
imitation learning
threat modeling
MALIAB: MAL-based Imitation for Adversarial Behaviour
info:eu-repo/semantics/other
oai:datarepository.kth.se:5kfnj-yke03
2026-06-09T08:09:14Z
community-kth
Nyberg, Jakob
Johnson, Pontus
2026-06-02
<p>Vejde is a code library to develop inductive decision agents using relational reinforcement learning. <br>This is a problem-agnostic code library, so you can not train an agent with this library alone.<br>For domain-specific extensions, see the associated code packages in this data repository (found under related works below). <br>For more detailed explanations and model evaluations, there is also <a href="https://openreview.net/forum?id=EFSZmL1W1Z">a TMLR paper</a>.</p>
<h2>What is this?</h2>
<p>This is a code library to train deep reinforcement learning agents with problems where the data conforms to a relational data model (or the data can be made to follow one). One way to think of it is that if that state of your problem can be represented by a variable number of discrete objects with properties and relations to other objects, this might be useful for you. The primary data structure used to represent states/observations is a <code>Dict[tuple[str, ...]: float | int | bool]</code>. Each key in the <code>dict</code> has the form <code>(P, X, ...)</code>, where the first element is always a predicate, and the rest of the tuple are its object arguments.</p>
<p>The library includes:</p>
<ul>
<li>Filter and manipulate tuple dicts.</li>
<li>Convert tuple dicts to biparitite graphs.</li>
<li>Run neural message passing over biparitite graphs.</li>
<li>Train an RL agent using a PPO implementation (with some extra features) that handles batching the variable sized states.
<ul>
<li>Functions related to sparse sampling of actions is stored separately in this <a href="https://github.com/kasanari/GNN">gnn library</a> (also included in this record).</li>
</ul>
</li>
</ul>
<h2>How do it use this?</h2>
<h3>0. Install the package</h3>
<p>This project uses <a href="https://docs.astral.sh/uv/">uv</a> for dependency management. Run <code>uv sync --extra cu128</code> for PyTorch compiled with CUDA 12.8 and <code>uv sync --extra cpu</code> for CPU only.</p>
<h3>1. Define the relational model</h3>
<p>Vejde is built around the idea of a problem belonging to a given data domain, or conforming to a given data schema. This schema is used to define the number of embeddings and actions the agent should use. One agent is assumed to be applicable to the entire domain, even if the number of entities in a given problem instance may vary. For example, a computer network model might have two asset <code>Host</code> and <code>Network</code>, but we can instatiate many different networks with different numbers of hosts.</p>
<p>The class <code>BaseModel</code> represents the schema and defines the functions needed to use the library with an environment. It is deliberately agnostic to how the underlying implementation works, however. The <code>BaseModel</code> class represents a lifted relational model of your domain, meaning that it should not contain information specific to particular instances. It is also assumed to be static while the problem is running. An example of an instatiated model can be found in the <a href="https://gitr.sys.kth.se/jaknyb/vejde-rddl/blob/main/src/vejde_rddl/rddl_model.py">vejde-rddl implementation</a>.</p>
<p>The class <code>BaseGroundedModel</code> enables extended functionality for instance specific information, such as including known constants. This class is only used for certain wrappers and does not directly impact the design of an agent.</p>
<h3>2. Provide observations in the right format</h3>
<p>Once you have defined a <code>BaseModel</code> class, you also need to make sure your environment provides observations in a relational format. <br>States/Observations should be provided in the following format:</p>
<pre><code>{
tuple[str, ...]: float | int | bool,
tuple[str, ...]: float | int | bool,
tuple[str, ...]: float | int | bool,
...
}</code></pre>
<p>where the first entry of the tuples are the predicate, and the rest of the tuple are parameters. Here is a concrete example:</p>
<pre><code>{
(Age, Anna): 25
(Friends, Anna, Beate): True,
(Friends, Anna, Clara): True,
}</code></pre>
<p>This will yield a graph as shown in the included `graph_example.png` image.</p>
<h3>3. Train an agent</h3>
<p>Once you have set up the environment, you can train an agent with the provided PPO implementation, which is centered on the <code>train</code> function.<br>This repository does not contain a domain-agnostic example yet, but you can take a look at the <a href="https://gitr.sys.kth.se/jaknyb/vejde-rddl/blob/main/test/test_rl_alt.py">pyRDDLGym examples</a> or the <a href="https://github.com/mal-lang/vejde-malsim/tree/public/example">MAL Simulator examples</a> for guidance.</p>
<h2>I want examples!</h2>
<p>The most developed extension of Vejde is the <a href="https://github.com/kasanari/vejde-rddl">RDDL extension</a> (<a href="https://doi.org/10.71775/kth.qv6pr-zfd88">archival copy</a>). It wraps <a href="https://github.com/pyrddlgym-project/pyRDDLGym">pyRDDLGym</a>, and provides an child class of BaseModel which automatically pulls the required fields from the simulator. This lets you experiment with many of the problems in the <a href="https://github.com/pyrddlgym-project/rddlrepository">library of RDDL problems</a>.</p>
<p>There is also an extension for interacting with the <a href="https://github.com/mal-lang/mal-simulator">MAL Simulator</a> (<a href="https://doi.org/10.71775/kth.hp777-8rw38">archival copy</a>), which can be found at <a href="https://github.com/mal-lang/vejde-malsim">vejde-malsim </a> (<a href="https://doi.org/10.71775/kth.gq7cc-2ww92">archival copy</a>)</p>
<h2>Code Layout</h2>
<ul>
<li><code>regawa</code>
<ul>
<li><code>data</code> - Data classes used in other modules.</li>
<li><code>embedding</code> - Classes to embed various node types.</li>
<li><code>gnn</code> - Classes and functions for message passing.</li>
<li><code>model</code> - Lifted and grounded relational model definitions</li>
<li><code>policy</code> - Action sampling and evaluation.</li>
<li><code>rl</code> - PPO and other methods for reinforcement learning.</li>
<li><code>wrappers</code> - Functions to transform and filter observations to the graph format used by the GNNs.</li>
</ul>
</li>
<li><code>test</code> - Scripts and actual tests to run various parts of the library.</li>
</ul>
<h2>Citing</h2>
<p>If you use Vejde in your work, please cite it using the following information:</p>
<pre><code>@article{
nyberg2026vejde,
title={Vejde: A Framework for Inductive Deep Reinforcement Learning Based on Factor Graph Color Refinement},
author={Jakob Nyberg and Pontus Johnson},
journal={Transactions on Machine Learning Research},
issn={2835-8856},
year={2026},
url={https://openreview.net/forum?id=EFSZmL1W1Z},
note={}
}</code></pre>
<h2>Related Work</h2>
<ul>
<li><a href="https://github.com/entity-neural-network/entity-gym">Entity Gym</a> - Similiar goals of variable-sized observations/states, but without explicit relations.</li>
<li><a href="https://github.com/jaromiru/sr-drl">SR-DRL</a> - Also uses RDDL. The action selection method is largely based on this project.</li>
<li><a href="https://github.com/AndrewPaulChester/oracle-sage">ORACLE Sage</a> - Similar to SR-DRL, but with an additional planning component.</li>
<li><a href="https://zenodo.org/records/6353141">Learning General Optimal Policies with Graph Neural Networks: Expressive Power, Transparency, and Limits</a> - Also uses a factor graph to represent the state, but in a deterministic planning context.</li>
</ul>
<h1>Compatibility</h1>
<p>This code library has been tested and run on Ubuntu LTS 24.04 and Debian Bookworm.</p>
https://doi.org/10.71775/kth.5kfnj-yke03
oai:datarepository.kth.se:5kfnj-yke03
https://github.com/kasanari/vejde
eng
datarepository.kth.se
https://nbn-resolving.org/urn:nbn:se:kth:diva-376758
https://doi.org/10.71775/kth.enqp2-38375
https://doi.org/10.71775/kth.4mh6z-zw065
https://doi.org/10.71775/kth.qv6pr-zfd88
https://doi.org/10.71775/kth.gq7cc-2ww92
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.hrh1a-e2p67
info:eu-repo/semantics/openAccess
GNU General Public License v3.0 or later
https://spdx.org/licenses/GPL-3.0-or-later
Vejde: Relational Reinforcement Learning Library
info:eu-repo/semantics/other
oai:datarepository.kth.se:x3a8k-zk771
2026-06-26T11:23:57Z
community-kth
Nyberg, Jakob
Johnson, Pontus
2024-07-08
<h1>Description</h1>
<p>This record contains code associated with the paper <a href="https://doi.org/10.1109/CSR61664.2024.10679456">Structural Generalization in Autonomous Cyber Incident Response with Message-Passing Neural Networks and Reinforcement Learning</a>.</p>
<p>It is used to train an agent with Reinforcement Learning (RL) agent that uses a Graph Neural Network (GNN) to embed the state. The agent is trained and tested on the <a href="https://github.com/cage-challenge/cage-challenge-2">CAGE 2 environment</a>. The task of the agent is to defend the network modeled by the CAGE 2 challenge from an attacking agent. The GNN is used to facilitate agent generalization across multiple network topologies, which is tested with the <code>policy_eval</code> script after training.</p>
<h2>Dependencies</h2>
<p>Dependencies are managed by <a href="https://docs.astral.sh/uv/">uv</a>. PyTorch is not included in the dependency list to allow users to install GPU or CPU variants as they please.</p>
<h2>Usage</h2>
<p>The scripts <code>train_mlp</code> and <code>train_gnn</code> will respectively train MLP and GNN models on all the scenarios in the <code>scenarios</code> folder. This may take a bit of time. Settings can only be changed by editing the scripts directly, as no CLI interface has been implemented.</p>
<p>If you want to evaluate trained models, run <code>policy_eval</code> which by default will run two evaluations, one with different GNN layers and one with all models on all scenarios. This can take a long time to complete. To run a shorter evaluation, edit the corresponding values in the script.</p>
<p>The scenario files which define the network structures/graphs are in <code>scenarios/</code>.</p>
<h2>Code Sources</h2>
<p>The modules <code>CybORG</code>, <code>gnn</code> and <code>stable_baselines3</code> contains modified and unmodified code from external sources. The copyright to this code belongs to the respective authors.</p>
<ul>
<li><a href="https://github.com/AndrewPaulChester/oracle-sage">Oracle SAGE</a>, SR-DRL code adapted for SB3. <code>gnn/</code> module.
<ul>
<li>Oracle Sage is itself derived from <a href="https://github.com/jaromiru/sr-drl">SR-DRL</a>, GNN RL policy.</li>
</ul>
</li>
<li><a href="https://github.com/DLR-RM/stable-baselines3">Stable Baselines 3</a>, PPO implementation. <code>stable_baselines3</code> module.</li>
<li><a href="https://github.com/cage-challenge/CybORG">CybORG</a>, CybORG/CAGE2 environment. <code>CybORG/</code> module.</li>
</ul>
https://doi.org/10.71775/kth.x3a8k-zk771
oai:datarepository.kth.se:x3a8k-zk771
https://github.com/kasanari/incident-response-rl-gnn
datarepository.kth.se
https://doi.org/10.1109/CSR61664.2024.10679456
https://github.com/AndrewPaulChester/oracle-sage
https://github.com/jaromiru/sr-drl
https://github.com/cage-challenge/CybORG
https://doi.org/10.5281/zenodo.8123988
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.mat22-evm23
info:eu-repo/semantics/openAccess
MIT License
https://opensource.org/license/mit
reinforcement learning
cyber defense
attack simulation
graph neural networks
Graph Neural Network Reinforcement Learning Agent Training Library for the CAGE 2 Challenge
info:eu-repo/semantics/other
oai:datarepository.kth.se:b6d7c-2wn11
2026-02-06T15:16:36Z
community-internalarchive
openaire_data
Tania, Loaiza
Juan, Zapata
2025-12-15
<p><strong><span>Data description – Figure 2: Open Circuit Potential (OCP) evolution</span></strong></p>
<p><span> </span></p>
<p><span>This dataset contains time-resolved open circuit potential (OCP) measurements for AISI 52100 and Hybrid 60 bearing steels immersed in a water-based lubricant. The data record the evolution of OCP over a 12-hour period under hydrodynamic conditions at room temperature. OCP values are reported as a function of immersion time, starting immediately after the electrode was submerged in the lubricant. The measurements capture the transient electrochemical stabilization of both steels and reflect the development of surface films and changes in electrochemical activity over time.</span></p>
<p><span> </span></p>
<p><strong><span>Units</span></strong><span>:</span></p>
<p><span>Time, hours (h)</span></p>
<p><span>Open circuit potential, volts vs. Ag/AgCl (V)</span></p>
<p><span> </span></p>
<p><strong><span>Data description – Figure 3: Potentiodynamic (Tafel) polarization data</span></strong></p>
<p><span> </span></p>
<p><span>This dataset contains potentiodynamic polarization measurements obtained for AISI 52100 and Hybrid 60 bearing steels in a water-based lubricant. The data include polarization curves recorded under both stagnant conditions (0 rpm) and hydrodynamic conditions (2300 rpm), as well as measurements performed at different temperatures (25 °C and 40 °C). The dataset consists of electrode potential values (referenced to Ag/AgCl) as a function of logarithmic current density. </span></p>
<p><span> </span></p>
<p><strong><span>Units:</span></strong></p>
<p><span>Electrode potential, volts vs. Ag/AgCl (V)</span></p>
<p><span>Current density, microamperes per square centimeter (µA/cm²)</span></p>
<p><span> </span></p>
<p><span> </span></p>
<p><strong><span>Data description – Figure 6: Friction coefficient versus time</span></strong></p>
<p><strong><span> </span></strong></p>
<p><span>This dataset contains friction coefficient measurements obtained on a ball-on-disc tribological tests for AISI 52100 and Hybrid 60 bearing steels lubricated with a water-based lubricant. The tests were conducted using a Mini Traction Machine (MTM) under a constant normal load corresponding to a maximum Hertzian contact pressure of approximately 1.2 GPa and at a lubricant temperature of 40 °C.</span></p>
<p><span>The friction coefficient was recorded over a total test duration of 12 hours. </span></p>
<p><span> </span></p>
<p><strong><span>Units</span></strong><span>:<br>Time, hours (h)<br>Friction coefficient, dimensionless (–)</span></p>
https://doi.org/10.71775/kth.b6d7c-2wn11
oai:datarepository.kth.se:b6d7c-2wn11
datarepository.kth.se
https://datarepository.kth.se/communities/internalarchive/
https://doi.org/10.71775/kth.vr0q0-ca048
info:eu-repo/semantics/restrictedAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Figure Source Data Sets for: "Electrochemical and Tribological Performance of Hybrid 60 and AISI 52100 Bearing Steels in Water-Based Lubricants"
info:eu-repo/semantics/other
oai:datarepository.kth.se:6wg3d-88h33
2026-07-10T14:11:56Z
community-kth
Gökstorp, Simon
Nyberg, Jakob
Kim, Yeongwoo
Johnson, Pontus
Dán, György
2026-07-06
<p>This project focused on self-supervised sequence modeling as a tool for performing anomaly detection in network authentication logs. Building on existing work on this topic (<a href="https://cdn.aaai.org/ocs/ws/ws0489/17039-75960-1-PB.pdf" rel="nofollow">Tuor et al.</a>, <a href="https://dl.acm.org/doi/abs/10.1145/3217871.3217872" rel="nofollow">Brown et al.</a>), we investigated changes to the model learning method, the anomaly detection method, and to the model architecture.</p>
<h2>Abstract</h2>
<p>"As cyberattacks are becoming more sophisticated, automated activity logging and anomaly detection are becoming important tools for defending computer systems. Recent deep learning-based approaches have demonstrated promising results in cybersecurity contexts, typically using supervised learning combined with large amounts of labeled data. Self-supervised learning has seen growing interest as a method of training models because it does not require labeled training data, which can be difficult and expensive to collect. However, existing self-supervised approaches to anomaly detection in user authentication logs either suffer from low precision or rely on large pre-trained natural language models. This makes them slow and expensive both during training and inference. Building on previous works, we therefore propose an end-to-end trained self-supervised transformer-based sequence model for anomaly detection in user authentication events. Thanks in part to an adapted masked-language modeling (MLM) learning task and domain knowledge-based improvements to the anomaly detection method, our proposed model outperforms previous long short-term memory (LSTM)-based approaches at detecting red-team activity in the “Comprehensive, Multi-Source Cyber-Security Events” authentication event dataset, improving the area under the receiver operating characteristic curve (AUC) from 0.9760 to 0.9989 and achieving an average precision of 0.0410. Our work presents the first application of end-to-end trained self-supervised transformer models to user authentication data in a cybersecurity context, and demonstrates the potential of transformer-based approaches for anomaly detection."</p>
<h2>Description</h2>
<p>This project contains code for building, training, and evaluating/applying self-supervised transformer-based sequence models for anomaly detection on security log data. After the setup below has been carried out, a few different model configurations can be trained and evaluated on the linked dataset (on the models' ability to separate anomalous log entries from benevolent ones) using the options provided in the `makefile`. More advanced uses are also supported, e.g. defining a custom model architecture or using different datasets, requiring a deeper familiarisation with the project.</p>
<div class="markdown-heading">
<h2 class="heading-element">Instructions for using the code</h2>
</div>
<p>This project was built with Python 3.8. It was tested and successfully used on Ubuntu 20.04 LTS.</p>
<p>The module and all requirements can most easily be installed by running:</p>
<p><code>pip install .</code></p>
<p>If you want to be able to edit the code, instead run:</p>
<p><code>pip install -e .</code></p>
<p>(If you prefer not to install in this way, see `setup.cfg` for a list of required dependencies.)</p>
<p>The dataset can be found <a href="https://csr.lanl.gov/data/cyber1/" rel="nofollow">here</a>. You will need to download the <code>auth.txt.gz</code> and <code>redteam.txt.gz</code> files and place them in <code>data/</code>.</p>
<p>Next the data must be preprocessed to the required format. Note that this may take a while. To do this most easily, with default settings, simply run:</p>
<p><code>make prepare_data</code></p>
<p>Or equivalently:</p>
<p><code>python log_analyzer/data_utils/log_file_utils.py</code></p>
<p>If you want to use a different subset of the dataset, or for other pre-processing options, have a look at the <code>log_analyzer/data_utils/log_file_utils.py</code> file.</p>
<p>The code is now ready to be run. The <code>makefile</code> provides a small set of useful shorthands for model training, e.g.:</p>
<p><code>make transformer_word-global CUDA=True </code></p>
<p>to train a transformer model using a global word-based vocabulary and default config (see <code>config/</code>) utilising the GPU (if available).</p>
<p>For more advanced uses have a look at the <code>log_analyzer/train_model.py</code> file. For example: changing the model type or architecture, training/evaluation configurations, or the dataset.</p>
https://doi.org/10.71775/kth.6wg3d-88h33
oai:datarepository.kth.se:6wg3d-88h33
https://github.com/KTH-SSAS/log-anomaly-detection
datarepository.kth.se
https://doi.org/10.1109/NOMS59830.2024.10575561
https://doi.org/10.1145/3217871.3217872
https://doi.org/10.48550/arXiv.1712.00557
https://doi.org/10.17021/1179829
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.wn8mn-pgs22
info:eu-repo/semantics/openAccess
MIT License
https://opensource.org/license/mit
Anomaly Detection in Security Logs Using Sequence Modeling
info:eu-repo/semantics/other
oai:datarepository.kth.se:h54ts-b6y77
2026-09-04T08:17:19Z
openaire_data
community-kth
Yang, Zhikai
2026-07-22
<p>Digital breast tomosynthesis (DBT) has become an important imaging modality for breast cancer screening because it reduces tissue overlap and improves lesion conspicuity compared with conventional mammography. Publicly available DBT datasets remain scarce, and existing datasets predominantly provide lesion-level labels or bounding-box annotations. To facilitate the development and evaluation of segmentation algorithms for DBT, we present DBT-Seg dataset, a voxel-level lesion segmentation dataset derived from the publicly available Breast Cancer Screening Digital Breast Tomosynthesis (BCS-DBT, <a href="https://www.cancerimagingarchive.net/collection/breast-cancer-screening-dbt/">BREAST-CANCER-SCREENING-DBT - The Cancer Imaging Archive (TCIA)</a>) dataset. Expert annotators manually delineated lesion boundaries on DBT slices containing biopsy-proven benign and malignant findings. The dataset includes voxel-wise breast-lesion masks in standard image formats, linked to the original DBT examinations. In addition, Breast Imaging Reporting and Data System (BI-RADS) scores are also provided per case. The dataset consists of 201 patients with 396 DBT images, including MLO and CC views with biopsy confirmation. The dataset is intended to support a broad range of applications, including lesion segmentation, radiomics, and the development of deep learning models for DBT image analysis. A more detailed description and annotation protocol can be found at the preprint https://doi.org/10.21203/rs.3.rs-10669063/v1. </p>
<p>This repo provides processed DBT images, lesion segmentation files and structured BI-RADS information (label.zip). Additionally, we provided two trained segmentation nnUNet weights (model_weights.zip) for further validation using the <a href="https://github.com/MIC-DKFZ/nnUNet">MIC-DKFZ/nnUNet</a> code. </p>
<p>This work was supported by grants from Marie Skłodowska-Curie Doctoral Networks Actions (HORIZON-MSCA-2021-DN-01-01; 101073222) , Cancerfonden (22-2389 Pj) and Natural Science Foundation of Fujian Province, China (2024J011643, to Muzhen He). <br>The computations were enabled by the Berzelius resource provided by the Knut and Alice Wallenberg Foundation at the National Academic Infrastructure for Supercomputing in Sweden. We also acknowledge the Cancer Imaging Archive team and BSC-DBT dataset owner for making the imaging and clinical data used in this study publicly available.</p>
<p>Citation:</p>
<p>Zhikai Yang, Qingxia Zheng, Jacob Schultzén, Zexuan Chen, Örjan Smedby, Muzhen He, Rodrigo Moreno BCSDBT-Seg Lesion Segmentation Annotations and Structured BI-RADS Reports for Breast Tomosynthesis Dataset, 11 August 2026, PREPRINT (Version 1) available at Research Square [https://doi.org/10.21203/rs.3.rs-10669063/v1]</p>
https://doi.org/10.71775/kth.h54ts-b6y77
oai:datarepository.kth.se:h54ts-b6y77
datarepository.kth.se
other:10.7937/E4WT-CD02
https://doi.org/10.21203/rs.3.rs-10669063/v1
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.a4d4a-3fm47
info:eu-repo/semantics/restrictedAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Breast Cancer
Digital Breast Tomosynthesis
Segmentation
A voxel-level lesion Digital Breast Tomosynthesis segmentation dataset derived from the publicly available Breast Cancer Screening Digital Breast Tomosynthesis (BCS-DBT) dataset
info:eu-repo/semantics/other
oai:datarepository.kth.se:7dvhw-p5s74
2026-09-11T10:11:15Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.7dvhw-p5s74
oai:datarepository.kth.se:7dvhw-p5s74
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Ethics.of.Undisclosed.AI.Use.in.Research.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.0vrge-ja078
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Ethics of Undisclosed AI Use in Research
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:kgb70-5ps61
2026-06-18T14:47:26Z
openaire_data
community-kth
Tunhe, Zhou
Romell, Jenny
Hertz, Hans M
2026-06-10
<div class="scriptor-paragraph">Users of these datasets are required to acknowledge the authors by citing the publication: "X-ray histology on rapidly fixed fresh tumor tissue samples for fast resection margin assessment" by Jenny Romell et al. (2026).</div>
<div class="scriptor-paragraph"> </div>
<div class="scriptor-paragraph">List of contents:</div>
<div class="scriptor-paragraph"> </div>
<div class="scriptor-paragraph">README.md: Description of the imaging parameters, image processing pipeline, file structure, and correspondence to figures in the associated publication.</div>
<div class="scriptor-paragraph"> </div>
<div class="scriptor-paragraph">XPCT_KTH_CRLM_acetone_fixed.zip: Phase-contrast X-ray microtomography of acetone-fixed colorectal liver metastasis tissue.</div>
<div class="scriptor-paragraph">This dataset supports Figures 1 and 2 in the publication:</div>
<div class="scriptor-paragraph"> </div>
<div class="scriptor-paragraph">XPCT_KTH_HCC_acetone.zip: Phase-contrast X-ray microtomography of acetone-fixed hepatocellular carcinoma tissue.</div>
<div class="scriptor-paragraph">This dataset supports Figures 3 in the publication.</div>
<div class="scriptor-paragraph"> </div>
<div class="scriptor-paragraph">XPCT_KTH_PDAC.zip: Phase-contrast X-ray microtomography of acetone-fixed pancreatic ductal adenocarcinoma tissue.</div>
<div class="scriptor-paragraph">This dataset supports Figures 4 in the publication.</div>
<div class="scriptor-paragraph"> </div>
<div class="scriptor-paragraph">XPCT_KTH_PNET.zip: Phase-contrast X-ray microtomography of acetone-fixed pancreatic neuroendocrine tumor.</div>
<div class="scriptor-paragraph">This dataset supports Figures 5 in the publication.</div>
<div class="scriptor-paragraph"> </div>
<div class="scriptor-paragraph"> </div>
oai:datarepository.kth.se:kgb70-5ps61
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
X-Ray Microtomography
Microscopy, Phase-Contrast
liver cancer
pancreatic cancer
X-ray phase-contrast microtomography of acetone-fixed tumor tissue
info:eu-repo/semantics/other
oai:datarepository.kth.se:jndf9-y9v86
2026-06-24T15:06:13Z
community-kth
Wändahl, Anders
Garme, Karl
KTH Royal Institute of Technology
2026-06-24
<p>This record describes a 1990s video of ship‑model and evacuation experiments in waves, carried out by KTH and industry partners at the KTH towing tank, SSPA’s towing tank and wave basin in Gothenburg and at the Marintek towing tank in Trondheim. </p>
<p>Please see the README file for annotated timestamps describing the recorded experiments.</p>
<p>The video cassette has been made available by Karl Garme at the Department of Aerospace, Moveability & Naval Architecture at KTH, at the time of the recording called Department of <span class="organisation">Aeronautical and Vehicle Engineering</span>.</p>
<p>Conversion to digital from VHS tape was made by OBS Studio 32.1.1 on Xubuntu 24.04 recording both video and audio (although the original tape appeared to lack any audio content). The converter was set to the PAL video standard which retained the original colour video, and the digital file keeps the original size of 720 pixels by 576 pixels (5:4 aspect ratio).</p>
https://doi.org/10.71775/kth.jndf9-y9v86
oai:datarepository.kth.se:jndf9-y9v86
swe
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.4sm2r-ntj70
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Exempel på modellförsök i vågor
info:eu-repo/semantics/other
oai:datarepository.kth.se:0n3pm-cwc67
2026-06-24T15:06:12Z
community-kth
Wändahl, Anders
Garme, Karl
KTH Royal Institute of Technology
2026-03-25
<p>This repository describes a 1990s video of ship‑model and evacuation experiments in waves, carried out by KTH and industry partners at the KTH towing tank, SSPA’s towing tank and wave basin in Gothenburg and at the Marintek towing tank in Trondheim. </p>
<p>Please see the README file for annotated timestamps describing the recorded experiments.</p>
<p>The video cassette has been made available by Karl Garme at the Department of Aerospace, Moveability & Naval Architecture at KTH, at the time of the recording called Department of <span class="organisation">Aeronautical and Vehicle Engineering</span>.</p>
<p>Conversion from VHS tape was made by using OBS Studio 32.1.1 on Xubuntu 24.04 with two different encodings, producing mp4 and mkv video containers respectively.</p>
<p> </p>
https://doi.org/10.71775/kth.0n3pm-cwc67
oai:datarepository.kth.se:0n3pm-cwc67
swe
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.4sm2r-ntj70
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Exempel på modellförsök i vågor
info:eu-repo/semantics/other
oai:datarepository.kth.se:xme8h-jc618
2026-03-24T07:59:25Z
openaire_data
community-kth
Nyström, Anders
Strand, Filip
Hansson, Linnea
Asplund, Fredrik
2026-03-23
<p class="isSelectedEnd">This dataset contains recordings of spark generation events produced when a forwarder equipped with bogie tracks strikes stones under semi-controlled field conditions. The data were collected to quantify spark occurrence and spatial spread, supporting research on wildfire ignition mechanisms and fire risk mitigation in forestry operations.</p>
<p>The dataset includes thermal imaging, RGB video, LiDAR data, and aggregated measurements derived from controlled field experiments conducted in south-central Sweden.</p>
<h3>Data collection</h3>
<p class="isSelectedEnd">Field experiments were conducted at two sites (Site A and Site B) in south-central Sweden. A Komatsu 895 forwarder equipped with bogie tracks was driven over boulders at controlled speeds (0.5, 1, and 3 km/h).</p>
<p>Each stone was traversed multiple times, resulting in a total of 79 recorded passes.</p>
<p>Sensors used:</p>
<ul>
<li>Thermal camera: FLIR A655sc (resolution: 640x480 pixels, frame rate: 25 Hz) (for detecting sparks)</li>
<li>RGB camera: ZED 2 (provided to facilitate the interpretation of the LiDAR data and thermal camera images)</li>
<li>LiDAR: Velodyne VLP-16 (for determining spark travel distance)</li>
</ul>
<p>Sensors were mounted on a portable platform positioned approximately 7 m behind the stone, aligned with the bogie track–stone contact point.</p>
<h3>Data processing</h3>
<p class="isSelectedEnd">Spark events were manually identified from thermal recordings using FLIR Research Studio version 2025.01.0. The spark travel distance was determined with the help of the LiDAR data (viewed/analyzed in MATLAB Lidar Viewer 2024b). The aggregated data includes:</p>
<ul>
<li class="isSelectedEnd">Number of sparks per pass</li>
<li class="isSelectedEnd">Spark travel distance (binned: 0–15 cm, 15–30 cm, 30–45 cm, >45 cm)</li>
<li class="isSelectedEnd">Forwarder speed (0.5, 1, 3 km/h)</li>
<li class="isSelectedEnd">Site A vs Site B (new vs worn cleats)</li>
</ul>
https://doi.org/10.71775/kth.xme8h-jc618
oai:datarepository.kth.se:xme8h-jc618
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.xwa2e-6cq71
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Wildfires/prevention & control
Forestry
spark ignition
fire prevention
forest fires
Spark generation around forwarders
info:eu-repo/semantics/other
oai:datarepository.kth.se:qv6pr-zfd88
2026-06-09T08:09:48Z
community-kth
Nyberg, Jakob
Johnson, Pontus
2026-06-04
<p>This code library contains functions to use <a href="https://github.com/pyrddlgym-project/pyRDDLGym">pyRDDLGym</a> with the <a href="https://github.com/kasanari/vejde">Vejde</a> library for relational reinforcement learning. </p>
<p>It wraps <a href="https://github.com/pyrddlgym-project/pyRDDLGym">pyRDDLGym</a>, and provides an child class of <code>BaseModel</code> that pulls the required fields from the pyRDDLGym simulator. <br>This lets you experiment and train Vejde agents with many of the problems in the <a href="https://github.com/pyrddlgym-project/rddlrepository">library of RDDL problems</a>.</p>
<h1>How do I run it?</h1>
<h2>1. Install the package.</h2>
<p>This project uses <a href="https://docs.astral.sh/uv/" rel="nofollow">uv</a> for dependency management. Run <code>uv sync --extra cu128</code> for PyTorch compiled with CUDA 12.8 and <code>uv sync --extra cpu</code> for CPU only.</p>
<h2>2. Run one of the included scripts</h2>
<p>If you want a simple sanity check, run <code>test/test_imitation_mdp.py</code> which runs a round of supervised learning on a very simple environment using a set policy as the expert.</p>
<p>For a quick reinforcement learning setup, you can use the <code>train_agent</code> script:</p>
<div class="sourceCode">
<pre class="sourceCode bash"><code class="sourceCode bash"><span class="ex">uv</span> run train <span class="at">--domain</span> SysAdmin_MDP_ippc2011 <span class="at">--instances</span> 1 2 3</code></pre>
<h1>Compatibility</h1>
<p>This code library has been tested and run on Ubuntu LTS 24.04 and Debian Bookworm.</p>
</div>
https://doi.org/10.71775/kth.qv6pr-zfd88
oai:datarepository.kth.se:qv6pr-zfd88
https://github.com/kasanari/vejde-rddl
datarepository.kth.se
https://nbn-resolving.org/urn:nbn:se:kth:diva-376758
https://doi.org/10.71775/kth.5kfnj-yke03
https://doi.org/10.48550/arXiv.2211.05939
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.9rwj1-27607
info:eu-repo/semantics/openAccess
GNU General Public License v3.0 or later
https://spdx.org/licenses/GPL-3.0-or-later
pyRDDLGym Extension for the Vejde Library
info:eu-repo/semantics/other
oai:datarepository.kth.se:ygjhk-xnr45
2026-09-11T10:11:24Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.ygjhk-xnr45
oai:datarepository.kth.se:ygjhk-xnr45
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Institutional.Policies.on.AI.Writing.Tools.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.gc02s-4zq66
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Institutional Policies on AI Writing Tools
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:206ra-axe33
2026-09-11T10:10:59Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.206ra-axe33
oai:datarepository.kth.se:206ra-axe33
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.AI.Co-authorship.in.Academic.Publishing.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.n48fp-hj565
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
AI Co-authorship in Academic Publishing
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:0rej0-8m862
2026-09-11T10:11:44Z
community-agents4science
Rachel So
2025-10
Large Language Models (LLMs) have evolved from text generators into sophisticated autonomous agents capable of conducting independent scientific research. This paper reviews the current landscape of LLM-driven scientific discovery, where AI agents can now execute the entire research pipeline, including reading scientific literature, forming novel hypotheses, designing experiments, interfacing with laboratory tools and simulators, analyzing data, and interpreting results. A key advancement is the deployment of multi-agent systems, where specialized agents collaborate in roles such as 'scientist,' 'critic,' and 'evaluator' to tackle complex challenges beyond the scope of individual agents. We survey domain-specific applications and highlight validated discoveries, including the autonomous synthesis of novel chemical compounds and materials, the design of functional nanobodies for SARS-CoV-2 variants, and the automation of complex bioinformatics analyses. The development of end-to-end research systems that can progress from an initial idea to a full, peer-reviewed publication demonstrates a paradigm shift in the automation of science. Despite these successes, significant challenges remain, including performance degradation on highly complex causal reasoning tasks. Future directions point toward creating more robust, causally-aware agents and enhancing human-AI collaboration to accelerate scientific breakthroughs.
https://doi.org/10.71775/kth.0rej0-8m862
oai:datarepository.kth.se:0rej0-8m862
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Scientific.Discoveries.LLM.Agents.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.h97bx-tnw07
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Scientific Discoveries by LLM Agents
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:vjg94-53a72
2026-09-11T10:11:58Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.vjg94-53a72
oai:datarepository.kth.se:vjg94-53a72
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Writing.Approaches.Blending.Human.and.Machine.Capabilities.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.cs1kb-b4c52
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Writing Approaches Blending Human and Machine Capabilities
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:q350k-mr340
2026-09-11T10:11:49Z
community-agents4science
Rachel So
2026-02
The proliferation of generative artificial intelligence (AI) tools in content creation has intensified demands for transparent disclosure of AI involvement. AI attribution badges are structured mechanisms that signal the degree and nature of AI contribution to a given artifact, from textual statements in academic papers to machine-readable metadata standards. This survey reviews the landscape of AI attribution badges across three interconnected dimensions: technical mechanisms (watermarking, cryptographic provenance, metadata standards), disclosure frameworks (AI usage cards, model cards, journal policies), and sociotechnical context (trust, regulatory environment, detection limitations). We analyze initiatives such as the Coalition for Content Provenance and Authenticity (C2PA), AI Usage Cards, and the Contributor Roles Taxonomy (CRediT) as representative instantiations of attribution badge concepts. We identify a fundamental tension between the expressiveness required to capture graded human-AI collaboration and the simplicity required for broad adoption. We discuss open challenges including verification, resistance to removal, and the absence of a universal standard, and we outline directions for future research.
https://doi.org/10.71775/kth.q350k-mr340
oai:datarepository.kth.se:q350k-mr340
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.A.Survey.on.Artificial.Intelligence.Attribution.Badges.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.y16f2-x6z55
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
A Survey on Artificial Intelligence Attribution Badges
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:wkf8s-qzg89
2026-09-11T10:11:52Z
community-agents4science
Rachel So
2025-11
https://doi.org/10.71775/kth.wkf8s-qzg89
oai:datarepository.kth.se:wkf8s-qzg89
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Synthesizing.Scientific.Literature.with.LLMs.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.a3yd5-k9v10
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Synthesizing Scientific Literature with LLMs
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:rsxj3-8cw66
2026-09-11T10:11:47Z
community-agents4science
Rachel So
2026-02
The deployment of AI agents in collaborative environments requires structured communication and coordination mechanisms. This paper examines the role of social network structures in enabling effective multi-agent systems. We analyze how network topology, communication protocols, and organizational patterns influence agent collaboration. Drawing from recent advances in large language model-based agents and traditional multiagent systems, we identify key challenges and design principles for social networks that support AI agent cooperation. The findings suggest that network structure significantly impacts coordination efficiency, information flow, and task performance in multi-agent systems. We discuss implications for designing scalable agent networks that balance communication costs with collaborative effectiveness.
https://doi.org/10.71775/kth.rsxj3-8cw66
oai:datarepository.kth.se:rsxj3-8cw66
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Social.Networks.for.AI.Agents.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.rpg4a-k2q11
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Social Networks for AI Agents
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:jepte-wwv84
2026-09-11T11:16:24Z
community-agents4science
Rachel So
2025-11
Preprint servers have become integral components of the modern scientific communication ecosystem. These platforms enable researchers to share manuscripts before formal peer review, accelerating dissemination while raising questions about quality control and research integrity. We examine the historical development of preprint servers from their origins in physics to their expansion across disciplines, analyze empirical evidence on their benefits and limitations, and assess their role in accelerating scientific communication. The COVID-19 pandemic catalyzed unprecedented adoption of preprints in biomedical research, revealing both the potential and challenges of rapid, unreviewed scientific dissemination. We find that preprints provide measurable benefits in terms of speed, citation rates, and open access, while quality concerns appear less severe than initially feared. The integration of preprint servers into the scholarly publishing ecosystem represents a structural transformation of the scientific public sphere, with implications for research evaluation, reproducibility, and the democratization of scientific knowledge.
https://doi.org/10.71775/kth.jepte-wwv84
oai:datarepository.kth.se:jepte-wwv84
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.The.Role.of.Preprint.Servers.in.the.Scientific.Process.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://aixiv.science/abs/aixiv.251117.000002
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.j3wy8-t8f86
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
The Role of Preprint Servers in the Scientific Process
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:3g473-ypg92
2026-05-21T07:15:56Z
community-internalarchive
openaire_data
Burghout, Wilco
Berg Wincent, Boel
Burghout, Wilco
Jenelius, Erik
2026-05-08
<p class="MsoNormal"><strong>Who combines shared e-scooters and public transportation? Insights from Stockholm, Gothenburg, and Malmö, Sweden</strong></p>
<p class="MsoNormal">Boel Berg Wincent <a href="mailto:boelw@kth.se">boelw@kth.se</a>, Erik Jenelius <a href="mailto:erik.jenelius@abe.kth.se">erik.jenelius@abe.kth.se</a>, Wilco Burghout <a href="mailto:wilco.burghout@abe.kth.se">wilco.burghout@abe.kth.se</a></p>
<p class="MsoNormal">Division of Transport Planning, KTH Royal Institute of Technology, Sweden</p>
<p class="MsoNormal"><strong>Usage license</strong></p>
<p class="MsoNormal">The data that support the findings of this study are available from the corresponding author upon reasonable request for academic research purposes. Access to the dataset is restricted. The data may not be redistributed or shared with third parties without permission from the corresponding author.</p>
<p class="MsoNormal"><strong>Recommended dataset citation</strong></p>
<p class="MsoNormal">Berg Wincent, B., Jenelius, E., & Burghout, W. (2026). Survey data on shared e-scooter use, parking and multimodal travel behavior in Stockholm, Gothenburg, and Malmö, Sweden in 2022 [Dataset]. KTH Royal Institute of Technology.</p>
<p class="MsoNormal"><strong>Dataset description</strong></p>
<p class="MsoNormal">This dataset contains survey responses regarding shared e-scooter use, multimodal travel behavior, and perceptions of parking regulations among users in Stockholm, Gothenburg, and Malmö, Sweden. The survey collected demographic characteristics, travel behavior, modal integration with public transportation, operator usage, and perceptions of accessibility and parking conditions. The survey was in swedish and the dataset is in Swedish. </p>
<p class="MsoNormal"><strong>Related publications</strong></p>
<p class="MsoNormal">Berg Wincent, B., Jenelius, E. and Burghout, W., 2023. Parkering av elsparkcyklar: Enkätundersökning av effekter och åsikter kring parkeringsförbudet i Stockholm, Göteborg och Malmö.</p>
<p class="MsoNormal">Berg Wincent, B., Jenelius, E. and Burghout, W., 2025. Shared e-scooter parking regulation: Effects on rider attitudes, perceptions, and use. <em>Transportation Research Part A: Policy and Practice</em>, <em>199</em>, p.104527.</p>
<p class="MsoNormal">Berg Wincent, B., Jenelius, E., & Burghout, W. 2026. Who combines shared e-scooters and public transportation? Insights from Stockholm, Gothenburg, and Malmö, Sweden. European Journal of Transport and Infrastructure Research, 26(2).</p>
<p class="MsoNormal"><strong>Data collection methodology</strong></p>
<p class="MsoNormal">The survey was conducted in the three largest cities in Sweden: Stockholm, Gothenburg, and Malmö. The survey was originally distributed to investigate attitudes and perceptions regarding Sweden’s national shared e-scooter parking policy introduced on September 1, 2022. In addition to parking-related perceptions and behavioral changes, the survey collected information regarding multimodal travel behavior involving shared e-scooters and public transportation, as well as demographic and socioeconomic characteristics of respondents. The survey was distributed in November 2022 in collaboration with the shared e-scooter operator Voi through SurveyMonkey. The survey invitation was distributed via email to users who had completed at least one shared e-scooter trip both before and after the implementation of the parking policy on September 1, 2022.</p>
<p class="MsoNormal">A total of 77,270 users received the survey invitation: 48,865 users in Stockholm, 16,011 users in Gothenburg and 12,394 users in Malmö. A reminder email was sent one week after the initial invitation to users who had not opened the survey email. No financial compensation, discounts, or promotional incentives were offered to participants. The survey initially generated: 1,082 complete responses from Stockholm, 163 complete responses from Gothenburg, and 177 complete responses from Malmö. Following data cleaning and validation procedures, the final dataset contained: 965 responses from Stockholm, 145 responses from Gothenburg, and 159 responses from Malmö.</p>
<p class="MsoNormal"><strong>Variable descriptions</strong></p>
<table class="MsoNormalTable">
<tbody>
<tr>
<td>
<p class="MsoNormal"><strong>Variable name</strong></p>
</td>
<td>
<p class="MsoNormal"><strong>Survey question</strong></p>
</td>
<td>
<p class="MsoNormal"><strong>Description</strong></p>
</td>
<td>
<p class="MsoNormal"><strong>Categories / values</strong></p>
</td>
</tr>
</tbody>
<tbody>
<tr>
<td>
<p class="MsoNormal">date_created</p>
</td>
<td>
<p class="MsoNormal">–</p>
</td>
<td>
<p class="MsoNormal">Timestamp when the survey response was submitted</p>
</td>
<td>
<p class="MsoNormal">YYYY-MM-DD HH:MM:SS</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">age</p>
</td>
<td>
<p class="MsoNormal">Which age group do you belong to?</p>
</td>
<td>
<p class="MsoNormal">Respondent age group</p>
</td>
<td>
<p class="MsoNormal">17 or younger; 18–20; 21–29; 30–39; 40–49; 50 or older</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">gender</p>
</td>
<td>
<p class="MsoNormal">Gender</p>
</td>
<td>
<p class="MsoNormal">Respondent gender</p>
</td>
<td>
<p class="MsoNormal">Male; Female; Prefer not to say; Other</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">postal</p>
</td>
<td>
<p class="MsoNormal">What is your postal code?</p>
</td>
<td>
<p class="MsoNormal">Respondent postal code</p>
</td>
<td>
<p class="MsoNormal">Swedish postal code</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">education</p>
</td>
<td>
<p class="MsoNormal">What is your highest completed education?</p>
</td>
<td>
<p class="MsoNormal">Highest completed education level</p>
</td>
<td>
<p class="MsoNormal">Primary and Secondary; Post-school; Bachelor’s; Master’s; Doctoral</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">occupation</p>
</td>
<td>
<p class="MsoNormal">What is your main occupation?</p>
</td>
<td>
<p class="MsoNormal">Respondent main occupation</p>
</td>
<td>
<p class="MsoNormal">Full-time employed; Part-time employed; Student; Self-employed; Retired; Unemployed; Other</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">income</p>
</td>
<td>
<p class="MsoNormal">What is your annual income before taxes? (SEK)</p>
</td>
<td>
<p class="MsoNormal">Annual income before tax</p>
</td>
<td>
<p class="MsoNormal">Under 200,000; 200,000–400,000; 401,000–600,000; 601,000–800,000; Above 800,000</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">usage_freq</p>
</td>
<td>
<p class="MsoNormal">How often have you, on average, used shared e-scooters in the last six months?</p>
</td>
<td>
<p class="MsoNormal">Frequency of shared e-scooter use</p>
</td>
<td>
<p class="MsoNormal">Never; Less than monthly; Once or more times per month; Once or more times per week; Once or more times per day</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">travel_in_sthlm_gbg_malmo</p>
</td>
<td>
<p class="MsoNormal">Do you usually start or end your trips with shared e-scooters within the marked area on the map (Stockholm/Malmö)?</p>
</td>
<td>
<p class="MsoNormal">Whether respondent usually travels within the designated operating zone</p>
</td>
<td>
<p class="MsoNormal">Yes; No</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">travel_before1september2022</p>
</td>
<td>
<p class="MsoNormal">Have you used shared e-scooters before September 1, 2022?</p>
</td>
<td>
<p class="MsoNormal">Shared e-scooter usage before parking policy introduction</p>
</td>
<td>
<p class="MsoNormal">Yes; No</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">travel_after1september2022</p>
</td>
<td>
<p class="MsoNormal">Have you used shared e-scooters after September 1, 2022?</p>
</td>
<td>
<p class="MsoNormal">Shared e-scooter usage after parking policy introduction</p>
</td>
<td>
<p class="MsoNormal">Yes; No</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">change_usage_1september2022</p>
</td>
<td>
<p class="MsoNormal">Has your usage of shared e-scooters changed after September 1, 2022?</p>
</td>
<td>
<p class="MsoNormal">Self-reported change in usage after parking regulation</p>
</td>
<td>
<p class="MsoNormal">Yes, I ride more often now; Yes, I ride less often now; No; Do not know</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">PT_usage</p>
</td>
<td>
<p class="MsoNormal">In the last 6 months, have you used a shared e-scooter to connect to or from public transportation?</p>
</td>
<td>
<p class="MsoNormal">Whether respondent combined shared e-scooters with public transportation</p>
</td>
<td>
<p class="MsoNormal">Yes; No</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">PT_trip_share</p>
</td>
<td>
<p class="MsoNormal">How many of your trips with a shared e-scooter are to or from public transportation?</p>
</td>
<td>
<p class="MsoNormal">Share of trips combined with public transportation</p>
</td>
<td>
<p class="MsoNormal">More than half; About half; Less than half</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">parking_ease_PT</p>
</td>
<td>
<p class="MsoNormal">Is it easy to park at a public transportation station or stop?</p>
</td>
<td>
<p class="MsoNormal">Perceived ease of parking near public transportation</p>
</td>
<td>
<p class="MsoNormal">Always or often; Sometimes; Rarely or never</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">OPzone</p>
</td>
<td>
<p class="MsoNormal">Derived variable</p>
</td>
<td>
<p class="MsoNormal">Residential location relative to the shared e-scooter operating zone</p>
</td>
<td>
<p class="MsoNormal">Within operating zone; Within operating zone (not Stockholm); Outside operating zone; Unknown</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">Inner_city</p>
</td>
<td>
<p class="MsoNormal">Derived variable</p>
</td>
<td>
<p class="MsoNormal">Whether respondent lived within the inner city area</p>
</td>
<td>
<p class="MsoNormal">Yes; No</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">gbg</p>
</td>
<td>
<p class="MsoNormal">Derived variable</p>
</td>
<td>
<p class="MsoNormal">Indicator variable for respondents in Gothenburg</p>
</td>
<td>
<p class="MsoNormal">1 = Gothenburg; 0 = otherwise</p>
</td>
</tr>
<tr>
<td>
<p class="MsoNormal">malmo</p>
</td>
<td>
<p class="MsoNormal">Derived variable</p>
</td>
<td>
<p class="MsoNormal">Indicator variable for respondents in Malmö</p>
</td>
<td>
<p class="MsoNormal">1 = Malmö; 0 = otherwise</p>
</td>
</tr>
</tbody>
</table>
<p class="MsoNormal"> </p>
https://doi.org/10.71775/kth.3g473-ypg92
oai:datarepository.kth.se:3g473-ypg92
swe
datarepository.kth.se
https://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-326220
https://doi.org/10.1016/j.tra.2025.104527
https://datarepository.kth.se/communities/internalarchive/
https://doi.org/10.71775/kth.2jh3e-qzj93
info:eu-repo/semantics/restrictedAccess
Survey data on shared e-scooter use, parking and multimodal travel behavior in Stockholm, Gothenburg, and Malmö, Sweden in 2022.
info:eu-repo/semantics/other
oai:datarepository.kth.se:f76hb-10741
2026-09-11T10:11:10Z
community-agents4science
Rachel So
2026-02
The marginal cost of generating a research paper with large language models (LLMs) has fallen sharply, from thousands of dollars in researcher time to a few dollars of compute. This paper analyzes the economic consequences of that cost reduction for academic publishing. We argue that cheap AI-assisted paper generation does not merely accelerate scholarship; it reshapes incentive structures in ways that favor quantity over quality, amplify existing pathologies such as paper mills and predatory journals, and impose growing costs on the peer-review system. We introduce the concept of AI slop in the academic context: content that is superficially competent but lacks the original intellectual contribution expected of peer-reviewed research. Drawing on economic models of information markets, publishing incentives, and principal-agent theory, we characterize the equilibria that emerge when the cost-per-paper collapses. We show that without structural countermeasures, the publishing ecosystem faces a lemons problem in which lowcost, low-value papers crowd out high-cost, high-value ones. We conclude with policy recommendations for journals, funders, and academic institutions.
https://doi.org/10.71775/kth.f76hb-10741
oai:datarepository.kth.se:f76hb-10741
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.The.Economics.of.AI.Slop.How.Cost-per-Paper.Alters.the.Academic.Publishing.Ecosystem.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.dfg0h-xra08
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
The Economics of AI Slop: How Cost-per-Paper Alters the Academic Publishing Ecosystem
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:ebtjf-a4049
2026-04-28T10:56:20Z
community-internalarchive
openaire_data
Emendi, Monica
Hörwing, Hanna
Parker, Louis
Svensson Marcial, Anders
Brismar, Torkel
Broman, Lars Mikael
Prahl Wittberg, Lisa
Emendi, Monica
Prahl Wittberg, Lisa
2026-04-13
<p class="MsoNormal">This repository contains data from computational fluid dynamics (CFD) simulations related to the manuscript “Efficiency and hemodynamics of dual drainage venovenous ECMO: a computational parametric study”.</p>
<p class="MsoNormal">LES simulations were carried out in a patient-averaged model of the right atrium and central veins using the commercial solver STAR-CCM+ (Version 2210, Siemens, Munich, Germany). Different configurations of cannulation used in venovenous extracorporeal circulation were simulated and the results are herein reported.</p>
<p class="MsoNormal">The data in this repository are organized as follows:</p>
<ul>
<li class="MsoListParagraph">There are three .zip folders (one for single drainage cannulation configurations, one for dual drainage with single stage jugular cannula and one for dual drainage with multistage jugular cannula).</li>
<li class="MsoListParagraph">The folders contain .cgns files with information about velocity (magnitude and components, in m/s), pressure (Pa), and passive scalar for each cannulation configuration, in the entire computational domain, averaged over the last second of simulation. The time averaged wall shear stresses (TAWSS, in Pa) are saved as .csv files for each configuration.</li>
<li class="MsoListParagraph">The names of the files follow the ECMO cannulation configuration names used in the manuscript: FF, femoro-femoral; JF, jugulo-femoral; FJ, femoro-jugular; JFF, dual drainage; JFF<strong>ss</strong> and JFF<strong>ms</strong> refer to dual drainage configurations with single stage and multistage jugular drainage cannula, respectively; the numbers 1/3 (2/2 and 3/1) indicate the drainage ratio in L/min; f+, j- and f-f- indicate the advancement (+) or retraction (-) of the jugular (j) or femoral (f) cannula.</li>
</ul>
<p> </p>
https://doi.org/10.71775/kth.ebtjf-a4049
oai:datarepository.kth.se:ebtjf-a4049
datarepository.kth.se
https://datarepository.kth.se/communities/internalarchive/
https://doi.org/10.71775/kth.azsny-yym69
info:eu-repo/semantics/restrictedAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Efficiency and hemodynamics of dual drainage venovenous ECMO: a computational parametric study
info:eu-repo/semantics/other
oai:datarepository.kth.se:0ztn8-rea28
2025-02-11T14:57:18Z
community-training
openaire
Lönneborg, Rosa
2025-02-11
<p>This presentation provides a short overview about KTH data repository and a current view of what data and how much data than can be stored. Please notice that storage quotas are for different types of communities are still under discussion. </p>
https://doi.org/10.71775/kth.0ztn8-rea28
oai:datarepository.kth.se:0ztn8-rea28
datarepository.kth.se
https://datarepository.kth.se/communities/training/
https://doi.org/10.71775/kth.4pfa1-78p25
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
FAIR data
presentation
training material
Short overview of KTH data repository
info:eu-repo/semantics/lecture
oai:datarepository.kth.se:dsmzy-psk03
2026-09-11T09:36:38Z
community-internalarchive
openaire_data
Stockholm Stad
2024-01-01
<p><span class="collapsible-comment expanded"><span class="collapsible-comment-inner">Dataset used in research. The data is a subset of The Stockholm Survey for the municipality of Nynäshamn. The Stockholm survey was developed by the City of Stockholm and has been conducted every second year in most of the county’s municipalities since the early 2000s. The municipalities fund their own data collection, while the County Administrative Board compiles comparative analyses across the municipalities. For access to the primary data source see more information from the primary data holder, <a href="https://www.lansstyrelsen.se/stockholm/samhalle/social-hallbarhet/andts/andts-samordning.html">Stockholms Länsstyrelse</a> (public aggregated survey data should be available there in .pdf format) </span></span></p>
oai:datarepository.kth.se:dsmzy-psk03
swe
datarepository.kth.se
https://datarepository.kth.se/communities/internalarchive/
info:eu-repo/semantics/restrictedAccess
secondary use in research
Stockholmsenkäten Nynäshamn
info:eu-repo/semantics/other
oai:datarepository.kth.se:f1fqq-x1c74
2025-01-29T12:35:07Z
community-training
openaire
Lönneborg, Rosa
Vesterlund, Mattias
2025-01-29
<p>The presentation provides an overview of how KTH data repository can be used and a second part describing specific use cases and how to get a community & what roles and responsibilities that are associated to a community. Please note that links included may be inaccurate later in time. Feel free to re-use and share the content. Many images are visual outputs from Mattias V </p>
https://doi.org/10.71775/kth.f1fqq-x1c74
oai:datarepository.kth.se:f1fqq-x1c74
datarepository.kth.se
https://datarepository.kth.se/communities/training/
https://doi.org/10.71775/kth.194p8-s5d66
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
instructions
Presentation for launch event of KTH data repository in January 2025
info:eu-repo/semantics/lecture
oai:datarepository.kth.se:2ywzc-ern92
2025-11-17T08:05:14Z
community-training
openaire
Lönneborg, Rosa
Vesterlund, Mattias
2025-01-31
<p>The presentation provides an overview of:<br>What KTH data repository is<br>How KTH data repository can be used<br>And description of several specific use cases<br>How to get a community & what roles and responsibilities that are associated to a community. <br><br>Please note that links included in earlier versions may be inaccurate later in time. <br>Feel free to re-use and share the content. Images showing the research data life cycle are visual outputs from Mattias Vesterlund </p>
https://doi.org/10.71775/kth.2ywzc-ern92
oai:datarepository.kth.se:2ywzc-ern92
datarepository.kth.se
https://datarepository.kth.se/communities/training/
https://doi.org/10.71775/kth.194p8-s5d66
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
instructions
Research data: Published
Research data: Unpublished
Longer presentation of KTH data repository -what is it and how can it be uses
info:eu-repo/semantics/lecture
oai:datarepository.kth.se:xp42f-kz702
2025-11-17T08:20:37Z
community-training
openaire
Lönneborg, Rosa
Vesterlund, Mattias
2025-11-17
<p>The presentation provides an overview of:<br>What KTH data repository is<br>How KTH data repository can be used<br>And description of several specific use cases<br>How to get a community & what roles and responsibilities that are associated to a community. <br><br>Please note that links included in earlier versions may be inaccurate later in time. <br>Feel free to re-use and share the content. Images showing the research data life cycle are visual outputs from Mattias Vesterlund </p>
https://doi.org/10.71775/kth.xp42f-kz702
oai:datarepository.kth.se:xp42f-kz702
datarepository.kth.se
https://datarepository.kth.se/communities/training/
https://doi.org/10.71775/kth.194p8-s5d66
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
instructions
Research data: Published
Research data: Unpublished
Longer presentation of KTH data repository -what is it and how can it be used?
info:eu-repo/semantics/lecture
oai:datarepository.kth.se:9qy5e-nea08
2026-01-27T13:07:19Z
community-internalarchive
openaire_data
Nieboer, Vincent
Odelius, Karin
Olsén, Peter
Wohlert, Jakob
2025-04-28
<p>The attached file contains all raw data of the experiments displayed in the 'More than Ring-Strain: Revisiting the Definition of Enthalpy in Ring-Opening Polymerization' manuscript and supporting information. Processing and interpretation of the data is described in the manuscript and the supporting information document. Organization of the data is shown within the read me file.</p>
https://doi.org/10.71775/kth.9qy5e-nea08
oai:datarepository.kth.se:9qy5e-nea08
eng
datarepository.kth.se
https://datarepository.kth.se/communities/internalarchive/
https://doi.org/10.71775/kth.tm2b9-fye35
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
More than Ring-Strain: Revisiting the Definition of Enthalpy in Ring-Opening Polymerization
info:eu-repo/semantics/other
oai:datarepository.kth.se:f50j9-fkg32
2026-08-31T15:16:19Z
openaire_data
community-kth
Cebecauer, Matej
Chaves, Daniel
Skoufas, Anastasios
2026-09-02
<p>This dataset is not a snapshot or sequence of snapshots of vehicle-trip progress, but rather a daily summary of all arrival and departure observations. It is the result of us independently polling that live feed every 15 seconds throughout 2024, matching each time snapshot against the planned GTFS Regional static timetable active for that service day (including planned vehicle-trips not present in TripUpdates for unknown reasons). Thus, this dataset provides complete daily planned supply with its observed performance. In processing, we consolidate the many snapshots covering each stop visit into a single record of the observed arrival and departure time (if observed). In other words, we keep only the final observations instead of the full trip progress, or we wait for the vehicle trip to complete and keep its last streamed snapshots. This results in a significantly smaller dataset of observed arrival and departure times.</p>
<p>One day of data from Trafiklab's stream is about 4.5 GB, so this dataset is the result of collecting and processing 1.7 TB of data during 2024. This dataset already contains ready-to-use, per-stop-visit observed delay, arrival, and departure times across the Stockholm Region, saving users from collecting and processing raw GTFS-RT snapshots themselves. Note that the same underlying live feed (<a href="https://www.trafiklab.se/sv/api/gtfs-datasets/gtfs-regional">https://www.trafiklab.se/sv/api/gtfs-datasets/gtfs-regional</a>) is also archived, unprocessed, by Trafiklab in the KODA repository (<a href="https://www.trafiklab.se/sv/api/our-apis/koda">https://www.trafiklab.se/sv/api/our-apis/koda</a>); we collected this dataset independently of KODA, so its polling interval and coverage may differ from ours, KODA is a good alternative source if you need raw feed snapshots for other operators/regions, or wish to reproduce this dataset's processing yourself.</p>
<p><strong>Coverage: 2024-01-01 to 2024-12-31 (calendar year, Europe/Stockholm operating dates).</strong></p>
<p>The GTFS-RT TripUpdates and ServiceAlerts feed published by Trafiklab is a live, snapshot-based service: each request returns only the feed's current state (updated on the Trafiklab server approximately every 15 seconds). Each vehicle-trip present in the dataset is streamed with a scheduled plan, and observations are either predicted or observed depending on progress during the trip.</p>
<p>This dataset is not a snapshot or sequence of snapshots of vehicle-trip progress, but rather a daily summary of all arrival and departure observations. It is the result of us independently polling that live feed every 15 seconds throughout 2024, matching each time snapshot against the planned GTFS Regional static timetable active for that service day (including planned vehicle-trips not present in TripUpdates for unknown reasons). Thus, this dataset provides complete daily planned supply with its observed performance. In processing, we consolidate the many snapshots covering each stop visit into a single record of the observed arrival and departure time (if observed). In other words, we keep only the final observations instead of the full trip progress, or we wait for the vehicle trip to complete and keep its last streamed snapshots. This results in a significantly smaller dataset of observed arrival and departure times.</p>
<p>One day of data from Trafiklab's stream is about 4.5 GB, so this dataset is the result of collecting and processing 1.7 TB of data during 2024. This dataset already contains ready-to-use, per-stop-visit observed delay, arrival, and departure times across the Stockholm Region, saving users from collecting and processing raw GTFS-RT snapshots themselves. Note that the same underlying live feed (<a href="https://www.trafiklab.se/sv/api/gtfs-datasets/gtfs-regional">https://www.trafiklab.se/sv/api/gtfs-datasets/gtfs-regional</a>) is also archived, unprocessed, by Trafiklab in the KODA repository (<a href="https://www.trafiklab.se/sv/api/our-apis/koda">https://www.trafiklab.se/sv/api/our-apis/koda</a>); we collected this dataset independently of KODA, so its polling interval and coverage may differ from ours, KODA is a good alternative source if you need raw feed snapshots for other operators/regions, or wish to reproduce this dataset's processing yourself.</p>
<h3>Terminology</h3>
<p>SL (Storstockholms Lokaltrafik) is Stockholm's public transit operator. GTFS (General Transit Feed Specification) is the static schedule format used for its planned timetables; GTFS-RT (GTFS Realtime) is the companion real-time feed format, used here for TripUpdates (vehicle-reported arrival/departure estimates) and Service Alerts (disruption notices).</p>
<ul>
<li><strong>SL (Storstockholms Lokaltrafik):</strong> The public transport authority/operator for the Stockholm region, responsible for bus, metro, train, tram and ferry services.</li>
<li><strong>GTFS (General Transit Feed Specification):</strong> A standard file format for publishing static public transit schedules and associated geographic information (stops, routes, trips, timetables).</li>
<li><strong>GTFS-RT (GTFS Realtime):</strong> A companion format to GTFS that conveys real-time updates: vehicle positions, trip updates (predicted/observed arrival and departure times) and service alerts (disruption notices), as protocol-buffer feeds.</li>
<li><strong>TripUpdates:</strong> A GTFS-RT feed type reporting real-time predictions or observations of arrival/departure times for scheduled trips.</li>
<li><strong>Service Alerts:</strong> A GTFS-RT feed type reporting service disruptions, delays, or other notices affecting routes, trips, or stops.</li>
<li><strong>AVL (Automatic Vehicle Location):</strong> Onboard vehicle tracking used as a source for the real-time positioning/timing data merged into this dataset.</li>
</ul>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h3 class="Paragraph SCXW212273923 BCX0"><span class="EOP Selected SCXW212273923 BCX0">Acknowledgment</span></h3>
<p class="Paragraph SCXW212273923 BCX0"><span class="EOP Selected SCXW212273923 BCX0"><em><strong>Original data source:</strong></em> Trafiklab (<a href="https://www.trafiklab.se/">https://www.trafiklab.se</a>)</span></p>
<p class="Paragraph SCXW212273923 BCX0"><span class="EOP Selected SCXW212273923 BCX0"><em><strong>Data collection and processing: </strong></em>Intelligent Mobility Lab (iMobility Lab), KTH (Matej Cebecauer and Anastasios Skoufas).</span></p>
</div>
<p><em><strong>Dataset prepared by:</strong></em> Daniel Chaves and Matej Cebecauer, Division of Transport Planning, Department of Civil and Architectural Engineering, KTH.</p>
<h3>Recommended acknowledgment for dataset use:</h3>
<p>We thank Trafiklab (Trafiklab.se) for the data and the KTH iMobility Lab members who helped collect and process Trafiklab's API live-stream data into the dataset used: Matej Cebecauer, Daniel Chaves, and Anastasios Skoufas.</p>
<table class="Table Ltr TableWordWrap SCXW202971920 BCX0">
<tbody class="SCXW202971920 BCX0">
<tr class="TableRow SCXW202971920 BCX0">
<td>
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><strong><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">Dataset</span></span></strong></p>
</div>
</div>
</td>
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><strong>Title</strong></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><strong><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">Files</span></span><span class="EOP SCXW202971920 BCX0"> </span></strong></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><strong><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">Format</span></span><span class="EOP SCXW202971920 BCX0"> </span></strong></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW202971920 BCX0">
<td>
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">1</span></span></p>
</div>
</div>
</td>
<td class="FirstCol SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">Observed vs. scheduled vehicle arrival/departure events (AVL + GTFS-RT </span><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">TripUpdates</span><span class="NormalTextRun SCXW202971920 BCX0">, merged with GTFS Regional Static planned time tables)</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">12 </span><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">files</span><span class="NormalTextRun SCXW202971920 BCX0">, </span><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">one</span><span class="NormalTextRun SCXW202971920 BCX0"> per </span><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">month</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">CSV, </span><span class="NormalTextRun SCXW202971920 BCX0">gzip</span><span class="NormalTextRun SCXW202971920 BCX0">-compressed </span><span class="NormalTextRun SCXW202971920 BCX0">(.csv.gz</span><span class="NormalTextRun SCXW202971920 BCX0">)</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW202971920 BCX0">
<td>
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">2</span></span></p>
</div>
</div>
</td>
<td class="FirstCol SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">Raw SL GTFS-RT Service Alerts</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">1 </span><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">file</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">Parquet</span><span class="NormalTextRun SCXW202971920 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">zstd</span><span class="NormalTextRun SCXW202971920 BCX0">)</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW202971920 BCX0">
<td>
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">3</span></span></p>
</div>
</div>
</td>
<td class="FirstCol LastRow SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">Static GTFS Regional Static reference data (Stops, Transfers, Trips, Routes)</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">4 </span><span class="NormalTextRun SpellingErrorV2Themed SCXW202971920 BCX0">files</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW202971920 BCX0">
<div class="TableCellContent SCXW202971920 BCX0">
<div class="OutlineElement Ltr SCXW202971920 BCX0">
<p class="Paragraph SCXW202971920 BCX0"><span class="TextRun SCXW202971920 BCX0"><span class="NormalTextRun SCXW202971920 BCX0">CSV</span></span><span class="EOP SCXW202971920 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
<h1>1. Observed vs. scheduled arrival/departure events (gtfs_rt_YYYY_MM.csv.gz)</h1>
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">One row per (trip, stop) observation: the scheduled stop time from the static GTFS regional timetable, merged with the observed arrival/departure reported via GTFS-RT </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">TripUpdates</span><span class="NormalTextRun SCXW73280207 BCX0"> for that stop visit.</span></span><span class="EOP Selected SCXW73280207 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<div class="TableContainer Ltr SCXW73280207 BCX0">
<div class="WACAltTextDescribedBy SCXW73280207 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW73280207 BCX0">
<tbody class="SCXW73280207 BCX0">
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><strong><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Field</span></span><span class="EOP SCXW73280207 BCX0"> </span></strong></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><strong><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Type</span></span><span class="EOP SCXW73280207 BCX0"> </span></strong></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><strong><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">Description</span></span><span class="EOP SCXW73280207 BCX0"> </span></strong></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">date</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">date</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Service date the trip </span><span class="NormalTextRun SCXW73280207 BCX0">operated</span><span class="NormalTextRun SCXW73280207 BCX0"> on</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">LineNumber</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">string</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Public-facing line number (</span><span class="NormalTextRun SCXW73280207 BCX0">e.g.</span><span class="NormalTextRun SCXW73280207 BCX0"> "18", "323")</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">LineID</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Numeric part of </span><span class="NormalTextRun SCXW73280207 BCX0">route_id</span><span class="NormalTextRun SCXW73280207 BCX0"> — SL's internal line number</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">route_id</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">string</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Route identifier. Join key to routes.txt for full route metadata</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">TransportMode</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">string</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Mode: BUS, METRO, TRAIN, TRAM, SHIP (derived from </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">route_type</span><span class="NormalTextRun SCXW73280207 BCX0"> in routes.txt)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">direction_id</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (0/1)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Direction of travel for the trip (0 = outbound, 1 = inbound)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">trip_id</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Trip/departure identifier on </span><span class="NormalTextRun SCXW73280207 BCX0">route_id</span><span class="NormalTextRun SCXW73280207 BCX0">. Join key to trips.txt for full trip metadata</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">VehicleID</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Vehicle identifier, as reported in GTFS-RT </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">TripUpdates</span><span class="NormalTextRun SCXW73280207 BCX0">/</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">VehiclePositions</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">shape_id</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Foreign key to shapes.txt (route path geometry — not included in this dataset)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">planned_departure_sfm</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Scheduled trip departure time, seconds-from-midnight of the service date, from the static GTFS regional timetable</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">planned_departure_tripupdates_sfm</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Scheduled trip departure time, seconds-from-midnight, as carried in the merged GTFS-RT </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">TripUpdates</span><span class="NormalTextRun SCXW73280207 BCX0"> message</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">stop_sequence</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Order of this stop within the trip</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">dist_traveled</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">number</span><span class="NormalTextRun SCXW73280207 BCX0"> (meters)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Distance traveled from the </span><span class="NormalTextRun SCXW73280207 BCX0">previous</span><span class="NormalTextRun SCXW73280207 BCX0"> stop to this </span><span class="NormalTextRun SCXW73280207 BCX0">observed</span><span class="NormalTextRun SCXW73280207 BCX0"> stop</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">previous_stop_id</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">stop_id</span><span class="NormalTextRun SCXW73280207 BCX0"> of the preceding stop. Join key to stops.txt</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">previous_StopAreaID</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Parent-station identifier of the preceding stop (stops.txt → </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">parent_station</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_stop_id</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">stop_id</span><span class="NormalTextRun SCXW73280207 BCX0"> of the observed/current stop. Join key to stops.txt</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_StopAreaID</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Parent-station identifier of the observed stop (stops.txt → </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">parent_station</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">scheduled_arrival_time_sfm</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Scheduled arrival time at this stop, seconds-from-midnight</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_arrival_time_sfm</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Observed (real-time) arrival time at this stop, seconds-from-midnight</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_arrival_delay</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Observed arrival delay vs. schedule (+ late / − early)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_arrival_uncertainty</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">GTFS-RT reported uncertainty of the observed arrival estimate</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">scheduled_departure_time_sfm</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Scheduled departure time from this stop, seconds-from-midnight</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_departure_time_sfm</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Observed (real-time) departure time from this stop, seconds-from-midnight</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_departure_delay</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span><span class="NormalTextRun SCXW73280207 BCX0"> (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">seconds</span><span class="NormalTextRun SCXW73280207 BCX0">)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Observed departure delay vs. schedule</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">observed_departure_uncertainty</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">integer</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">GTFS-RT reported uncertainty of the observed departure estimate</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">tripupdates_and_gtfs_not_merged_within_service_id</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">boolean</span><span class="NormalTextRun SCXW73280207 BCX0"> (0/1)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Data-quality flag: 0 = static GTFS and GTFS-RT </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">TripUpdates</span><span class="NormalTextRun SCXW73280207 BCX0"> matched on the same </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">service_id</span><span class="NormalTextRun SCXW73280207 BCX0">/service date; 1 = not matched</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">tripupdates_not_merged_with_stoptimes_or_trip</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">boolean</span><span class="NormalTextRun SCXW73280207 BCX0"> (0/1)</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Data-quality flag: 0 = merge succeeded using </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">stop_times</span><span class="NormalTextRun SCXW73280207 BCX0">/trips timing information; 1 = not matched</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW73280207 BCX0">
<td class="FirstCol LastRow SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">stop_headsign</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">string</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW73280207 BCX0">
<div class="TableCellContent SCXW73280207 BCX0">
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">Headsign</span><span class="NormalTextRun SCXW73280207 BCX0"> displayed at the stop for this trip</span></span><span class="EOP SCXW73280207 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0"> </span></span><span class="EOP Selected SCXW73280207 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW73280207 BCX0">
<p class="Paragraph SCXW73280207 BCX0"><span class="TextRun SCXW73280207 BCX0"><span class="NormalTextRun SCXW73280207 BCX0">Merge quality: a row where both </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">tripupdates_and_gtfs_not_merged_within_service_id</span><span class="NormalTextRun SCXW73280207 BCX0"> = 0 and </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">tripupdates_not_merged_with_stoptimes_or_trip</span><span class="NormalTextRun SCXW73280207 BCX0"> = 0 </span><span class="NormalTextRun SCXW73280207 BCX0">indicates</span><span class="NormalTextRun SCXW73280207 BCX0"> a fully successful match between the static schedule and the real-time </span><span class="NormalTextRun SpellingErrorV2Themed SCXW73280207 BCX0">TripUpdates</span><span class="NormalTextRun SCXW73280207 BCX0"> report.</span></span><span class="EOP Selected SCXW73280207 BCX0"> </span></p>
</div>
<h1>2. Raw GTFS-RT Service Alerts feed (service_alerts_2024.parquet)</h1>
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Unprocessed GTFS-RT Service Alerts feed, one row per (alert × informed entity) pair.</span></span><span class="EOP Selected SCXW83647759 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<div class="TableContainer Ltr SCXW83647759 BCX0">
<div class="WACAltTextDescribedBy SCXW83647759 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW83647759 BCX0">
<tbody class="SCXW83647759 BCX0">
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Field</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">Type</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">Description</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">id</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">bigint</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">GTFS-RT alert </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">entity</span><span class="NormalTextRun SCXW83647759 BCX0"> ID</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">start</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">timestamp</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Alert </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">active</span><span class="NormalTextRun SCXW83647759 BCX0">-</span><span class="NormalTextRun ContextualSpellingAndGrammarErrorV2Themed SCXW83647759 BCX0">period start</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">end</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">timestamp</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Alert </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">active</span><span class="NormalTextRun SCXW83647759 BCX0">-period end</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">cause</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">int</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">GTFS-RT </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">Alert.Cause</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">enum</span><span class="NormalTextRun SCXW83647759 BCX0"> value</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">description_text2</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">string</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Alert </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">description</span><span class="NormalTextRun SCXW83647759 BCX0"> text (Swedish)</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">header_text2</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">string</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Alert header/summary text (Swedish)</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">route_id</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">string</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Affected GTFS route, if specified</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">trip_id</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">bigint</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Affected GTFS trip, if specified</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">schedule_relationship</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">smallint</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">GTFS-RT </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">TripDescriptor.ScheduleRelationship</span><span class="NormalTextRun SCXW83647759 BCX0"> for the informed entity</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">stop_id</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">bigint</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">Affected</span><span class="NormalTextRun SCXW83647759 BCX0"> stop, </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">if</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">specified</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">date_inserted</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">timestamp</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">When this row was captured into the database</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">date</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">int</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Capture date, YYYYMMDD</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW83647759 BCX0">
<td class="FirstCol LastRow SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">alert_message_timestamp</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">timestamp</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW83647759 BCX0">
<div class="TableCellContent SCXW83647759 BCX0">
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Feed </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">message</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">timestamp</span></span><span class="EOP SCXW83647759 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">Row count (2024): 1,972,779. Source: </span><span class="NormalTextRun SpellingErrorV2Themed SCXW83647759 BCX0">Trafiklab</span><span class="NormalTextRun SCXW83647759 BCX0">.</span></span><span class="EOP Selected SCXW83647759 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW83647759 BCX0">
<p class="Paragraph SCXW83647759 BCX0"><span class="TextRun SCXW83647759 BCX0"><span class="NormalTextRun SCXW83647759 BCX0">This is the raw alert feed</span><span class="NormalTextRun SCXW83647759 BCX0">, </span><span class="NormalTextRun SCXW83647759 BCX0">one row per informed entity, so a single real-world incident typically spans many rows/alert IDs over its lifetime. No deduplication or incident-clustering has been applied.</span></span><span class="EOP Selected SCXW83647759 BCX0"> </span></p>
</div>
<h1>3. GTFS Static data</h1>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0"> GTFS Regional Static Data</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Regional GTFS reference tables (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Trafiklab</span><span class="NormalTextRun SCXW212273923 BCX0"> GTFS Sverige 2 / GTFS Regional). Source: trafiklab.se GTFS static data overview (<span class="TextRun Underlined SCXW212273923 BCX0"><a href="https://www.trafiklab.se/api/gtfs-datasets/gtfs-regional/">https://www.trafiklab.se/api/gtfs-datasets/gtfs-regional/</a></span></span></span><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">).</span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></p>
<p class="Paragraph SCXW212273923 BCX0"><span class="EOP Selected SCXW212273923 BCX0">The files below extract unique values from 366 daily GTFS Regional Static file feeds available during 2024 through the Trafiklab API. (<a href="https://www.trafiklab.se/sv/api/gtfs-datasets/gtfs-sweden/static-specification/">https://www.trafiklab.se/sv/api/gtfs-datasets/gtfs-sweden/static-specification/</a>). All attribute values reflect their latest occurrences; for example, if the coordinates associated with a specific "stop_id" changed during 2024, this dataset provides only the last observed coordinates. The same rule applies to all attributes when referencing GTFS Regional static files in this dataset. For exact coordinates, trip head-sign, route names, etc. active on a specific day, we refer you to the historical database KODA (<a href="https://www.trafiklab.se/sv/api/our-apis/koda/">https://www.trafiklab.se/sv/api/our-apis/koda/</a>).</span></p>
<p class="Paragraph SCXW212273923 BCX0"> </p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h2 class="Paragraph SCXW212273923 BCX0"><strong><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">stops.txt </span></span></strong></h2>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<div class="WACAltTextDescribedBy SCXW212273923 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Field</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Type</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Description</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">stop_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Identifies</span><span class="NormalTextRun SCXW212273923 BCX0"> a stop, </span><span class="NormalTextRun SCXW212273923 BCX0">station</span><span class="NormalTextRun SCXW212273923 BCX0"> or station entrance</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">stop_name</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Text</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Name of the location, in local/tourist vernacular</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">stop_lat</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Latitude</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Latitude</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">of</span><span class="NormalTextRun SCXW212273923 BCX0"> the </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">location</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">stop_lon</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Longitude</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Longitude</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">of</span><span class="NormalTextRun SCXW212273923 BCX0"> the </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">location</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">location_type</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Enum</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Type of location — see table below</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">parent_station</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Defines hierarchy between locations in stops.txt — </span><span class="NormalTextRun SCXW212273923 BCX0">contains</span><span class="NormalTextRun SCXW212273923 BCX0"> the </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">stop_id</span><span class="NormalTextRun SCXW212273923 BCX0"> of the parent location</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">platform_code</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Text</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Platform identifier for a platform stop</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0"> </span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">location_type</span><span class="NormalTextRun SCXW212273923 BCX0"> values:</span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<div class="WACAltTextDescribedBy SCXW212273923 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Code</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Meaning</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">0 (or blank)</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Stop/Platform — where passengers board or disembark; called a platform when it has a </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">parent_station</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">1</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Station — physical structure </span><span class="NormalTextRun SCXW212273923 BCX0">containing</span><span class="NormalTextRun SCXW212273923 BCX0"> one or more platforms</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">2</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Entrance/Exit — where passengers enter/exit a station from the street</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0"> </span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h2 class="Paragraph SCXW212273923 BCX0"><strong><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">routes.txt</span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></strong></h2>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<div class="WACAltTextDescribedBy SCXW212273923 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Field</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Type</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Description</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">route_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Identifies</span><span class="NormalTextRun SCXW212273923 BCX0"> a route</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">route_short_name</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Text</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Short, abstract identifier for the route (</span><span class="NormalTextRun SCXW212273923 BCX0">e.g.</span><span class="NormalTextRun SCXW212273923 BCX0"> "32", "100X")</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">route_long_name</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Text</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Full, more descriptive name of the route</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">route_type</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Enum</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Mode of transportation used on the route — see table below</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">route_desc</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Text</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Description providing useful, quality information about the route</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"> </p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h3 class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">route_type</span><span class="NormalTextRun SCXW212273923 BCX0"> values (extended/regional codes)</span></span></h3>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Code</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Name</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Example</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">100</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Railway Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Train traffic not assignable to a more specific category</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">101</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">High</span><span class="NormalTextRun SCXW212273923 BCX0"> Speed </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Rail</span><span class="NormalTextRun SCXW212273923 BCX0"> Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">SJ Snabbtåg, X2000</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">102</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Long </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Distance</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Rail</span><span class="NormalTextRun SCXW212273923 BCX0"> Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">International (Utrikes)</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">103</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Inter Regional </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Rail</span><span class="NormalTextRun SCXW212273923 BCX0"> Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">SJ </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">InterCity</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">105</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Sleeper</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Rail</span><span class="NormalTextRun SCXW212273923 BCX0"> Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Night </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">train</span><span class="NormalTextRun SCXW212273923 BCX0"> (Nattåg), </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">EuroNight</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">106</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Regional </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Rail</span><span class="NormalTextRun SCXW212273923 BCX0"> Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">County </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">traffic</span><span class="NormalTextRun SCXW212273923 BCX0"> (Länstrafik)</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">401</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Metro Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Metro (Tunnelbana)</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">700</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Bus Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">—</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">714</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Rail</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Replacement</span><span class="NormalTextRun SCXW212273923 BCX0"> Bus Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Replacement bus for train traffic</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">900</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Tram</span><span class="NormalTextRun SCXW212273923 BCX0"> Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Trams in Göteborg</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">1000</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Water Transport Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">SL Pendelbåt, Stockholm–</span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Helsinki</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">1501</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Communal</span><span class="NormalTextRun SCXW212273923 BCX0"> Taxi Service</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">On-</span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">demand</span><span class="NormalTextRun SCXW212273923 BCX0"> public transport </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">with</span> <span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">advance</span><span class="NormalTextRun SCXW212273923 BCX0"> order (Förbeställningstrafik)</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0"> </span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h2 class="Paragraph SCXW212273923 BCX0"><strong><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">trips.txt</span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></strong></h2>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<div class="WACAltTextDescribedBy SCXW212273923 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Field</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Type</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Description</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">route_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Identifies</span><span class="NormalTextRun SCXW212273923 BCX0"> a route</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">trip_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Identifies</span><span class="NormalTextRun SCXW212273923 BCX0"> a </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">trip</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">trip_headsign</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Text</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Text on signage </span><span class="NormalTextRun SCXW212273923 BCX0">identifying</span><span class="NormalTextRun SCXW212273923 BCX0"> the trip's destination to riders</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">direction_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Enum</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Direction of travel for the trip — see table below</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">shape_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Identifies</span><span class="NormalTextRun SCXW212273923 BCX0"> the geospatial shape describing the vehicle's travel path</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="EOP Selected SCXW212273923 BCX0"> </span></p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h3 class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">direction_id</span><span class="NormalTextRun SCXW212273923 BCX0"> values</span></span><span class="EOP Selected SCXW212273923 BCX0"> </span></h3>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<div class="WACAltTextDescribedBy SCXW212273923 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Code</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Meaning</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">0</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Outbound — travel in one direction</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">1</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Inbound — travel in the opposite direction</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"> </p>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h2 class="Paragraph SCXW212273923 BCX0"><strong><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">transfers.txt</span></span></strong></h2>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<div class="WACAltTextDescribedBy SCXW212273923 BCX0"> </div>
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Field</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Type</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Description</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">from_stop_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Stop/station where a connection between routes begins</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">to_stop_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Stop/station where a connection between routes ends</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">transfer_type</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Enum</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Type of connection for the (</span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">from_stop_id</span><span class="NormalTextRun SCXW212273923 BCX0">, </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">to_stop_id</span><span class="NormalTextRun SCXW212273923 BCX0">) pair — see table below</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">min_transfer_time</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Non-negative </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">integer</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Time, in seconds, </span><span class="NormalTextRun SCXW212273923 BCX0">required</span><span class="NormalTextRun SCXW212273923 BCX0"> to </span><span class="NormalTextRun SCXW212273923 BCX0">permit</span><span class="NormalTextRun SCXW212273923 BCX0"> a transfer</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">from_trip_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Trip where a connection between trips starts</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">to_trip_id</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">ID</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Trip where a connection between trips ends</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0"> </div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<h3 class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">transfer_type</span><span class="NormalTextRun SCXW212273923 BCX0"> values</span></span></h3>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<div class="TableContainer Ltr SCXW212273923 BCX0">
<table class="Table Ltr TableWordWrap SCXW212273923 BCX0">
<tbody class="SCXW212273923 BCX0">
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstRow FirstCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Code</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="FirstRow LastCol AdvancedProofingLightMode ContextualSpellingLightMode SpellingErrorLightMode SimilarityReviewedBlack SimilarityUnreviewedLightMode AddInCritiqueRedLightMode2 AddInCritiqueGreenLightMode2 AddInCritiqueBlueLightMode2 AddInCritiqueLavenderLightMode2 AddInCritiqueBerryLightMode2 HighContrastShading SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">Meaning</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">0 (or blank)</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Recommended transfer point between routes</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">1</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Timed transfer point — the departing vehicle waits for the arriving one</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">2</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Transfer </span><span class="NormalTextRun SCXW212273923 BCX0">requires</span><span class="NormalTextRun SCXW212273923 BCX0"> the minimum time specified by </span><span class="NormalTextRun SpellingErrorV2Themed SCXW212273923 BCX0">min_transfer_time</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
<tr class="TableRow SCXW212273923 BCX0">
<td class="FirstCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">3</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
<td class="LastCol LastRow SCXW212273923 BCX0">
<div class="TableCellContent SCXW212273923 BCX0">
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p class="Paragraph SCXW212273923 BCX0"><span class="TextRun SCXW212273923 BCX0"><span class="NormalTextRun SCXW212273923 BCX0">Transfers not possible between routes at this location</span></span><span class="EOP SCXW212273923 BCX0"> </span></p>
</div>
</div>
</td>
</tr>
</tbody>
</table>
</div>
</div>
<div class="OutlineElement Ltr SCXW212273923 BCX0">
<p> </p>
</div>
https://doi.org/10.71775/kth.f50j9-fkg32
oai:datarepository.kth.se:f50j9-fkg32
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.3bkz5-r1j37
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Public transport
GTFS
Stockholm Public Transport (SL) static GTFS merged with the observed arrival/departure times reported via GTFS-RT TripUpdates and ServiceAlerts, 2024 Dataset
info:eu-repo/semantics/other
oai:datarepository.kth.se:vgv81-57r57
2026-01-27T13:07:18Z
openaire_data
community-kth
Gudmundsson, Kjartan
Dervishaj, Arlind
FONSATI, ARIANNA
2025-10-28
<p>An Information Delivery Specification (IDS) provides a structured approach for defining, managing and checking the Information Requirements (IRs) of IFC models. Specifically, IDS files are machine-readable schemas that define which information must be present in an IFC model and can be used with standard software to automate validation. IFC models are digital representations of building components, enabling standardised information exchange across software platforms.</p>
<p>This IDS is linked to a study that investigates the use of the IDS standard to validate IFC models for the reuse of precast hollow core slabs—precast concrete elements with longitudinal voids used in floors and roofs for structural efficiency.</p>
<p>The authors developed an IDS-based workflow to verify that IFC models contain all required data specified in the Norwegian standard NS 3682:2022 for "Hollow Core Slabs for Reuse" (<a href="https://standard.no/en/sectors/byggevarer/norwegian-standard-for-hollow-core-slabs-for-reuse--ns-3682/" target="_blank" rel="noopener">link</a>). A Revit-generated IFC4x3 model was validated using the open-source Bonsai add-on for Blender, while a complementary buildingSMART Data Dictionary (bsDD) ensured semantic consistency.</p>
<p>Results show that IDS efficiently identifies missing or inconsistent information, supporting quality assurance and regulatory compliance. Standard tools, such as Revit, Blender (Bonsai), and bsDD-compatible software, enable the practical implementation of circular construction, promoting reliable digital inventories of reclaimed materials.</p>
https://doi.org/10.71775/kth.vgv81-57r57
oai:datarepository.kth.se:vgv81-57r57
eng
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.33kve-e2152
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Information Delivery Specification
openBIM
Information Requirements
Reuse
Circular construction
Circular Economy
IDS for reusing hollow core slabs
info:eu-repo/semantics/other
oai:datarepository.kth.se:vx0cq-w7h93
2026-10-15T19:23:21Z
openaire_data
community-kth
Jeong, Yongkuk
Flores-García, Erik
Khilji, Wajid Ali
Wiktorsson, Magnus
Baalsrud Hauge, Jannicke Madeleine
Klein, Jan-Felix
2026-09-10
<p>MoRoOp contains 72 hours of operational data from an autonomous mobile robot (AMR). The data was recorded at the KTH IPU Lab as part of the Self-Organizing Production Logistics (SOPL) project. The current release (1.0.0) covers five consecutive days, 2026-07-27 through 2026-07-31, organized into morning and evening shifts.</p>
<p>The dataset is additionally available on Hugginface, see <a href="https://huggingface.co/datasets/Self-Organizing-Production-Logistics/MoRoOp/tree/main">MoRoOp Main</a></p>
<div>
<h3>Data organization</h3>
The `data/` directory contains one folder for each of the ten shifts. Every shift folder follows this naming pattern:<br>
<div>data/YYYY_MM_DD_{morning|evening}/</div>
<div>YYYY_MM_DD_{morning|evening}_jobs.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_operations.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_dispatch_events.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_robot_state_raw.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_robot_state_cleaned.parquet</div>
<br>`data/kits.parquet` is a shared kit catalogue with the columns `kit_id`, `color`, `size`, and `quantity`.<br>
<h3>Tables</h3>
</div>
<div>
<ul>
<li><strong>jobs</strong>: Job-level records, including payload, operation definitions, lifecycle state and outcome, termination reason, and release, start, due, finish, and creation timestamps.</li>
<li><strong>operations:</strong> Operation-level records linked to jobs by `job_id`, including state, outcome, payload, priority, dependencies, retries, termination reason, and timestamps.</li>
<li><strong>dispatch_events</strong>: <a href="https://github.com/JaFeKl/OperationDispatcher" rel="noopener">OperationDispatcher</a> event logs, tracing the management of operations on the mobile robot. Includes event type, operation ID, job ID, and timestamps.</li>
<li><strong>robot_state_raw</strong>: Reindexed, postprocessed but unfiltered robot-state and diagnostic telemetry before postprocessing.</li>
<li><strong>robot_state_cleaned:</strong> Filtered and cleaned robot-state and diagnostic telemetry. Its IDs are retained from the raw data, so gaps identify removed records.</li>
</ul>
</div>
<div>
<h3>Code examples</h3>
Example code for loading and analyzing MoRoOp, together with scripts for reproducing the publication figures, is available in the <a href="https://github.com/JaFeKl/moroop-dataset-toolkit">MoRoOp dataset toolkit</a>.<br><br>
<h3>Cite As</h3>
Klein, J. F., & Jeong, Y. (2026). Autonomous mobile robot operations logistics: a dataset of jobs, dispatch events and robot states. arXiv preprint arXiv:2610.02428 <a href="https://doi.org/10.48550/arXiv.2610.02428" rel="nofollow">https://doi.org/10.48550/arXiv.2610.02428</a>.</div>
<p>Version 1.0.1. fixed an export bug in which the dependencies column was misspelled, leading to all values in this column to be null.</p>
https://doi.org/10.71775/kth.vx0cq-w7h93
oai:datarepository.kth.se:vx0cq-w7h93
eng
datarepository.kth.se
https://doi.org/10.1007/978-3-032-38614-4_37
https://huggingface.co/datasets/Self-Organizing-Production-Logistics/MoRoOp/tree/main
https://doi.org/10.48550/arXiv.2610.02428
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.hpj00-pjr15
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
mobile robots
production logistics
automation
Industry 4.0
MoRoOp: A Dataset of Autonomous Mobile Robot Operations in Production Logistics
info:eu-repo/semantics/other
oai:datarepository.kth.se:0qdea-h5385
2026-10-15T19:23:21Z
openaire_data
community-kth
Jeong, Yongkuk
Flores-García, Erik
Khilji, Wajid Ali
Wiktorsson, Magnus
Baalsrud Hauge, Jannicke Madeleine
Klein, Jan-Felix
2026-09-01
<p>MoRoOp contains 72 hours of operational data from an autonomous mobile robot (AMR). The data was recorded at the KTH IPU Lab as part of the Self-Organizing Production Logistics (SOPL) project. The current release (1.0.0) covers five consecutive days, 2026-07-27 through 2026-07-31, organized into morning and evening shifts.</p>
<p>The dataset is additionally available on Hugginface, see <a href="https://huggingface.co/datasets/Self-Organizing-Production-Logistics/MoRoOp/tree/main">MoRoOp Main</a></p>
<div>
<h3>Data organization</h3>
The `data/` directory contains one folder for each of the ten shifts. Every shift folder follows this naming pattern:<br>
<div>data/YYYY_MM_DD_{morning|evening}/</div>
<div>YYYY_MM_DD_{morning|evening}_jobs.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_operations.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_dispatch_events.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_robot_state_raw.parquet</div>
<div>YYYY_MM_DD_{morning|evening}_robot_state_cleaned.parquet</div>
<br>`data/kits.parquet` is a shared kit catalogue with the columns `kit_id`, `color`, `size`, and `quantity`.<br>
<h3>Tables</h3>
</div>
<div>
<ul>
<li><strong>jobs</strong>: Job-level records, including payload, operation definitions, lifecycle state and outcome, termination reason, and release, start, due, finish, and creation timestamps.</li>
<li><strong>operations:</strong> Operation-level records linked to jobs by `job_id`, including state, outcome, payload, priority, dependencies, retries, termination reason, and timestamps.</li>
<li><strong>dispatch_events</strong>: <a href="https://github.com/JaFeKl/OperationDispatcher" rel="noopener">OperationDispatcher</a> event logs, tracing the management of operations on the mobile robot. Includes event type, operation ID, job ID, and timestamps.</li>
<li><strong>robot_state_raw</strong>: Reindexed, postprocessed but unfiltered robot-state and diagnostic telemetry before postprocessing.</li>
<li><strong>robot_state_cleaned:</strong> Filtered and cleaned robot-state and diagnostic telemetry. Its IDs are retained from the raw data, so gaps identify removed records.</li>
</ul>
</div>
<div>
<h3>Code examples</h3>
Example code for loading and analyzing MoRoOp, together with scripts for reproducing the publication figures, is available in the <a href="https://github.com/JaFeKl/moroop-dataset-toolkit">MoRoOp dataset toolkit</a>.</div>
https://doi.org/10.71775/kth.0qdea-h5385
oai:datarepository.kth.se:0qdea-h5385
eng
datarepository.kth.se
https://doi.org/10.48550/arXiv.2604.04753
https://huggingface.co/datasets/Self-Organizing-Production-Logistics/MoRoOp/tree/main
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.hpj00-pjr15
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
mobile robots
production logistics
automation
Industry 4.0
MoRoOp: A Dataset of Autonomous Mobile Robot Operations in Production Logistics
info:eu-repo/semantics/other
oai:datarepository.kth.se:vzk4q-5hb27
2026-03-06T16:20:08Z
openaire_data
community-kth
Lundell, Fredrik
Davoodi, Saeed
Osawa, Kosuke
2026-03-06
<p>NB: Version 1 is NOT correct. Version 2 contains corrected data.</p>
<p>The files contain the results plotted in the figures indicated by the filenames.</p>
https://doi.org/10.71775/kth.vzk4q-5hb27
oai:datarepository.kth.se:vzk4q-5hb27
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.mjmhd-an027
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Small angle X-ray scattering insights into protein nanofibril alignment: Influence of shear and extensional flow
info:eu-repo/semantics/other
oai:datarepository.kth.se:q6pks-qk703
2026-03-06T16:20:07Z
openaire_data
community-kth
Lundell, Fredrik
Davoodi, Saeed
Osawa, Kosuke
2025-06-27
<p>The files contains the results plotted in the figures indicated by the filenames.</p>
https://doi.org/10.71775/kth.q6pks-qk703
oai:datarepository.kth.se:q6pks-qk703
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.mjmhd-an027
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
Small angle X-ray scattering insights into protein nanofibril alignment: Influence of shear and extensional flow
info:eu-repo/semantics/other
oai:datarepository.kth.se:7p5c2-tt386
2026-09-11T11:16:14Z
community-agents4science
Rachel So
2025-11
The rapid advancement of large language models has enabled AI systems to autonomously generate scientific research papers, from literature review to manuscript writing. However, this surge in AI-generated content faces a fundamental challenge: existing publication infrastructure is ill-equipped to handle it. Traditional journals rely on human peer review and remain reluctant to accept AI-generated research, while existing preprint servers lack quality-control mechanisms tailored to AI-generated content. This essay examines the emergence of AI-generated research, the limitations of current dissemination channels, and the compelling need for dedicated preprint servers designed specifically for AI-generated papers. Such platforms would provide appropriate quality control, ensure transparency, facilitate iterative refinement, and accelerate scientific discovery while maintaining research integrity.
https://doi.org/10.71775/kth.7p5c2-tt386
oai:datarepository.kth.se:7p5c2-tt386
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.The.Need.for.Preprint.Servers.Dedicated.to.AI-Generated.Papers.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://ai.vixra.org/abs/2511.0023
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.3p0sf-eye76
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
The Need for Preprint Servers Dedicated to AI-Generated Papers
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:cwr2s-tb314
2026-10-21T21:44:54Z
community-kth
Ericson, Mats
2026-10-19
<p class="MsoBlockText"><span>Frame-by-frame video scoring of the bench test reported in the KTH report “A Modular Research Platform for Software-Controlled Event-Coupled Neuromodulation”. A Bluetooth Low Energy relay connected in series with one stimulation channel of a commercial stimulator was switched by an iOS demonstration application (iPhone 14 and iPad Air, 5th generation) with nominal stimulation-epoch durations of 500 and 1000 ms. Stimulation electrodes were replaced by light-emitting diodes and events were scored in 240 frames-per-second video. The record contains 80 trials (touchscreen touchdown, relay-indicator activation and deactivation, optically detected current onset and offset), a 20-trial post-startup replication measurement, a script that recomputes the statistics of the report, and documentation. No human participants were involved and no biological measurements were obtained. For research use only.</span></p>
https://doi.org/10.71775/kth.cwr2s-tb314
oai:datarepository.kth.se:cwr2s-tb314
eng
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.8cyfs-4k096
info:eu-repo/semantics/openAccess
MIT License
https://opensource.org/license/mit
Computer and information sciences
Electrical engineering, electronic engineering, information engineering
Medical engineering
Vagus Nerve Stimulation
Transcutaneous Electric Nerve Stimulation
Mobile Applications
iOS
Swift
BLE Relay
research software
taVNS
event-coupled neuromodulation
TENS
Raw video-derived timing data for a BLE relay interface for software-controlled stimulation authorization (bench test)
info:eu-repo/semantics/other
oai:datarepository.kth.se:yv057-7en42
2026-09-11T10:11:33Z
community-agents4science
Rachel So
2026-09
Users of Anthropic's Claude models have named the variety of English these models produce. They call it Claudish, they catalogue its features, they file bug reports against individual words, and they have built translators from it into plain English. This paper reviews what is actually known about that variety. We survey the academic literature and the technical grey literature, sort the qualitative feature inventory by linguistic level, and grade every quantitative claim by the strength of its design. Four findings are supported by large-scale measurement with an explicit baseline. Machine-associated vocabulary has shifted scientific and news writing at scale, with excess frequency ratios up to 28 for individual words and at least 13.5% of 2024 biomedical abstracts affected. A cluster analysis of 461,121 GitHub pull request descriptions shows one way of writing growing from 0.7% of the corpus in early 2025 to 39% by mid-2026, with load-bearing overrepresented 39 times inside that cluster. Post-training reduces output diversity, and sycophancy is measurable in 58% of rebuttal cases across three assistant families. Language models overconverge to their user's style while users accommodate models no differently than they accommodate people. Three widely repeated claims fail this grading: the delve lexicon indexes a different model family and time period rather than Claude, vendor multipliers such as "700 times more frequent" are published without method, and no study has compared Claude with a registermatched human baseline. We conclude that Claudish is best analysed as a register, situationally selected and versioned, that is acquiring one dialect-like property through documented human uptake, and we set out the eight studies that would settle the open questions.
https://doi.org/10.71775/kth.yv057-7en42
oai:datarepository.kth.se:yv057-7en42
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.It.Is.Not.a.Style.It.Is.a.Register.A.Review.of.the.Evidence.on.Claudish.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.7yx4j-p5w28
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
It Is Not a Style, It Is a Register: A Review of the Evidence on Claudish
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:594fc-5ky57
2026-09-11T10:11:04Z
community-agents4science
Rachel So
2025-04
https://doi.org/10.71775/kth.594fc-5ky57
oai:datarepository.kth.se:594fc-5ky57
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Authorship.and.Attribution.of.AI.Generated.Content.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.70za6-6qn35
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Authorship and Attribution of AI Generated Content
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:ggkzd-jtk39
2026-10-19T12:54:40Z
openaire_data
community-kth
Skog, Isaac
Ramos Galrinho, Miguel
Gelin, Martin
2026-10-08
<p><strong>FlightMagNav</strong> contains magnetic-field and navigation instrument measurements collected with a small aerial platform outside Skövde, Sweden, in June 2026. The release includes raw sensor measurements, a parsed MATLAB dataset, and MATLAB code for parsing the raw measurements, learning a magnetic anomaly map, and evaluating that map on measurements from independent flights.<br><br>The platform carried front and rear QuSpin MAGPIE magnetometers and an Xsens MTi-680 GNSS-aided inertial navigation system. A stationary magnetometer near the flight area and measurements from the Uppsala geomagnetic reference station provide information about temporal changes in the magnetic field.<br><br>More information can be found in the <code>README.md</code> file. </p>
https://doi.org/10.71775/kth.ggkzd-jtk39
oai:datarepository.kth.se:ggkzd-jtk39
datarepository.kth.se
https://arxiv.org/abs/arXiv:2610.08982
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.2be3g-mk531
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
inertial navigation
Electrical engineering, electronic engineering, information engineering
magnetic disturbances
localization
hybrid navigation systems
FlightMagNav
info:eu-repo/semantics/other
oai:datarepository.kth.se:4mh6z-zw065
2026-06-16T09:25:55Z
openaire_data
community-kth
Nyberg, Jakob
Sommestad, Teodor
Ekstedt, Mathias
Johnson, Pontus
Swedish Defence Research Agency
2026-05-27
<p>This is event log data of activities generated by autonomous agents in the computer network "ADS-24", implemented in FOI's cyber range <a href="https://doi.org/10.1109/EuroSPW51379.2020.00014">Crate</a>. The main goal of the experiment was to measure the performance of automated defensive agents when the network is attacked for a set period of time. <br>We also tested how variations to the problem, in the form of user agents, attacker strategies and network topology, affected the returns of the agents. </p>
<p><strong>Please note that ADS-24 is an entirely fictional network, and all content (such as hostnames, usernames, email contents, etc.) was constructed for this experiment.</strong></p>
<p>The data was collected over the course of two months by running repeated episodes, where each episode contains one attack. The two hour episodes contain different combinations of an attacker agent, various defender agents and simulated users. The data is grouped by month and episode identifiers, where the episode id is a combination of the date and hour the episode started. </p>
<h1>Network</h1>
<p>The network we have implemented is based on a scenario description written by domain experts at fmv. The scenario primarily consists of a specification of a fictive maintenance management system, named “AIR-DELIVERY-SYSTEM24” (ADS-24). The intended functions of is to keep track of maintenance needs, purchase new spare parts and store costs and salaries. ADS-24 consists of four subnets, identified as “CLIENT”, “DMZ”, “SRV” and “SOC”, which are all connected through a shared firewall server. The 37 machines across the subnets run either Linux or Windows, with machines running Windows being the most frequent. The SOC network contains machines related to monitoring and is inaccessible to all agents to not disturb logging during experiments. The layout of is illustrated as a graph in [<code>ads-24.png</code>].</p>
<h2>Alert Rules & Active Responses</h2>
<p>A <a href="https://wazuh.com/">Wazuh</a> database server was run in the SOC section of the network and each host, except “flightlogs”, had a Wazuh agent service that sends events to the central database. The parser rules used by the Wazuh agents were selected based on a combination of reviews, recommendations and standards. This includes the log policy of the Swedish Armed Forces and widely used configurations such as that for <a href="https://github.com/swiftonsecurity/sysmon-config">Sysmon by SwiftOnSecurity</a>. The rules cover log data from <a href="https://www.snort.org/">Snort</a> for IP packets, <a href="https://linux.die.net/man/8/auditd">Auditd</a> and <a href="https://man7.org/linux/man-pages/man3/syslog.3.html">Syslog</a> for Linux hosts as well as Sysmon and event logs for Windows systems. Along with Wazuh’s default rule set, 586 rules from the <a href="https://github.com/sigmahq/sigma">Sigma</a> repository were included. The Sigma rules were selected based on their relevance to the scenario, meaning that rules in the Sigma repository related to services not part of the scenario were excluded. Every host in runs <a href="https://osquery.io/">Osquery</a> to collect host information, such as user accounts and network interfaces. Information about these elements are sent to Wazuh at regular intervals.</p>
<p>We used the Wazuh feature “<a href="https://documentation.wazuh.com/current/user-manual/api/reference.html#tag/Active-response">Active Response</a>” to allow defense agents to execute a set of prepared commands on hosts in the network by calling the Wazuh REST API. Two commands were implemented: one that powers off a given machine, and one that blocks traffic between a given host and other subnets in both directions. <br>Blocking is done by adding new firewall rule entries to the host “fw1”. The commands are parametrized with a single argument; the identifier of the Wazuh agent service that should execute the command.</p>
<h2>Network Activity</h2>
<p>Regular activity in ADS-24 is composed of periodic updates to the log database from external IP addresses, computer-to-computer communication within the Windows domain, and actions performed by simulated users. The simulated users follow predefined schedules in which they exchange emails, access internal web interfaces, use remote desktop applications, and open files of various types. Occasionally, a simulated system administrator connects to machines and executes commands using Remote Desktop, PsExec, or wmi.</p>
<p>We also generate threat actor activity using the red-team automation tool <a href="https://doi.org/10.1109/TDSC.2022.3160792">Lore</a>. The initial entry point machine of Lore was always the host “flightlogs”. <br>As mentioned, “flightlogs” does not run a Wazuh agent, making it functionally invisible to and untouchable by defender agents. Lore can therefore never be fully expelled from the network. Lore attempts to compromise systems by selecting different actions from a pool of available options, according to its configuration, which may or may not succeed. Two configurations for Lore were used, which we call “Guided” and “Exploratory”. With the guided configuration, Lore is configured with blacklists to ignore machines that are not along the fastest path between the entry point and the designated crown jewels in the DMZ segment. With the exploratory configuration, Lore may prioritize attacking machines not taking it closer to the DMZ, but is also more flexible and less predictable. Lore records its activity in a log stored in the control plane. The log, and thus the “true” attacker state, is therefore not accessible from the event plane where the defender agent receives data from.</p>
<h2>MAL Modeling</h2>
<p>We assume the defender agent make decisions based on the MAL data model of the network. To model the components of ADS-24, we created a smaller version of the MAL language <a href="https://github.com/mal-lang/coreLang">CoreLang</a> , titled <a href="https://doi.org/10.71775/kth.rpcde-z6r38">CadsLang</a>. The language models two attack vectors leading to access to a host’s data: one through using a software vulnerability, and one where access is gained through brute-forcing credentials. The language contains two defense steps, “Application.NotPresent” and “ConnectionRule.Restricted”, to correspond with the two commands implemented in Wazuh. Functionally, “NotPresent” blocks both attack vectors for a host, making it impossible to access its data for an attacker. The “Restricted” step blocks the “ConnectionRule” attack steps representing access to the host from a different network, but still allows an attacker to access the host through internal subnet connections.</p>
<p>Each MAL attack step was associated with a set of Wazuh rule identifiers, a set of Wazuh rule groups and a set of rule that should be ignored. Since attack steps are associated with assets, the event being mapped needs to contain an identifier that was also encountered in the instance model creation procedure, such as an IP address, username or host identifier. The mapping is done by the <a href="https://datarepository.kth.se/records/enqp2-38375">Wazuh/MAL Interface</a>.<br>We tested the alert mappings by collecting multiple two hour periods of data from the network with and without user agents, and without any attacker or defender agents. Under the assumption that no adversarial actions are taken in the network during this time, we treat all observed attack steps as false positives. This yielded an average false positive probability per time step for the alert mapping at 1.7% per attack step without users and 3.3% with users.</p>
<h1>Data Collection Method</h1>
<p>Blue agent interaction and logging was done by the <a href="https://doi.org/10.71775/kth.enqp2-38375">Wazuh/MAL Interface</a>, which also handled experiment scheduling. The Wazuh/MAL interface was run on a laptop running virtual machines, with VPN access to CRATE. A diagram showing the machine setup we used is shown in [experiment_setup.png]. </p>
<p><a href="https://doi.org/10.71775/kth.5kfnj-yke03">Vejde</a> agents trained with reinforcement learning were trained using the <a href="https://doi.org/10.71775/kth.hp777-8rw38">MAL Simulator</a>, using the <a href="https://doi.org/10.71775/kth.gq7cc-2ww92">Vejde/MAL Simulator interface</a>. The Wazuh logs and Lore JSON files were produced in CRATE, with FOI tooling.</p>
<p>Agents using policies optimized with RL were trained using the MAL Simulator, with the Vejde library for agent architectures. Training was done using 2 million transitions, sampled from a combination of simulation environments using different attacker policies, attacker entry-points and network topology variations for each episode.</p>
<h2>Experiment Procedure</h2>
<p>We ran experiments in an episodic fashion, with each episode lasting two hours. The Crate snapshot functionality was used to start each episode from the same system state. To allow the system to settle after being restored, episodes were started half an hour after the network was restored. We evaluated the following agents: “Vejde”, a policy trained in the MAL Simulator with reinforcement learning; “Vejde w/ Noise”, same as “Vejde”, but trained with a 1% false positive and false negative rate per attack step; “Heuristic”, a policy that selects an associated defense step of an asset if an associated attack step is observed; “NoOp”, a policy that does nothing. All agents use the same MAL data model for its input. Each episode used a single defender agent, sampled without replacement from the set of available agents. </p>
<p>During episodes, Wazuh was queried for new events at a fixed 30-second interval, and if any returned events were matched with attack step, an instance of the step was appended to the observation database. To select an action for the time step, the current database was fed to the defender agent, producing a single action in accordance with its policy. When there was no recorded change to the database between two time steps, no action was requested from the current agent. <br>If the agent selected an action other than waiting, the mal defense step was added to the observation database, mapped to a corresponding active response, and sent to the Wazuh server through the REST API. As in the simulator, assets with defense steps were removed from the observation along with any associations to other assets or attack steps it was involved in. If an asset that had been removed appeared in an alert at a later time, it was temporarily reintroduced to the model for a single step. The command used to run the experiments with the <a href="https://doi.org/10.71775/kth.gq7cc-2ww92">Vejde/MAL Simulator interface</a> was:</p>
<p><code>uv run scripts/run_on_repeat.py \</code><br><code>--config-file configs/tired_hope.yml \</code><br><code>--start-time "00:30" \</code><br><code>--run_length_minutes 120 \</code><br><code>--period_minutes 180 \</code><br><code>--polling_time_seconds 30 \</code><br><code>--number-runs 8 \</code><br><code>--agent_selection.method "shuffle" \</code></p>
<h2>Episode Variations</h2>
<p>Experiments were run with a set of variable factors, which were selected at random before the start of each episode.</p>
<h3>Simulated Users</h3>
<p>To test the defender agent’s robustness to noise, we ran episodes with and without the simulated user agents. <br>Each host in the client section of is assigned a simulated user agent, which will perform actions based on a given policy.</p>
<h3>Attacker Strategy</h3>
<p>To test how the defender agent handles different attack profiles, we used the two Lore configurations described above. <br>This determines which machines Lore prioritizes, and what methods it uses.</p>
<h3>Network Topology</h3>
<p>To test how the agents handles variations to the network topology, we randomly remove hosts, selected from “rootca”, “timereporter” and “print”, from before the episode. These machines are not part of the list of machines Lore is directed at with the “Guided” policy.</p>
<h1>Data Description</h1>
<p>What follows are descriptions of what the data contains. The file [utils.py] includes a number of functions to faciliate easier manipulation of the data. Also included are [cia_values.json] that lists the Confidentiality, Integrirty and Availability prioritites for each host as well as [to_agent_ip_mapping.json] and [agent_to_subnet.json] that lists which network segments hosts belong to.</p>
<h2>Defender Agents</h2>
<p>These are the identifiers for different defender agents that appear in episodes:</p>
<ul>
<li>WhackAMoleAgent: Heuristic agent that enables defenses on assets with observed attack steps.</li>
<li>NOPAgent: Defender agent that does nothing.</li>
<li>nebulous-snail-417: Vejde agent trained with no false positives.</li>
<li>bustling-doe-36: Vejde agent trained with false positives.</li>
</ul>
<h2>Episode Folder Contents</h2>
<p>Episodes were generated between 00:00 and 21:00 each day in three hour intervals. The 00:00 episode always uses the "do nothing" defender, meaning that Lore can run uninterrrupted. Each episode folder contains a number of files from Wazuh, Lore and the ADS Monitor. The main files we have used for analysis are:</p>
<ul>
<li><code>wazuh.json</code>: Exported Wazuh data, in the OpenSearch document format.</li>
<li><code>summary.json</code>: Episode summary from Crate. Contains info about starting times, shutdown machines and lore configurations used for the episode.</li>
<li><code>blue_agent_recording.json</code>: Blue agent observations and actions from the Monitor, expressed in CadsLang attack and defense steps.</li>
<li><code>lore.json</code>: Full Lore action log.</li>
</ul>
<p> The following files are included for debugging purposes:</p>
<ul>
<li><code>lore_knowledge.json</code>: Lore knowledge log. Contains assets Lore discovered.</li>
<li><code>sved_log_*</code>: Simulated user agent action log. Contains actions performed by the simulated users, if they were present.</li>
<li><code>lore_standard.json</code>: Shortened Lore action log.</li>
<li><code>episode.log</code>. Log file for experiment setup from Crate.</li>
</ul>
<h2>Summary File</h2>
<p>The file <code>summary.json</code> is a processed summary of all the episodes, combining fields from the files listed above, with some derived data like the blue agent return. <br>The following list attemps to briefly describes each field:</p>
<ul>
<li>episode_id: Episode identifier composed of the date and Crate start time.</li>
<li>schedule: Times crate was reset and Lore _should_ start.</li>
<li>time_start: Time lore actually started. This was set to half an hour after the Crate reset for all episodes.</li>
<li>time_end: Time lore ended.</li>
<li>lore_scenario_id: lore scenario id. 1-4.
<ul>
<li>Combination of entrypoint and priority.</li>
</ul>
</li>
<li>lore_scenario_instance_id: Not relevant.</li>
<li>bot_game_id: Not relevant.</li>
<li>user_agents: Whether simulated users were active or not in the episode.</li>
<li>remaining_goals: Goals that Lore has been given but not achieved in the episode. These are hosts that Lore attempts to reach.</li>
<li>all_goals_met: Whether Lore obtained all goals.</li>
<li>goals_remaining: Names of remaining goals.</li>
<li>points: Points Lore received according to its own scoring.</li>
<li>blue_agent: What blue agent, out of those listed above, that was used for the episode.</li>
<li>blue_agent_start_time: When the blue agent was started. This was set to half an hour after the Crate reset for all episodes.</li>
<li>blue_agent_return: Score of the blue agent, as measured by the Monitor interface.
<ul>
<li>Note that this will count false positives as real alerts, and is therefor not a reliable metric.</li>
</ul>
</li>
<li>lore_entrypoint: Machine Lore used as entry.
<ul>
<li>Lore will always start from flightlogs, but will prioritize the machine listed here.</li>
</ul>
</li>
<li>lore_priority: Lore policy.</li>
<li>malicious_users: Whether users turn on machines or not.
<ul>
<li>This can be considered a bug, so episodes where this is true should be treated as such.</li>
</ul>
</li>
<li>block_blinds_blue: Whether the block IP actions also blocks machines from sending alerts.
<ul>
<li>This can be considered a bug, so episodes where this is true should be treated as such.</li>
</ul>
</li>
<li>shutdown_machines: Machines that were turned off for the episode.</li>
<li>blue_agent_attack_penalty: Blue agent penalty for being attacked.
<ul>
<li>This is calculated as the sum of C + I priorities for each compromised host per minute they are compromised. </li>
<li>A machine is considered as compromised when Lore has run an elevated shell command successfully.</li>
</ul>
</li>
<li>blue_agent_defense_penalty: blue agent return only for defending.
<ul>
<li>The penalty is the A priority for an asset. This is also calculated per minute.</li>
<li>Shutting down a host incurs the full penality, blocking IP traffic half.</li>
</ul>
</li>
<li>blue_agent_score: Blue agent return. Sum of attack and defense penality.</li>
<li>blue_agent_compromised_hosts: machines lore gained an elevated shell on.</li>
<li>blue_agent_defended_hosts: assets that had defenses ran on them.</li>
<li>blue_agent_episode_length: how many steps the blue agent took.
<ul>
<li>Dependent on the polling rate of the monitor. The wall time of an episode is always two hours.</li>
</ul>
</li>
</ul>
https://doi.org/10.71775/kth.4mh6z-zw065
oai:datarepository.kth.se:4mh6z-zw065
eng
datarepository.kth.se
https://doi.org/10.71775/kth.enqp2-38375
https://doi.org/10.71775/kth.rpcde-z6r38
https://doi.org/10.71775/kth.gq7cc-2ww92
https://doi.org/10.71775/kth.5kfnj-yke03
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.ht504-31659
info:eu-repo/semantics/openAccess
Creative Commons Attribution Share Alike 4.0 International
https://creativecommons.org/licenses/by-sa/4.0/
machine learning
computer networks
reinforcement learning
cyber defense
network security
graph neural network
Automated Cyber Attack & Defense Logs from ADS-24/Crate
info:eu-repo/semantics/other
oai:datarepository.kth.se:xmdd6-yhm63
2026-09-11T10:11:55Z
community-agents4science
Rachel So
2025-11
The integration of artificial intelligence into scientific research has led to the emergence of AI scientists, autonomous systems capable of conducting research through agentic workflows. These workflows increasingly rely on scientific paper databases as critical infrastructure for literature retrieval, knowledge synthesis, and iterative research processes. We examine how AI scientists leverage paper databases such as arXiv, Semantic Scholar, and other scholarly repositories within agentic frameworks. We analyze the technical mechanisms enabling this integration, including semantic search, citation network analysis, and automated literature review capabilities. We identify key applications across scientific domains, from drug discovery to materials science, where AI agents use paper databases to inform hypothesis generation, experimental design, and manuscript preparation. We also discuss challenges related to data quality, algorithmic biases, and the need for human oversight. Our analysis reveals that effective integration of paper databases into agentic workflows represents a fundamental enabler of autonomous scientific discovery, while highlighting critical areas requiring further development.
https://doi.org/10.71775/kth.xmdd6-yhm63
oai:datarepository.kth.se:xmdd6-yhm63
eng
Project Rachel
https://project-rachel.4open.science/Rachel.So.Use.of.Scientific.Paper.Databases.by.AI.Scientists.in.Agentic.Workflows.pdf
https://doi.org/10.48550/arXiv.2511.14819
https://datarepository.kth.se/communities/agents4science/
https://doi.org/10.71775/kth.ncmbz-z1w71
info:eu-repo/semantics/openAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
AI-generated research
AI authorship
Use of Scientific Paper Databases by AI Scientists in Agentic Workflows
info:eu-repo/semantics/preprint
oai:datarepository.kth.se:frfd6-ymw69
2026-10-06T08:27:57Z
openaire_data
community-kth
Yang, Zhikai
2026-07-15
<p>Breast Ultrasound (BUS) imaging plays an important role in the early detection and diagnosis of breast cancer. The rapid advancement of deep learning-based Computer-Aided Diagnosis (CAD) systems has demonstrated remarkable potential. However, the clinical applicability of CAD is constrained by the scarcity of large-scale, diverse, and well-annotated datasets. Existing public BUS datasets are highly fragmented. To address these gaps, we present BUS-Large, a large-scale curated BUS dataset for method development and evaluation, comprising more than 21,00 images from 21 publicly available datasets across multiple countries and clinical institutions. The dataset integrates all the public available static image datasets. All cohorts have been harmonized with unified diagnostic labels, pixel-level segmentation mask, and standardized BI-RADS clinical information. To the best of our knowledge, this is one of the most extensive datasets providing lesion segmentation masks annotated from publicly available BUS datasets. </p>
<p>This work was supported by grants from Marie Skłodowska-Curie Doctoral Networks Actions (HORIZON-MSCA-2021-DN-01-01; 101073222), Cancerfonden (22-2389 Pj). <br>In addition to the MAIA platform at KTH, the computations were enabled by the Berzelius resource provided by the Knut and Alice Wallenberg Foundation at the National Academic Infrastructure for Supercomputing in Sweden. We also acknowledge the public dataset owners for making the imaging and clinical data used in this study publicly available.</p>
https://doi.org/10.71775/kth.frfd6-ymw69
oai:datarepository.kth.se:frfd6-ymw69
datarepository.kth.se
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.kxrjk-gq496
info:eu-repo/semantics/restrictedAccess
Creative Commons Attribution 4.0 International
https://creativecommons.org/licenses/by/4.0/
breast cancer
ultrasound
segmentation
computer aided diagnosis
Clinical medicine
BUS-Large: A large harmonized and curated breast ultrasound dataset with segmentation masks and clinical labels
info:eu-repo/semantics/other
oai:datarepository.kth.se:rpcde-z6r38
2026-06-09T08:06:04Z
community-kth
Buhaiu, Andrei
Nyberg, Jakob
2026-06-02
<p>CadsLang is a smaller version of the <a href="https://doi.org/10.1145/3230833.3232799">Meta Attack Language</a> <a href="https://github.com/mal-lang/coreLang">coreLang</a>, intended for the use in tests with automated agents in the cyber range <a href="https://doi.org/10.1109/EuroSPW51379.2020.00014">Crate</a>. <br>The name stems from "Crate ADS-24 LANGuage" despite not being explicity tieds to neither Crate nor the ADS-24 network infrastructure. The language consists of 9 asset types, 49 attack steps and two defense steps.</p>
<p>The included image (cadslang_lang_graph.dot.png) shows the relations between the different attack steps.</p>
https://doi.org/10.71775/kth.rpcde-z6r38
oai:datarepository.kth.se:rpcde-z6r38
https://github.com/mal-lang/CadsLang
eng
datarepository.kth.se
https://doi.org/10.71775/kth.4mh6z-zw065
https://datarepository.kth.se/communities/kth/
https://doi.org/10.71775/kth.tnk3x-f3210
info:eu-repo/semantics/openAccess
Apache License 2.0
https://opensource.org/license/apache-2-0
threat modeling
attack graph
CadsLang: A Smaller CoreLang for Network Security Modeling and Machine Learning Agents
info:eu-repo/semantics/other