{
  "fetched_at": "2026-10-24T23:03:50Z",
  "source_url": "https://www.kaggle.com/competitions/data-science-hep-triggers/data",
  "pages": [
    {
      "name": "data-description",
      "content": "<p>Samples are simulated data. Six different decays are marked as \"interesting\" (1 - labeled) events.  As \"uninteresting\" events generic simulated proton-proton collisions are provided.</p>\r\n<p>Primary vertex (PV) is a collision point. Secondary vertex (SV) is a point where an unstable particle decayed. This particle is associated with SV.</p>\r\n<p>Each event consists of the set of secondary vertices. Number of secondary vertices varies for each event (there are up to 50 SVs in an event). Dataset is a set of all secondary vertices for all events, thus sample is a secondary vertex from some event.</p>\r\n<p><strong>Pay attention: in the submission you should estimate \"interestingness\" for each event, not for separate secondary vertices!</strong></p>\r\n<p>In the training dataset each sample has a weight (\"<strong>Weight</strong>\" column). Be sure to use these weights during training and quality estimation, because weights normalize amount of each signal decay. Weights are reflecting contribution of event, not SV (that's why weights are equal for all SVs within event).</p>\r\n<p>Side-note: you can easily split training dataset into separate decays using \"Weight\" column, if you want to use this information to train the model.</p>\r\n<h2>File descriptions</h2>\r\n<ul>\r\n<li><strong>train.csv</strong> - the training set</li>\r\n<li><strong>test.csv</strong> - the test set</li>\r\n<li><strong>submission.csv</strong> - a sample submission file in the correct format</li>\r\n<li><strong>baseline_data&amp;science.ipynb</strong> - a notebook with simple training and submission preparation</li>\r\n</ul>\r\n<h2>Data fields</h2>\r\n<p>Primary vertex (PV) is a collision point. Impact parameter is the closest distance between track and primary vertex. While you are considering a secondary vertex, an associated particle, which decays, is also called a parent particle and its products are called daughters.</p>\r\n<p><img src=\"https://storage.googleapis.com/kaggle-media/competitions/inclass/5428/media/triggers.png\" alt=\"Features explanation\" width=\"550\" /></p>\r\n<ul>\r\n<li><strong>EventID</strong> - id for event (it will be the same for secondary vertices that come from the same event)</li>\r\n<li><strong>Label</strong> - \"interesting\" event (label 1) or \"uninteresting\" (label 0), subject to predict for test sample</li>\r\n<li><strong>Mass</strong> - mass of the parent particle</li>\r\n<li><strong>Corrected_mass</strong> - \"corrected\" mass of the parent particle (takes into account missed products of the parent particle)</li>\r\n<li><strong>Pt</strong> - transverse momentum of the parent particle</li>\r\n<li><strong>Pt_sum</strong> - sum of transverse momenta (pt) for all daughters of the parent particle</li>\r\n<li><strong>Pt_min</strong> - the minimum of the transverse momenta for parent particle's products</li>\r\n<li><strong>IP_chi2</strong> - impact parameter chi2 of the parent particle</li>\r\n<li><strong>IP_chi2_sum</strong> - sum of IP_chi2 for products of the parent particle</li>\r\n<li><strong>Flight_distance</strong> - flight distance chi2 of the parent particle</li>\r\n<li><strong>Pseudorapidity</strong> - <a href=\"https://en.wikipedia.org/wiki/Pseudorapidity\">pseudorapidity</a></li>\r\n<li><strong>Track_number_PV</strong> - number of preselected tracks in the interaction point (PV)</li>\r\n<li><strong>Tracks_number</strong> - number of tracks in the SV</li>\r\n<li><strong>Tracks_number_passed</strong> - number of preselected tracks in the SV</li>\r\n<li><strong> Vertex_chi2</strong> - fit quality for secondary vertex construction</li>\r\n</ul>\r\n<p>Side-note: \"distance chi2\" means the following: we measure X±ΔX<sub> </sub>and Y±ΔY, then we compute \"distance chi2\" as |X-Y|/[(ΔX)<sup>2</sup>+(ΔY)<sup>2</sup>]. In a simple case we can put Y=0 and ΔY=0 and define the \"X chi2\" value.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "<p>The competition, organized by<a href=\"http://yandexdataschool.com/\"> Yandex School of Data Analysis</a>, is a part of <a href=\"https://events.yandex.ru/events/ds/17-sept-2016/\">Data&amp;Science</a> events. The task is to classify events (proton-proton collisions) into \"interesting\" (1-labeled samples), which probably contain searched physics and should be stored into memory, versus \"non-interesting\" (0-labeled samples), that should not be stored.</p>\r\n<p>The system which defines \"interesting\" events is called trigger system and works in real-time (online). This is the first stage of selecting event for further analysis in high energy physics experiments. In this competition, you should build a trigger system which efficiently selects events.</p>\r\n<p>Speed of the algorithm for online events processing is another story, you can ignore this factor during competition.</p>\r\n<p>To prepare your first submission see the notebook in the <strong>Data</strong> section.</p>\r\n<p>You can ask questions in the competition forum. Good luck!</p>\r\n<h2>Acknowledgments</h2>\r\n<p>We thank Mike Williams and Philip Iten for help in preparing this toy dataset.</p>\r\n<h2></h2>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "<p>The evaluation metric for this competition is the area under the receiver operator characteristic curve (ROC AUC).</p>\r\n<h2>Submission Format</h2>\r\n<p><strong>For every event in the dataset</strong>, not secondary vertex, submission file should contain two columns: EventId and Label. Predictions provided by your model are expected to follow this format:</p>\r\n<pre>EventId,Label<br />0,0.7<br />1,0.3<br />2,0.6<br />3,0.0<br />etc.</pre>\r\n<p>The provided prediction is expected to be higher for \"interesting\" events.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "\r\n\t<!-- Begin Base Rules -->\r\n    <h3>One account per participant</h3>\r\n    <p>You cannot sign up to Kaggle from multiple accounts and therefore you cannot submit from multiple accounts.</p>\r\n    <h3>No private sharing outside teams</h3>\r\n    <p>\r\n        Privately sharing code or data outside of teams is not permitted.\r\n        It's okay to share code if made available to all participants on the forums.\r\n    </p>\r\n    <h3>Team Mergers</h3>\r\n    <p>\r\n        Team mergers are allowed and can be performed by the team leader. In order to merge, the combined team must have a total submission count less than or equal to the maximum allowed as of the merge date. The maximum allowed is the number of submissions per day multiplied by the number of days the competition has been running.<br/>\r\n    </p>\r\n\r\n    <h3>Team Limits</h3>\r\n    <p>The maximum size of a team is 3 participants.</p>\r\n    <h3>Submission Limits</h3>\r\n    <p>You may submit a maximum of 5 entries per day.</p>\r\n    <p>You may select up to 2 final submissions for judging.</p>\r\n    <h3>Competition Timeline</h3>\r\n    <p>Start Date: <strong>9/15/2016 11:52 PM UTC</strong></p>\r\n    <p>Merger Deadline: <strong>None</strong></p>\r\n    <p>Entry Deadline: <strong>None</strong></p>\r\n    <p>End Date: <strong>10/2/2016 11:59 PM UTC</strong></p>\r\n\t<!-- End Base Rules -->\r\n<h3>INTELLECTUAL PROPERTY</h3>\r\n<h4>DATA</h4>\r\n<p>'Data' means the Data or Datasets linked from the Competition Website for the purpose of use by Participants in the Competition. For the avoidance of doubt, Data is deemed for the purpose of these Competition Rules to include any prototype or executable code provided to Participants by Kaggle or Competition Organizer via the Website. Participants must use the Data only as permitted by these Competition Rules and any associated data use rules specified on the Competition Website.</p>\r\n<p>Unless otherwise permitted by the terms of the Competition Website, Participants must use the Data solely for the purpose and duration of the Competition, including but not limited to reading and learning from the Data, analyzing the Data, modifying the Data and generally preparing your Submission and any underlying models and participating in forum discussions on the Website. Participants agree to use suitable measures to prevent persons who have not formally agreed to these Competition Rules from gaining access to the Data and agree not to transmit, duplicate, publish, redistribute or otherwise provide or make available the Data to any party not participating in the Competition. Participants agree to notify Kaggle immediately upon learning of any possible unauthorized transmission or unauthorized access of the Data and agree to work with Kaggle to rectify any unauthorized transmission. Participants agree that participation in the Competition shall not be construed as having or being granted a license (expressly, by implication, estoppel, or otherwise) under, or any right of ownership in, any of the Data.</p>",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}