# Data&Science: HEP triggers — Data

来源：https://www.kaggle.com/competitions/data-science-hep-triggers/data

采集时间：2026-10-24T23:03:51Z

Samples are simulated data. Six different decays are marked as "interesting" (1 - labeled) events.  As "uninteresting" events generic simulated proton-proton collisions are provided.
Primary vertex (PV) is a collision point. Secondary vertex (SV) is a point where an unstable particle decayed. This particle is associated with SV.
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.
Pay attention: in the submission you should estimate "interestingness" for each event, not for separate secondary vertices!
In the training dataset each sample has a weight ("
Weight
" 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).
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.
File descriptions
train.csv
- the training set
test.csv
- the test set
submission.csv
- a sample submission file in the correct format
baseline_data&science.ipynb
- a notebook with simple training and submission preparation
Data fields
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.
![Features explanation](https://storage.googleapis.com/kaggle-media/competitions/inclass/5428/media/triggers.png)
EventID
- id for event (it will be the same for secondary vertices that come from the same event)
Label
- "interesting" event (label 1) or "uninteresting" (label 0), subject to predict for test sample
Mass
- mass of the parent particle
Corrected_mass
- "corrected" mass of the parent particle (takes into account missed products of the parent particle)
Pt
- transverse momentum of the parent particle
Pt_sum
- sum of transverse momenta (pt) for all daughters of the parent particle
Pt_min
- the minimum of the transverse momenta for parent particle's products
IP_chi2
- impact parameter chi2 of the parent particle
IP_chi2_sum
- sum of IP_chi2 for products of the parent particle
Flight_distance
- flight distance chi2 of the parent particle
Pseudorapidity
-
[pseudorapidity](https://en.wikipedia.org/wiki/Pseudorapidity)
Track_number_PV
- number of preselected tracks in the interaction point (PV)
Tracks_number
- number of tracks in the SV
Tracks_number_passed
- number of preselected tracks in the SV
Vertex_chi2
- fit quality for secondary vertex construction
Side-note: "distance chi2" means the following: we measure X±ΔX
and Y±ΔY, then we compute "distance chi2" as |X-Y|/[(ΔX)
2
+(ΔY)
2
]. In a simple case we can put Y=0 and ΔY=0 and define the "X chi2" value.