{
  "annotation_id": "ca105a28-ce12-4778-a68c-23f8b4775e77",
  "date_created": "2026-03-02T18:00:50.499000Z",
  "date_modified": "2026-03-02T18:00:50.499000Z",
  "file_hash": "00aa52359a8bb02c59656c89d6b68f0fce7464a0218f1c9f1e3031fb335df054",
  "private": false,
  "record": {
    "abstract": "We present a novel multivariate classification technique based on Genetic\nProgramming. The technique is distinct from Genetic Algorithms and offers\nseveral advantages compared to Neural Networks and Support Vector Machines. The\ntechnique optimizes a set of human-readable classifiers with respect to some\nuser-defined performance measure. We calculate the Vapnik-Chervonenkis\ndimension of this class of learning machines and consider a practical example:\nthe search for the Standard Model Higgs Boson at the LHC. The resulting\nclassifier is very fast to evaluate, human-readable, and easily portable. The\nsoftware may be downloaded at: http://cern.ch/~cranmer/PhysicsGP.html",
    "arxiv_id": "physics/0402030",
    "authors": [
      "Kyle Cranmer",
      "R. Sean Bowman"
    ],
    "categories": [
      "physics.data-an"
    ],
    "doi": "10.1016/j.cpc.2004.12.006",
    "title": "PhysicsGP: A Genetic Programming Approach to Event Selection",
    "url": "https://arxiv.org/abs/physics/0402030"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "cc9738d7-36eb-47bb-b0cd-a1f06cf0c10c",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}