{
  "annotation_id": "788575a1-229a-4336-9d3a-09c6a828678d",
  "date_created": "2026-03-02T18:00:53.363000Z",
  "date_modified": "2026-03-02T18:00:53.363000Z",
  "file_hash": "85cc31a786f898d8d1912c26b704f8b5d141049d56da17da454b7d83278216b2",
  "private": false,
  "record": {
    "abstract": "The efficacy of particle identification is compared using artificial neutral\nnetworks and boosted decision trees. The comparison is performed in the context\nof the MiniBooNE, an experiment at Fermilab searching for neutrino\noscillations. Based on studies of Monte Carlo samples of simulated data,\nparticle identification with boosting algorithms has better performance than\nthat with artificial neural networks for the MiniBooNE experiment. Although the\ntests in this paper were for one experiment, it is expected that boosting\nalgorithms will find wide application in physics.",
    "arxiv_id": "physics/0408124",
    "authors": [
      "Byron P. Roe",
      "Hai-Jun Yang",
      "Ji Zhu",
      "Yong Liu",
      "Ion Stancu",
      "Gordon McGregor"
    ],
    "categories": [
      "physics.data-an",
      "hep-ex"
    ],
    "doi": "10.1016/j.nima.2004.12.018",
    "journal_ref": "Nucl.Instrum.Meth. A543 (2005) 577-584",
    "title": "Boosted Decision Trees as an Alternative to Artificial Neural Networks   for Particle Identification",
    "url": "https://arxiv.org/abs/physics/0408124"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "32005498-3b55-40d2-93d3-29f7d63ce6b7",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}