{
  "annotation_id": "865d5dda-9389-4423-a8a4-b98b4ee881a0",
  "date_created": "2026-03-02T18:01:00.479000Z",
  "date_modified": "2026-03-02T18:01:00.479000Z",
  "file_hash": "edb2b25a8c407227e2c3b6fc438cbc918260acc9365f6aafa2354a639914bc74",
  "private": false,
  "record": {
    "abstract": "An algorithm for optimization of signal significance or any other\nclassification figure of merit suited for analysis of high energy physics (HEP)\ndata is described. This algorithm trains decision trees on many bootstrap\nreplicas of training data with each tree required to optimize the signal\nsignificance or any other chosen figure of merit. New data are then classified\nby a simple majority vote of the built trees. The performance of this algorithm\nhas been studied using a search for the radiative leptonic decay B-\u003egamma l nu\nat BaBar and shown to be superior to that of all other attempted classifiers\nincluding such powerful methods as boosted decision trees. In the B-\u003egamma e nu\nchannel, the described algorithm increases the expected signal significance\nfrom 2.4 sigma obtained by an original method designed for the B-\u003egamma l nu\nanalysis to 3.0 sigma.",
    "arxiv_id": "physics/0507157",
    "authors": [
      "I. Narsky"
    ],
    "categories": [
      "physics.data-an"
    ],
    "doi": "10.1142/9781860948985_0030",
    "title": "Optimization of Signal Significance by Bagging Decision Trees",
    "url": "https://arxiv.org/abs/physics/0507157"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "f89843c7-e63e-41c6-9d14-40a614aeb919",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}