{
  "annotation_id": "cacb1096-65ee-4573-b5ac-151198424457",
  "date_created": "2026-03-02T18:01:14.519000Z",
  "date_modified": "2026-03-02T18:01:14.519000Z",
  "file_hash": "b8c2d5295c488eeac09f2e381b82cba53813023f702d5f9fa5e2333e2d02374d",
  "private": false,
  "record": {
    "abstract": "In this paper, we compare the performance, stability and robustness of\nArtificial Neural Networks (ANN) and Boosted Decision Trees (BDT) using\nMiniBooNE Monte Carlo samples. These methods attempt to classify events given a\nnumber of identification variables. The BDT algorithm has been discussed by us\nin previous publications. Testing is done in this paper by smearing and\nshifting the input variables of testing samples. Based on these studies, BDT\nhas better particle identification performance than ANN. The degradation of the\nclassifications obtained by shifting or smearing variables of testing results\nis smaller for BDT than for ANN.",
    "arxiv_id": "physics/0610276",
    "authors": [
      "Hai-Jun Yang",
      "Byron P. Roe",
      "Ji Zhu"
    ],
    "categories": [
      "physics.data-an"
    ],
    "doi": "10.1016/j.nima.2007.02.081",
    "journal_ref": "Nucl. Instrum. \u0026 Meth. A 574 (2007) 342-349",
    "title": "Studies of Stability and Robustness for Artificial Neural Networks and   Boosted Decision Trees",
    "url": "https://arxiv.org/abs/physics/0610276"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "d4279a64-91e6-4aee-ab8e-8093721c7573",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}