{
  "annotation_id": "a2d597a1-51ca-4543-ad3d-fbe3f8feb155",
  "date_created": "2026-03-02T18:01:31.676000Z",
  "date_modified": "2026-03-02T18:01:31.676000Z",
  "file_hash": "127e2f42e3d2baf8fe08ab08e11be96f53917953f9098788781bf18c86711958",
  "private": false,
  "record": {
    "abstract": "Sequence comparison is a widely used computational technique in modern\nmolecular biology. In spite of the frequent use of sequence comparisons the\nimportant problem of assigning statistical significance to a given degree of\nsimilarity is still outstanding. Analytical approaches to filling this gap\nusually make use of an approximation that neglects certain correlations in the\ndisorder underlying the sequence comparison algorithm. Here, we use the longest\ncommon subsequence problem, a prototype sequence comparison problem, to\nanalytically establish that this approximation does make a difference to\ncertain sequence comparison statistics. In the course of establishing this\ndifference we develop a method that can systematically deal with these disorder\ncorrelations.",
    "arxiv_id": "q-bio/0406009",
    "authors": [
      "Ralf Bundschuh",
      "Nicholas Chia"
    ],
    "categories": [
      "q-bio.QM"
    ],
    "title": "Finite Width Model Sequence Comparison",
    "url": "https://arxiv.org/abs/q-bio/0406009"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "8f01e4db-f161-4266-9f8a-05e68b22ee49",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}