{
  "annotation_id": "9907196d-7a86-46eb-b329-9fcd8d3104fa",
  "date_created": "2026-03-02T18:01:10.126000Z",
  "date_modified": "2026-03-02T18:01:10.126000Z",
  "file_hash": "3c623c76947b193c3ad28d8574f04f122cf208f82f4820c107a6ef2f85757782",
  "private": false,
  "record": {
    "abstract": "We introduce a complexity measure for symbolic sequences. Starting from a\nsegmentation procedure of the sequence, we define its complexity as the entropy\nof the distribution of lengths of the domains of relatively uniform composition\nin which the sequence is decomposed. We show that this quantity verifies the\nproperties usually required for a ``good\u0027\u0027 complexity measure. In particular it\nsatisfies the one hump property, is super-additive and has the important\nproperty of being dependent of the level of detail in which the sequence is\nanalyzed. Finally we apply it to the evaluation of the complexity profile of\nsome genetic sequences.",
    "arxiv_id": "physics/0606113",
    "authors": [
      "Ana P. Majtey",
      "Ramon Roman-Roldan",
      "Pedro W. Lamberti"
    ],
    "categories": [
      "physics.class-ph"
    ],
    "title": "A complexity measure for symbolic sequences and applications to DNA",
    "url": "https://arxiv.org/abs/physics/0606113"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "b5fbc2e3-5fc1-4247-bb43-18696ab810f5",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}