{
  "annotation_id": "62620563-2c7b-461c-9c31-0cf2bd22c29c",
  "date_created": "2026-03-02T18:01:06.680000Z",
  "date_modified": "2026-03-02T18:01:06.680000Z",
  "file_hash": "55da4f623ddcbe4319dc2ecce2f8a100785d1ae18e5ad04ebb2383d2b17808b2",
  "private": false,
  "record": {
    "abstract": "Here we extract the geographical addresses of authors in the Citeseer\ndatabase of computer science papers. We show that the productivity of research\ncentres in the United States follows a power-law regime, apart from the most\nproductive centres for which we do not have enough data to reach definite\nconclusions. To investigate the spatial distribution of computer science\nresearch centres in the United States, we compute the two-point correlation\nfunction of the spatial point process and show that the observed power-laws do\nnot disappear even when we change the physical representation from geographical\nspace to cartogram space. Our work suggests that the effect of physical\nlocation poses a challenge to ongoing efforts to develop realistic models of\nscientific productivity. We propose that the introduction of a fine scale\ngeography may lead to more sophisticated indicators of scientific output.",
    "arxiv_id": "physics/0603242",
    "authors": [
      "Rui Carvalho",
      "Michael Batty"
    ],
    "categories": [
      "physics.soc-ph",
      "physics.data-an"
    ],
    "doi": "10.1088/1742-5468/2006/10/P10012",
    "journal_ref": "J. Stat. Mech. (2006) P10012",
    "title": "The Geography of Scientific Productivity: Scaling in U.S. Computer   Science",
    "url": "https://arxiv.org/abs/physics/0603242"
  },
  "schema_id": "dorsal/arxiv",
  "source": {
    "execution_id": "02a35e55-7de5-4fab-acd0-2fa5e29dab45",
    "id": "arXiv Dataset IDs",
    "type": "Model",
    "variant": "snapshot-2026-03-01",
    "version": "0.1.0"
  },
  "user_id": 1000002
}