{"paper":{"title":"A large dataset of software mentions in the biomedical literature","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["q-bio.OT"],"primary_cat":"cs.DL","authors_text":"Ana-Maria Istrate, Boris Veytsman, Dario Taraborelli, Donghui Li, Ivana Williams, Michaela Torkar","submitted_at":"2022-09-01T19:04:47Z","abstract_excerpt":"We describe the CZ Software Mentions dataset, a new dataset of software mentions in biomedical papers. Plain-text software mentions are extracted with a trained SciBERT model from several sources: the NIH PubMed Central collection and from papers provided by various publishers to the Chan Zuckerberg Initiative. The dataset provides sources, context and metadata, and, for a number of mentions, the disambiguated software entities and links. We extract 1.12 million unique string software mentions from 2.4 million papers in the NIH PMC-OA Commercial subset, 481k unique mentions from the NIH PMC-OA"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.00693","kind":"arxiv","version":4},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2209.00693/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"}