{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GVJFYLL35ITKJJK72JD3AYFXNW","short_pith_number":"pith:GVJFYLL3","schema_version":"1.0","canonical_sha256":"35525c2d7bea26a4a55fd247b060b76d9e238f915ee0e6f0706eb60682b76ad2","source":{"kind":"arxiv","id":"2209.00693","version":4},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2209.00693","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DL","submitted_at":"2022-09-01T19:04:47Z","cross_cats_sorted":["q-bio.OT"],"title_canon_sha256":"b55b8854907b860014fc7956865bf5cc3c12dcac9de585cfe7e0f0cb690ad577","abstract_canon_sha256":"377f29c46edfd82af7c4d283a38d0d30bd334b4c364cca053ff60cbdc94baabd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:01:40.716804Z","signature_b64":"CE7OswcP+n8cc71k9zbvzmGEV2bzQ5OIavTnsedg5yatNDfdpHxa/DbK04hRH9Ii54v2VIeLGCc29OpHJ7yQDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35525c2d7bea26a4a55fd247b060b76d9e238f915ee0e6f0706eb60682b76ad2","last_reissued_at":"2026-07-05T05:01:40.716335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:01:40.716335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2209.00693","created_at":"2026-07-05T05:01:40.716394+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.00693v4","created_at":"2026-07-05T05:01:40.716394+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.00693","created_at":"2026-07-05T05:01:40.716394+00:00"},{"alias_kind":"pith_short_12","alias_value":"GVJFYLL35ITK","created_at":"2026-07-05T05:01:40.716394+00:00"},{"alias_kind":"pith_short_16","alias_value":"GVJFYLL35ITKJJK7","created_at":"2026-07-05T05:01:40.716394+00:00"},{"alias_kind":"pith_short_8","alias_value":"GVJFYLL3","created_at":"2026-07-05T05:01:40.716394+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28120","citing_title":"The Reciprocal Impact of Science and Software: A Cross-Corpus Analysis of How Research Shapes Software and Software Enables Research","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2404.06672","citing_title":"Biomedical Open Source Software: Crucial Packages and Hidden Heroes","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2604.23820","citing_title":"The software space of science","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW","json":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW.json","graph_json":"https://pith.science/api/pith-number/GVJFYLL35ITKJJK72JD3AYFXNW/graph.json","events_json":"https://pith.science/api/pith-number/GVJFYLL35ITKJJK72JD3AYFXNW/events.json","paper":"https://pith.science/paper/GVJFYLL3"},"agent_actions":{"view_html":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW","download_json":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW.json","view_paper":"https://pith.science/paper/GVJFYLL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.00693&json=true","fetch_graph":"https://pith.science/api/pith-number/GVJFYLL35ITKJJK72JD3AYFXNW/graph.json","fetch_events":"https://pith.science/api/pith-number/GVJFYLL35ITKJJK72JD3AYFXNW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW/action/storage_attestation","attest_author":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW/action/author_attestation","sign_citation":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW/action/citation_signature","submit_replication":"https://pith.science/pith/GVJFYLL35ITKJJK72JD3AYFXNW/action/replication_record"}},"created_at":"2026-07-05T05:01:40.716394+00:00","updated_at":"2026-07-05T05:01:40.716394+00:00"}