{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5NK7BKMLWZRXZG3MDMH3QI5OIN","short_pith_number":"pith:5NK7BKML","schema_version":"1.0","canonical_sha256":"eb55f0a98bb6637c9b6c1b0fb823ae4379e47a63094845d33bd14b7a4d59cbf1","source":{"kind":"arxiv","id":"2407.19305","version":2},"attestation_state":"computed","paper":{"title":"GP-VLS: A general-purpose vision language model for surgery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.TO"],"primary_cat":"cs.CV","authors_text":"Cyril Zakka, Joseph Cho, Samuel Schmidgall, William Hiesinger","submitted_at":"2024-07-27T17:27:05Z","abstract_excerpt":"Surgery requires comprehensive medical knowledge, visual assessment skills, and procedural expertise. While recent surgical AI models have focused on solving task-specific problems, there is a need for general-purpose systems that can understand surgical scenes and interact through natural language. This paper introduces GP-VLS, a general-purpose vision language model for surgery that integrates medical and surgical knowledge with visual scene understanding. For comprehensively evaluating general-purpose surgical models, we propose SurgiQual, which evaluates across medical and surgical knowled"},"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":"2407.19305","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-07-27T17:27:05Z","cross_cats_sorted":["cs.LG","q-bio.TO"],"title_canon_sha256":"96194b039889e401e8a69f53f53d1d8dc43a31bd583e517b77b3e76d3c91a3a0","abstract_canon_sha256":"feda515a0d9d8bdb46fc140c6e213e3c17c870ccbbf62f537d73cd9c80e53def"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:52:55.830534Z","signature_b64":"bs46OyWJEqUoq5BFa7EWlDqQqNWuAv5x67haQpH3Uai5nD009tcmzGfOF0OT9JVPM4t95zNIHMWVmcxNZFlDAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb55f0a98bb6637c9b6c1b0fb823ae4379e47a63094845d33bd14b7a4d59cbf1","last_reissued_at":"2026-07-05T08:52:55.830111Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:52:55.830111Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GP-VLS: A general-purpose vision language model for surgery","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","q-bio.TO"],"primary_cat":"cs.CV","authors_text":"Cyril Zakka, Joseph Cho, Samuel Schmidgall, William Hiesinger","submitted_at":"2024-07-27T17:27:05Z","abstract_excerpt":"Surgery requires comprehensive medical knowledge, visual assessment skills, and procedural expertise. While recent surgical AI models have focused on solving task-specific problems, there is a need for general-purpose systems that can understand surgical scenes and interact through natural language. This paper introduces GP-VLS, a general-purpose vision language model for surgery that integrates medical and surgical knowledge with visual scene understanding. For comprehensively evaluating general-purpose surgical models, we propose SurgiQual, which evaluates across medical and surgical knowled"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.19305","kind":"arxiv","version":2},"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/2407.19305/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":"2407.19305","created_at":"2026-07-05T08:52:55.830167+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.19305v2","created_at":"2026-07-05T08:52:55.830167+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.19305","created_at":"2026-07-05T08:52:55.830167+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NK7BKMLWZRX","created_at":"2026-07-05T08:52:55.830167+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NK7BKMLWZRXZG3M","created_at":"2026-07-05T08:52:55.830167+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NK7BKML","created_at":"2026-07-05T08:52:55.830167+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.23068","citing_title":"RoboSurg-VQA: A Multimodal Benchmark for Surgical Segmentation-Aware Visual Question Answering","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN","json":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN.json","graph_json":"https://pith.science/api/pith-number/5NK7BKMLWZRXZG3MDMH3QI5OIN/graph.json","events_json":"https://pith.science/api/pith-number/5NK7BKMLWZRXZG3MDMH3QI5OIN/events.json","paper":"https://pith.science/paper/5NK7BKML"},"agent_actions":{"view_html":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN","download_json":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN.json","view_paper":"https://pith.science/paper/5NK7BKML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.19305&json=true","fetch_graph":"https://pith.science/api/pith-number/5NK7BKMLWZRXZG3MDMH3QI5OIN/graph.json","fetch_events":"https://pith.science/api/pith-number/5NK7BKMLWZRXZG3MDMH3QI5OIN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN/action/storage_attestation","attest_author":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN/action/author_attestation","sign_citation":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN/action/citation_signature","submit_replication":"https://pith.science/pith/5NK7BKMLWZRXZG3MDMH3QI5OIN/action/replication_record"}},"created_at":"2026-07-05T08:52:55.830167+00:00","updated_at":"2026-07-05T08:52:55.830167+00:00"}