{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NAPUMY3DDGOOOYCH6DXVCZ2NSS","short_pith_number":"pith:NAPUMY3D","schema_version":"1.0","canonical_sha256":"681f466363199ce76047f0ef51674d94924017ecf7a09afb42663fd1b5f89e90","source":{"kind":"arxiv","id":"2507.05020","version":2},"attestation_state":"computed","paper":{"title":"Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Britty Baby, Nicolas Padoy, Soham Walimbe, Vinkle Srivastav","submitted_at":"2025-07-07T14:03:10Z","abstract_excerpt":"Surgical AI often involves multiple tasks within a single procedure, like phase recognition or assessing the Critical View of Safety in laparoscopic cholecystectomy. Traditional models, built for one task at a time, lack flexibility, requiring a separate model for each. To address this, we introduce MML-SurgAdapt, a unified multi-task framework with Vision-Language Models (VLMs), specifically CLIP, to handle diverse surgical tasks through natural language supervision. A key challenge in multi-task learning is the presence of partial annotations when integrating different tasks. To overcome thi"},"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":"2507.05020","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-07-07T14:03:10Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"f827607ef4885db6be83164097638de6614403f79c4820ec3c3c75a88adbae0f","abstract_canon_sha256":"fc88ce84203824493fc6a384ac868bdceb855aa03d769b65a77431e068fbf776"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:53.427797Z","signature_b64":"cSnvM/r6pG577UO/E3EJrgWAq83USrIBdtaAhEBXSDHCKIOfCkS/U6F9i0XbIQ11CPkOS02JPT5Qd/51NVyTBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"681f466363199ce76047f0ef51674d94924017ecf7a09afb42663fd1b5f89e90","last_reissued_at":"2026-07-05T11:34:53.427297Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:53.427297Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Adaptation of Multi-modal Representation Models for Multi-task Surgical Computer Vision","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Britty Baby, Nicolas Padoy, Soham Walimbe, Vinkle Srivastav","submitted_at":"2025-07-07T14:03:10Z","abstract_excerpt":"Surgical AI often involves multiple tasks within a single procedure, like phase recognition or assessing the Critical View of Safety in laparoscopic cholecystectomy. Traditional models, built for one task at a time, lack flexibility, requiring a separate model for each. To address this, we introduce MML-SurgAdapt, a unified multi-task framework with Vision-Language Models (VLMs), specifically CLIP, to handle diverse surgical tasks through natural language supervision. A key challenge in multi-task learning is the presence of partial annotations when integrating different tasks. To overcome thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.05020","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/2507.05020/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":"2507.05020","created_at":"2026-07-05T11:34:53.427365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.05020v2","created_at":"2026-07-05T11:34:53.427365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.05020","created_at":"2026-07-05T11:34:53.427365+00:00"},{"alias_kind":"pith_short_12","alias_value":"NAPUMY3DDGOO","created_at":"2026-07-05T11:34:53.427365+00:00"},{"alias_kind":"pith_short_16","alias_value":"NAPUMY3DDGOOOYCH","created_at":"2026-07-05T11:34:53.427365+00:00"},{"alias_kind":"pith_short_8","alias_value":"NAPUMY3D","created_at":"2026-07-05T11:34:53.427365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS","json":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS.json","graph_json":"https://pith.science/api/pith-number/NAPUMY3DDGOOOYCH6DXVCZ2NSS/graph.json","events_json":"https://pith.science/api/pith-number/NAPUMY3DDGOOOYCH6DXVCZ2NSS/events.json","paper":"https://pith.science/paper/NAPUMY3D"},"agent_actions":{"view_html":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS","download_json":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS.json","view_paper":"https://pith.science/paper/NAPUMY3D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.05020&json=true","fetch_graph":"https://pith.science/api/pith-number/NAPUMY3DDGOOOYCH6DXVCZ2NSS/graph.json","fetch_events":"https://pith.science/api/pith-number/NAPUMY3DDGOOOYCH6DXVCZ2NSS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS/action/storage_attestation","attest_author":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS/action/author_attestation","sign_citation":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS/action/citation_signature","submit_replication":"https://pith.science/pith/NAPUMY3DDGOOOYCH6DXVCZ2NSS/action/replication_record"}},"created_at":"2026-07-05T11:34:53.427365+00:00","updated_at":"2026-07-05T11:34:53.427365+00:00"}