{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:XPEMON53WMHNWVO5DJSHIB275J","short_pith_number":"pith:XPEMON53","schema_version":"1.0","canonical_sha256":"bbc8c737bbb30edb55dd1a6474075fea57fb2e07da32277dfca4b1763920b874","source":{"kind":"arxiv","id":"2503.11392","version":1},"attestation_state":"computed","paper":{"title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Constantin Patsch, David Gastager, Ghazal Ghazaei","submitted_at":"2025-03-14T13:36:13Z","abstract_excerpt":"Automated surgical workflow analysis is crucial for education, research, and clinical decision-making, but the lack of annotated datasets hinders the development of accurate and comprehensive workflow analysis solutions. We introduce a novel approach for addressing the sparsity and heterogeneity of annotated training data inspired by the human learning procedure of watching experts and understanding their explanations. Our method leverages a video-language model trained on alignment, denoising, and generative tasks to learn short-term spatio-temporal and multimodal representations. A task-spec"},"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":"2503.11392","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T13:36:13Z","cross_cats_sorted":[],"title_canon_sha256":"4ae53a0ebaad59e14802bd680748ce7334bc4a58f99f30d04be1edd2f217492a","abstract_canon_sha256":"c8b95ac5066ed8574e4327e189b5c93aaa6912690c6ba3eeab19f7ef9e036021"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:30.356442Z","signature_b64":"TM1yAnXWVw6uatk35v+3t1mOGHNJrTAMWEJiq0IuU9B9qz7Totm9cMElmOZR8s/+o9ckdqqctbZoVyS68ku8Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bbc8c737bbb30edb55dd1a6474075fea57fb2e07da32277dfca4b1763920b874","last_reissued_at":"2026-07-05T10:31:30.355719Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:30.355719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Constantin Patsch, David Gastager, Ghazal Ghazaei","submitted_at":"2025-03-14T13:36:13Z","abstract_excerpt":"Automated surgical workflow analysis is crucial for education, research, and clinical decision-making, but the lack of annotated datasets hinders the development of accurate and comprehensive workflow analysis solutions. We introduce a novel approach for addressing the sparsity and heterogeneity of annotated training data inspired by the human learning procedure of watching experts and understanding their explanations. Our method leverages a video-language model trained on alignment, denoising, and generative tasks to learn short-term spatio-temporal and multimodal representations. A task-spec"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11392","kind":"arxiv","version":1},"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/2503.11392/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":"2503.11392","created_at":"2026-07-05T10:31:30.355809+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11392v1","created_at":"2026-07-05T10:31:30.355809+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11392","created_at":"2026-07-05T10:31:30.355809+00:00"},{"alias_kind":"pith_short_12","alias_value":"XPEMON53WMHN","created_at":"2026-07-05T10:31:30.355809+00:00"},{"alias_kind":"pith_short_16","alias_value":"XPEMON53WMHNWVO5","created_at":"2026-07-05T10:31:30.355809+00:00"},{"alias_kind":"pith_short_8","alias_value":"XPEMON53","created_at":"2026-07-05T10:31:30.355809+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2506.21813","citing_title":"CAT-SG: A Large Dynamic Scene Graph Dataset for Fine-Grained Understanding of Cataract Surgery","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J","json":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J.json","graph_json":"https://pith.science/api/pith-number/XPEMON53WMHNWVO5DJSHIB275J/graph.json","events_json":"https://pith.science/api/pith-number/XPEMON53WMHNWVO5DJSHIB275J/events.json","paper":"https://pith.science/paper/XPEMON53"},"agent_actions":{"view_html":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J","download_json":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J.json","view_paper":"https://pith.science/paper/XPEMON53","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11392&json=true","fetch_graph":"https://pith.science/api/pith-number/XPEMON53WMHNWVO5DJSHIB275J/graph.json","fetch_events":"https://pith.science/api/pith-number/XPEMON53WMHNWVO5DJSHIB275J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J/action/storage_attestation","attest_author":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J/action/author_attestation","sign_citation":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J/action/citation_signature","submit_replication":"https://pith.science/pith/XPEMON53WMHNWVO5DJSHIB275J/action/replication_record"}},"created_at":"2026-07-05T10:31:30.355809+00:00","updated_at":"2026-07-05T10:31:30.355809+00:00"}