{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:XPEMON53WMHNWVO5DJSHIB275J","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c8b95ac5066ed8574e4327e189b5c93aaa6912690c6ba3eeab19f7ef9e036021","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T13:36:13Z","title_canon_sha256":"4ae53a0ebaad59e14802bd680748ce7334bc4a58f99f30d04be1edd2f217492a"},"schema_version":"1.0","source":{"id":"2503.11392","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2503.11392","created_at":"2026-07-05T10:31:30Z"},{"alias_kind":"arxiv_version","alias_value":"2503.11392v1","created_at":"2026-07-05T10:31:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11392","created_at":"2026-07-05T10:31:30Z"},{"alias_kind":"pith_short_12","alias_value":"XPEMON53WMHN","created_at":"2026-07-05T10:31:30Z"},{"alias_kind":"pith_short_16","alias_value":"XPEMON53WMHNWVO5","created_at":"2026-07-05T10:31:30Z"},{"alias_kind":"pith_short_8","alias_value":"XPEMON53","created_at":"2026-07-05T10:31:30Z"}],"graph_snapshots":[{"event_id":"sha256:d8c6c112ef03a9e5fcc1703baf0de7f97cdf5b75a2baf4947323b6bf103b92f9","target":"graph","created_at":"2026-07-05T10:31:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2503.11392/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Constantin Patsch, David Gastager, Ghazal Ghazaei","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T13:36:13Z","title":"Watch and Learn: Leveraging Expert Knowledge and Language for Surgical Video Understanding"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11392","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:033a2a8deebe8c62f75af2bd0006adbfcbfce4d2e434e0e9bf741adcd5ea2f56","target":"record","created_at":"2026-07-05T10:31:30Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c8b95ac5066ed8574e4327e189b5c93aaa6912690c6ba3eeab19f7ef9e036021","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-03-14T13:36:13Z","title_canon_sha256":"4ae53a0ebaad59e14802bd680748ce7334bc4a58f99f30d04be1edd2f217492a"},"schema_version":"1.0","source":{"id":"2503.11392","kind":"arxiv","version":1}},"canonical_sha256":"bbc8c737bbb30edb55dd1a6474075fea57fb2e07da32277dfca4b1763920b874","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"bbc8c737bbb30edb55dd1a6474075fea57fb2e07da32277dfca4b1763920b874","first_computed_at":"2026-07-05T10:31:30.355719Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:31:30.355719Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TM1yAnXWVw6uatk35v+3t1mOGHNJrTAMWEJiq0IuU9B9qz7Totm9cMElmOZR8s/+o9ckdqqctbZoVyS68ku8Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T10:31:30.356442Z","signed_message":"canonical_sha256_bytes"},"source_id":"2503.11392","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:033a2a8deebe8c62f75af2bd0006adbfcbfce4d2e434e0e9bf741adcd5ea2f56","sha256:d8c6c112ef03a9e5fcc1703baf0de7f97cdf5b75a2baf4947323b6bf103b92f9"],"state_sha256":"19cc249caf4977fc3004123a87f3be056990821c41efd74722600e0f944c5d24"}