{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RN7YQL5QBQF3SKQD54WRBTVA5U","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":"564c0c42d7dcae6241d0707c5b11ce5133e981afc1372eeffae94badf2790e2c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T06:33:12Z","title_canon_sha256":"70979b30599a901e90183c6d5a2bd23a168167f3e35d5e2beab4ae3dee5de5e2"},"schema_version":"1.0","source":{"id":"2409.04732","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2409.04732","created_at":"2026-07-05T09:06:09Z"},{"alias_kind":"arxiv_version","alias_value":"2409.04732v2","created_at":"2026-07-05T09:06:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.04732","created_at":"2026-07-05T09:06:09Z"},{"alias_kind":"pith_short_12","alias_value":"RN7YQL5QBQF3","created_at":"2026-07-05T09:06:09Z"},{"alias_kind":"pith_short_16","alias_value":"RN7YQL5QBQF3SKQD","created_at":"2026-07-05T09:06:09Z"},{"alias_kind":"pith_short_8","alias_value":"RN7YQL5Q","created_at":"2026-07-05T09:06:09Z"}],"graph_snapshots":[{"event_id":"sha256:6f7567f08d27f970d829019db34428a4ec0d2390708f3070c05b6f7e47a3a0a5","target":"graph","created_at":"2026-07-05T09:06:09Z","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/2409.04732/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We introduce VidLPRO, a novel video-language (VL) pre-training framework designed specifically for robotic and laparoscopic surgery. While existing surgical VL models primarily rely on contrastive learning, we propose a more comprehensive approach to capture the intricate temporal dynamics and align video with language. VidLPRO integrates video-text contrastive learning, video-text matching, and masked language modeling objectives to learn rich VL representations. To support this framework, we present GenSurg+, a carefully curated dataset derived from GenSurgery, comprising 17k surgical video ","authors_text":"Mohammadmahdi Honarmand, Muhammad Abdullah Jamal, Omid Mohareri","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T06:33:12Z","title":"VidLPRO: A $\\underline{Vid}$eo-$\\underline{L}$anguage $\\underline{P}$re-training Framework for $\\underline{Ro}$botic and Laparoscopic Surgery"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.04732","kind":"arxiv","version":2},"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:c78c58012d45204768b305bca22ff9c7cad4a265f3b0276b70282d52b2e89035","target":"record","created_at":"2026-07-05T09:06:09Z","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":"564c0c42d7dcae6241d0707c5b11ce5133e981afc1372eeffae94badf2790e2c","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-09-07T06:33:12Z","title_canon_sha256":"70979b30599a901e90183c6d5a2bd23a168167f3e35d5e2beab4ae3dee5de5e2"},"schema_version":"1.0","source":{"id":"2409.04732","kind":"arxiv","version":2}},"canonical_sha256":"8b7f882fb00c0bb92a03ef2d10cea0ed264656ec9fd2471d6116ab0066ef24c1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8b7f882fb00c0bb92a03ef2d10cea0ed264656ec9fd2471d6116ab0066ef24c1","first_computed_at":"2026-07-05T09:06:09.339371Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:06:09.339371Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SQK/JisEWuTLyaPYNApwugO63C8PQPxoMOV8e6tWyO/B9mw8gRfb/fl+Ho8sEjWDF4pLPoDkLIessv57vsnRCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T09:06:09.339825Z","signed_message":"canonical_sha256_bytes"},"source_id":"2409.04732","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c78c58012d45204768b305bca22ff9c7cad4a265f3b0276b70282d52b2e89035","sha256:6f7567f08d27f970d829019db34428a4ec0d2390708f3070c05b6f7e47a3a0a5"],"state_sha256":"35351a4ede8d1fbd67345469792da335f65fbbac078025b8029711bfc5724245"}