{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:4FF4RCNW5CXGBKZZH7I7QMY3IR","short_pith_number":"pith:4FF4RCNW","canonical_record":{"source":{"id":"2307.15220","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T22:38:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfbaf6ddec72dee00912e0871bcfe5325549d889d518456055d7de129189ebc8","abstract_canon_sha256":"4472579893a66b41afb723fb613158d4f61be8fbe4f5764464ed10678ef5fcb4"},"schema_version":"1.0"},"canonical_sha256":"e14bc889b6e8ae60ab393fd1f8331b444f237b6d81e0cceb6f01244f389fd29b","source":{"kind":"arxiv","id":"2307.15220","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15220","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15220v5","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15220","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"4FF4RCNW5CXG","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"pith_short_16","alias_value":"4FF4RCNW5CXGBKZZ","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"pith_short_8","alias_value":"4FF4RCNW","created_at":"2026-07-05T11:22:28Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:4FF4RCNW5CXGBKZZH7I7QMY3IR","target":"record","payload":{"canonical_record":{"source":{"id":"2307.15220","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T22:38:12Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"cfbaf6ddec72dee00912e0871bcfe5325549d889d518456055d7de129189ebc8","abstract_canon_sha256":"4472579893a66b41afb723fb613158d4f61be8fbe4f5764464ed10678ef5fcb4"},"schema_version":"1.0"},"canonical_sha256":"e14bc889b6e8ae60ab393fd1f8331b444f237b6d81e0cceb6f01244f389fd29b","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:28.510674Z","signature_b64":"ekY47jW3GPk9pjeRPkoCE0HAlSn2xp58iMYwIjNUjghBdgqAK5ud4y5sZz+KcZVLvPO2+z1Z0PIRQxEUYY+DCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e14bc889b6e8ae60ab393fd1f8331b444f237b6d81e0cceb6f01244f389fd29b","last_reissued_at":"2026-07-05T11:22:28.510214Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:28.510214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2307.15220","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iXb5APFCMEI4MkzRBYNg3/t2eBbM1gwKnHymWqkFak7bB/j3IL8kofEieuPN6CTGEmaiwoFqKYA/mLW3nHdyDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T02:04:12.259485Z"},"content_sha256":"61318f802ac9108e1e0f078e5a2f292d7fae3ed2b6b9652dc71dca68364afe7d","schema_version":"1.0","event_id":"sha256:61318f802ac9108e1e0f078e5a2f292d7fae3ed2b6b9652dc71dca68364afe7d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:4FF4RCNW5CXGBKZZH7I7QMY3IR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Jacques Marescaux, Joel L. Lavanchy, Kun Yuan, Nassir Navab, Nicolas Padoy, Pietro Mascagni, Tong Yu, Vinkle Srivastav","submitted_at":"2023-07-27T22:38:12Z","abstract_excerpt":"Recent advancements in surgical computer vision applications have been driven by vision-only models, which do not explicitly integrate the rich semantics of language into their design. These methods rely on manually annotated surgical videos to predict a fixed set of object categories, limiting their generalizability to unseen surgical procedures and downstream tasks. In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective vision and language supervisory signals for multi-modal representation learning wit"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15220","kind":"arxiv","version":5},"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/2307.15220/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:22:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"426x48adod47KtKvj7B0rD/kP+KiYfv3G0Udgm6uuUsDl6DAm1ZjYi+005ScyQodyl5+BRNYmoYialCTNuiYDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-16T02:04:12.260478Z"},"content_sha256":"7e1f1a342fcfe445227a8679e2d41b8e8a4c8c0e4848d92e2824afc90e65f01b","schema_version":"1.0","event_id":"sha256:7e1f1a342fcfe445227a8679e2d41b8e8a4c8c0e4848d92e2824afc90e65f01b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4FF4RCNW5CXGBKZZH7I7QMY3IR/bundle.json","state_url":"https://pith.science/pith/4FF4RCNW5CXGBKZZH7I7QMY3IR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4FF4RCNW5CXGBKZZH7I7QMY3IR/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-16T02:04:12Z","links":{"resolver":"https://pith.science/pith/4FF4RCNW5CXGBKZZH7I7QMY3IR","bundle":"https://pith.science/pith/4FF4RCNW5CXGBKZZH7I7QMY3IR/bundle.json","state":"https://pith.science/pith/4FF4RCNW5CXGBKZZH7I7QMY3IR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4FF4RCNW5CXGBKZZH7I7QMY3IR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:4FF4RCNW5CXGBKZZH7I7QMY3IR","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":"4472579893a66b41afb723fb613158d4f61be8fbe4f5764464ed10678ef5fcb4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T22:38:12Z","title_canon_sha256":"cfbaf6ddec72dee00912e0871bcfe5325549d889d518456055d7de129189ebc8"},"schema_version":"1.0","source":{"id":"2307.15220","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2307.15220","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"arxiv_version","alias_value":"2307.15220v5","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.15220","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"pith_short_12","alias_value":"4FF4RCNW5CXG","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"pith_short_16","alias_value":"4FF4RCNW5CXGBKZZ","created_at":"2026-07-05T11:22:28Z"},{"alias_kind":"pith_short_8","alias_value":"4FF4RCNW","created_at":"2026-07-05T11:22:28Z"}],"graph_snapshots":[{"event_id":"sha256:7e1f1a342fcfe445227a8679e2d41b8e8a4c8c0e4848d92e2824afc90e65f01b","target":"graph","created_at":"2026-07-05T11:22:28Z","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/2307.15220/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent advancements in surgical computer vision applications have been driven by vision-only models, which do not explicitly integrate the rich semantics of language into their design. These methods rely on manually annotated surgical videos to predict a fixed set of object categories, limiting their generalizability to unseen surgical procedures and downstream tasks. In this work, we put forward the idea that the surgical video lectures available through open surgical e-learning platforms can provide effective vision and language supervisory signals for multi-modal representation learning wit","authors_text":"Jacques Marescaux, Joel L. Lavanchy, Kun Yuan, Nassir Navab, Nicolas Padoy, Pietro Mascagni, Tong Yu, Vinkle Srivastav","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T22:38:12Z","title":"Learning Multi-modal Representations by Watching Hundreds of Surgical Video Lectures"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.15220","kind":"arxiv","version":5},"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":"sha256:61318f802ac9108e1e0f078e5a2f292d7fae3ed2b6b9652dc71dca68364afe7d","target":"record","created_at":"2026-07-05T11:22:28Z","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":"4472579893a66b41afb723fb613158d4f61be8fbe4f5764464ed10678ef5fcb4","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-07-27T22:38:12Z","title_canon_sha256":"cfbaf6ddec72dee00912e0871bcfe5325549d889d518456055d7de129189ebc8"},"schema_version":"1.0","source":{"id":"2307.15220","kind":"arxiv","version":5}},"canonical_sha256":"e14bc889b6e8ae60ab393fd1f8331b444f237b6d81e0cceb6f01244f389fd29b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e14bc889b6e8ae60ab393fd1f8331b444f237b6d81e0cceb6f01244f389fd29b","first_computed_at":"2026-07-05T11:22:28.510214Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:28.510214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ekY47jW3GPk9pjeRPkoCE0HAlSn2xp58iMYwIjNUjghBdgqAK5ud4y5sZz+KcZVLvPO2+z1Z0PIRQxEUYY+DCg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:28.510674Z","signed_message":"canonical_sha256_bytes"},"source_id":"2307.15220","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:61318f802ac9108e1e0f078e5a2f292d7fae3ed2b6b9652dc71dca68364afe7d","sha256:7e1f1a342fcfe445227a8679e2d41b8e8a4c8c0e4848d92e2824afc90e65f01b"],"state_sha256":"9d3c62582b6941df260f44426f2c82013d98ca19a6caeffc8dc25c30267004e4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"A6LUVJcLwhPR4aJz00u/iBjczZXGfojaWCV9nfLNwHO4XYVHl88W4jkbmUwHXvdTV7P/z2ELwu7A3qHATGNuAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-16T02:04:12.268279Z","bundle_sha256":"329870e36070aab2967e55947ecd784bd0f80bd5c5d191c7b2e8a3f077b3fa4f"}}