{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:G5OR3IEWBLYEEQA4JZDK2VG3N7","short_pith_number":"pith:G5OR3IEW","schema_version":"1.0","canonical_sha256":"375d1da0960af042401c4e46ad54db6fdff13f8aa6c91920523031e5a1cdd32e","source":{"kind":"arxiv","id":"2509.06831","version":1},"attestation_state":"computed","paper":{"title":"Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beat P. M\\\"uller, Jan S. Liechti, J\\'er\\^ome A. Kurylec, Jo\\\"el L. Lavanchy, Simon Pezold","submitted_at":"2025-09-08T16:04:19Z","abstract_excerpt":"We investigate how both the adaptation of a generic foundation model via transfer learning and the integration of complementary modalities from the operating room (OR) can support surgical data science. To this end, we use V-JEPA as the single-modality foundation of a multimodal model for minimally invasive surgery support. We analyze how the model's downstream performance can benefit (a) from finetuning on unlabeled surgical video data and (b) from providing additional time-resolved data streams from the OR in a multimodal setup.\n  In an in-house dataset of liver surgery videos, we analyze th"},"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":"2509.06831","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-09-08T16:04:19Z","cross_cats_sorted":[],"title_canon_sha256":"5bdd8b6075829c52a808b064d76c7a2a4913d1c08421bb24c16ad3e378a35d55","abstract_canon_sha256":"a30eac3a6fdba6031e49a2f3c6be305565dd13a6ab6ca92ba63b7df58ad02763"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:06:53.826209Z","signature_b64":"4LHJMDVWK5sdOkSe+z68bUPHBHZXOtPrENHeGhr7502+RWdlkMcNpPgQ1MyYH7cOkIz+GJ95iKjrHPJAaVe5AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"375d1da0960af042401c4e46ad54db6fdff13f8aa6c91920523031e5a1cdd32e","last_reissued_at":"2026-07-05T12:06:53.825734Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:06:53.825734Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Leveraging Generic Foundation Models for Multimodal Surgical Data Analysis","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Beat P. M\\\"uller, Jan S. Liechti, J\\'er\\^ome A. Kurylec, Jo\\\"el L. Lavanchy, Simon Pezold","submitted_at":"2025-09-08T16:04:19Z","abstract_excerpt":"We investigate how both the adaptation of a generic foundation model via transfer learning and the integration of complementary modalities from the operating room (OR) can support surgical data science. To this end, we use V-JEPA as the single-modality foundation of a multimodal model for minimally invasive surgery support. We analyze how the model's downstream performance can benefit (a) from finetuning on unlabeled surgical video data and (b) from providing additional time-resolved data streams from the OR in a multimodal setup.\n  In an in-house dataset of liver surgery videos, we analyze th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.06831","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/2509.06831/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":"2509.06831","created_at":"2026-07-05T12:06:53.825795+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.06831v1","created_at":"2026-07-05T12:06:53.825795+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.06831","created_at":"2026-07-05T12:06:53.825795+00:00"},{"alias_kind":"pith_short_12","alias_value":"G5OR3IEWBLYE","created_at":"2026-07-05T12:06:53.825795+00:00"},{"alias_kind":"pith_short_16","alias_value":"G5OR3IEWBLYEEQA4","created_at":"2026-07-05T12:06:53.825795+00:00"},{"alias_kind":"pith_short_8","alias_value":"G5OR3IEW","created_at":"2026-07-05T12:06:53.825795+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/G5OR3IEWBLYEEQA4JZDK2VG3N7","json":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7.json","graph_json":"https://pith.science/api/pith-number/G5OR3IEWBLYEEQA4JZDK2VG3N7/graph.json","events_json":"https://pith.science/api/pith-number/G5OR3IEWBLYEEQA4JZDK2VG3N7/events.json","paper":"https://pith.science/paper/G5OR3IEW"},"agent_actions":{"view_html":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7","download_json":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7.json","view_paper":"https://pith.science/paper/G5OR3IEW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.06831&json=true","fetch_graph":"https://pith.science/api/pith-number/G5OR3IEWBLYEEQA4JZDK2VG3N7/graph.json","fetch_events":"https://pith.science/api/pith-number/G5OR3IEWBLYEEQA4JZDK2VG3N7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7/action/storage_attestation","attest_author":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7/action/author_attestation","sign_citation":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7/action/citation_signature","submit_replication":"https://pith.science/pith/G5OR3IEWBLYEEQA4JZDK2VG3N7/action/replication_record"}},"created_at":"2026-07-05T12:06:53.825795+00:00","updated_at":"2026-07-05T12:06:53.825795+00:00"}