{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:X6DBCJGPMCQHBN7AIDKQNJFI32","short_pith_number":"pith:X6DBCJGP","schema_version":"1.0","canonical_sha256":"bf861124cf60a070b7e040d506a4a8de8a2399d05b8ff599fa9c6524a94014fd","source":{"kind":"arxiv","id":"2504.19918","version":1},"attestation_state":"computed","paper":{"title":"Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cristian Cosentino, Fabrizio Marozzo, Hugo Georgenthum, Pietro Li\\`o","submitted_at":"2025-04-28T15:46:02Z","abstract_excerpt":"The automatic summarization of surgical videos is essential for enhancing procedural documentation, supporting surgical training, and facilitating post-operative analysis. This paper presents a novel method at the intersection of artificial intelligence and medicine, aiming to develop machine learning models with direct real-world applications in surgical contexts. We propose a multi-modal framework that leverages recent advancements in computer vision and large language models to generate comprehensive video summaries. %\nThe approach is structured in three key stages. First, surgical videos a"},"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":"2504.19918","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-04-28T15:46:02Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c4e03da748a5068295244333da44febb3b84a3b482534a0ca402ff012228fd0","abstract_canon_sha256":"46361d5a6feb058b17049938d4edfc19fa36b5d249498fc53729fd8e370709f8"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:06.341062Z","signature_b64":"E4Q625wq4gU6zwrzxld+4rEmL9gSYVT2qBV09i3lBChjwx7LMRb18HJd7b4PiTaNX/eDcBzI3oDH1SUB7c57CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bf861124cf60a070b7e040d506a4a8de8a2399d05b8ff599fa9c6524a94014fd","last_reissued_at":"2026-07-05T10:55:06.340585Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:06.340585Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhancing Surgical Documentation through Multimodal Visual-Temporal Transformers and Generative AI","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Cristian Cosentino, Fabrizio Marozzo, Hugo Georgenthum, Pietro Li\\`o","submitted_at":"2025-04-28T15:46:02Z","abstract_excerpt":"The automatic summarization of surgical videos is essential for enhancing procedural documentation, supporting surgical training, and facilitating post-operative analysis. This paper presents a novel method at the intersection of artificial intelligence and medicine, aiming to develop machine learning models with direct real-world applications in surgical contexts. We propose a multi-modal framework that leverages recent advancements in computer vision and large language models to generate comprehensive video summaries. %\nThe approach is structured in three key stages. First, surgical videos a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.19918","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/2504.19918/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":"2504.19918","created_at":"2026-07-05T10:55:06.340642+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.19918v1","created_at":"2026-07-05T10:55:06.340642+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.19918","created_at":"2026-07-05T10:55:06.340642+00:00"},{"alias_kind":"pith_short_12","alias_value":"X6DBCJGPMCQH","created_at":"2026-07-05T10:55:06.340642+00:00"},{"alias_kind":"pith_short_16","alias_value":"X6DBCJGPMCQHBN7A","created_at":"2026-07-05T10:55:06.340642+00:00"},{"alias_kind":"pith_short_8","alias_value":"X6DBCJGP","created_at":"2026-07-05T10:55:06.340642+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.08712","citing_title":"From Articulated Kinematics to Routed Visual Control for Action-Conditioned Surgical Video Generation","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32","json":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32.json","graph_json":"https://pith.science/api/pith-number/X6DBCJGPMCQHBN7AIDKQNJFI32/graph.json","events_json":"https://pith.science/api/pith-number/X6DBCJGPMCQHBN7AIDKQNJFI32/events.json","paper":"https://pith.science/paper/X6DBCJGP"},"agent_actions":{"view_html":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32","download_json":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32.json","view_paper":"https://pith.science/paper/X6DBCJGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.19918&json=true","fetch_graph":"https://pith.science/api/pith-number/X6DBCJGPMCQHBN7AIDKQNJFI32/graph.json","fetch_events":"https://pith.science/api/pith-number/X6DBCJGPMCQHBN7AIDKQNJFI32/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32/action/timestamp_anchor","attest_storage":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32/action/storage_attestation","attest_author":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32/action/author_attestation","sign_citation":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32/action/citation_signature","submit_replication":"https://pith.science/pith/X6DBCJGPMCQHBN7AIDKQNJFI32/action/replication_record"}},"created_at":"2026-07-05T10:55:06.340642+00:00","updated_at":"2026-07-05T10:55:06.340642+00:00"}