{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:V3THO5KPSQYIR3WWCB3N5KAF2W","short_pith_number":"pith:V3THO5KP","schema_version":"1.0","canonical_sha256":"aee677754f943088eed61076dea805d586228e85c69ec7fb121b1c8541536e09","source":{"kind":"arxiv","id":"2312.06829","version":1},"attestation_state":"computed","paper":{"title":"Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Murali, Alain Garcia, Armine Vardazaryan, Deepak Alapatt, Didier Mutter, Nariaki Okamoto, Nicolas Padoy, Pietro Mascagni","submitted_at":"2023-12-11T20:42:27Z","abstract_excerpt":"Recently, spatiotemporal graphs have emerged as a concise and elegant manner of representing video clips in an object-centric fashion, and have shown to be useful for downstream tasks such as action recognition. In this work, we investigate the use of latent spatiotemporal graphs to represent a surgical video in terms of the constituent anatomical structures and tools and their evolving properties over time. To build the graphs, we first predict frame-wise graphs using a pre-trained model, then add temporal edges between nodes based on spatial coherence and visual and semantic similarity. Unli"},"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":"2312.06829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-12-11T20:42:27Z","cross_cats_sorted":[],"title_canon_sha256":"5549de7cb436e7918db8f3d25f00efac9367eb5d7ba550caeffdf01af1cd97d0","abstract_canon_sha256":"c3a22397e8efde5fee288e8c2e1eea8d4119d881293566a569a6aebed00d4b35"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:22:53.582498Z","signature_b64":"MCS9VH5VAbxl773fKRWST+SW6+lpA+ZacyRq2mZcn5UwjZy3BvHFbpnVNC982N/bbkLlt3mqDEL8qi2wR0wzDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"aee677754f943088eed61076dea805d586228e85c69ec7fb121b1c8541536e09","last_reissued_at":"2026-07-05T07:22:53.582052Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:22:53.582052Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Encoding Surgical Videos as Latent Spatiotemporal Graphs for Object and Anatomy-Driven Reasoning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Aditya Murali, Alain Garcia, Armine Vardazaryan, Deepak Alapatt, Didier Mutter, Nariaki Okamoto, Nicolas Padoy, Pietro Mascagni","submitted_at":"2023-12-11T20:42:27Z","abstract_excerpt":"Recently, spatiotemporal graphs have emerged as a concise and elegant manner of representing video clips in an object-centric fashion, and have shown to be useful for downstream tasks such as action recognition. In this work, we investigate the use of latent spatiotemporal graphs to represent a surgical video in terms of the constituent anatomical structures and tools and their evolving properties over time. To build the graphs, we first predict frame-wise graphs using a pre-trained model, then add temporal edges between nodes based on spatial coherence and visual and semantic similarity. Unli"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.06829","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/2312.06829/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":"2312.06829","created_at":"2026-07-05T07:22:53.582109+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.06829v1","created_at":"2026-07-05T07:22:53.582109+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.06829","created_at":"2026-07-05T07:22:53.582109+00:00"},{"alias_kind":"pith_short_12","alias_value":"V3THO5KPSQYI","created_at":"2026-07-05T07:22:53.582109+00:00"},{"alias_kind":"pith_short_16","alias_value":"V3THO5KPSQYIR3WW","created_at":"2026-07-05T07:22:53.582109+00:00"},{"alias_kind":"pith_short_8","alias_value":"V3THO5KP","created_at":"2026-07-05T07:22:53.582109+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/V3THO5KPSQYIR3WWCB3N5KAF2W","json":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W.json","graph_json":"https://pith.science/api/pith-number/V3THO5KPSQYIR3WWCB3N5KAF2W/graph.json","events_json":"https://pith.science/api/pith-number/V3THO5KPSQYIR3WWCB3N5KAF2W/events.json","paper":"https://pith.science/paper/V3THO5KP"},"agent_actions":{"view_html":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W","download_json":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W.json","view_paper":"https://pith.science/paper/V3THO5KP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.06829&json=true","fetch_graph":"https://pith.science/api/pith-number/V3THO5KPSQYIR3WWCB3N5KAF2W/graph.json","fetch_events":"https://pith.science/api/pith-number/V3THO5KPSQYIR3WWCB3N5KAF2W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W/action/storage_attestation","attest_author":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W/action/author_attestation","sign_citation":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W/action/citation_signature","submit_replication":"https://pith.science/pith/V3THO5KPSQYIR3WWCB3N5KAF2W/action/replication_record"}},"created_at":"2026-07-05T07:22:53.582109+00:00","updated_at":"2026-07-05T07:22:53.582109+00:00"}