{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Y2BQOLVHBPENMIDFS3PPPKYA4","short_pith_number":"pith:7Y2BQOLV","schema_version":"1.0","canonical_sha256":"fe34183975385e46b1032cb6f7bd5807172734b7031cd8228b3998e171d36023","source":{"kind":"arxiv","id":"2405.10075","version":2},"attestation_state":"computed","paper":{"title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kun Yuan, Nassir Navab, Nicolas Padoy, Vinkle Srivastav","submitted_at":"2024-05-16T13:14:43Z","abstract_excerpt":"Natural language could play an important role in developing generalist surgical models by providing a broad source of supervision from raw texts. This flexible form of supervision can enable the model's transferability across datasets and tasks as natural language can be used to reference learned visual concepts or describe new ones. In this work, we present HecVL, a novel hierarchical video-language pretraining approach for building a generalist surgical model. Specifically, we construct a hierarchical video-text paired dataset by pairing the surgical lecture video with three hierarchical lev"},"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":"2405.10075","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-05-16T13:14:43Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c08e83dbb96576c195222afadc22b0b769b3ba94794208e13b9a7aa44d64bbf8","abstract_canon_sha256":"2bf8300f972e8826cadf3292f7e00aaf2aa9f3ad19e788d3a0057de43dd043e0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:30:21.003126Z","signature_b64":"iDqB3tYfwA574ExNJlVZSpnQNwqDEncmQCoAFQcCpemqlGDxCtWFZ4NbIgtu2E9picz00S6vM5BHa350KVX7Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe34183975385e46b1032cb6f7bd5807172734b7031cd8228b3998e171d36023","last_reissued_at":"2026-07-05T10:30:21.002427Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:30:21.002427Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HecVL: Hierarchical Video-Language Pretraining for Zero-shot Surgical Phase Recognition","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Kun Yuan, Nassir Navab, Nicolas Padoy, Vinkle Srivastav","submitted_at":"2024-05-16T13:14:43Z","abstract_excerpt":"Natural language could play an important role in developing generalist surgical models by providing a broad source of supervision from raw texts. This flexible form of supervision can enable the model's transferability across datasets and tasks as natural language can be used to reference learned visual concepts or describe new ones. In this work, we present HecVL, a novel hierarchical video-language pretraining approach for building a generalist surgical model. Specifically, we construct a hierarchical video-text paired dataset by pairing the surgical lecture video with three hierarchical lev"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.10075","kind":"arxiv","version":2},"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/2405.10075/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":"2405.10075","created_at":"2026-07-05T10:30:21.002513+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.10075v2","created_at":"2026-07-05T10:30:21.002513+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.10075","created_at":"2026-07-05T10:30:21.002513+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Y2BQOLVHBPE","created_at":"2026-07-05T10:30:21.002513+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Y2BQOLVHBPENMID","created_at":"2026-07-05T10:30:21.002513+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Y2BQOLV","created_at":"2026-07-05T10:30:21.002513+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.15326","citing_title":"Recognize Any Surgical Object: Unleashing the Power of Weakly-Supervised Data","ref_index":20,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4","json":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4.json","graph_json":"https://pith.science/api/pith-number/7Y2BQOLVHBPENMIDFS3PPPKYA4/graph.json","events_json":"https://pith.science/api/pith-number/7Y2BQOLVHBPENMIDFS3PPPKYA4/events.json","paper":"https://pith.science/paper/7Y2BQOLV"},"agent_actions":{"view_html":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4","download_json":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4.json","view_paper":"https://pith.science/paper/7Y2BQOLV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.10075&json=true","fetch_graph":"https://pith.science/api/pith-number/7Y2BQOLVHBPENMIDFS3PPPKYA4/graph.json","fetch_events":"https://pith.science/api/pith-number/7Y2BQOLVHBPENMIDFS3PPPKYA4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4/action/storage_attestation","attest_author":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4/action/author_attestation","sign_citation":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4/action/citation_signature","submit_replication":"https://pith.science/pith/7Y2BQOLVHBPENMIDFS3PPPKYA4/action/replication_record"}},"created_at":"2026-07-05T10:30:21.002513+00:00","updated_at":"2026-07-05T10:30:21.002513+00:00"}