{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:T65F6P7JRZEMSV2JUWLM4MXHYW","short_pith_number":"pith:T65F6P7J","schema_version":"1.0","canonical_sha256":"9fba5f3fe98e48c95749a596ce32e7c58b81d121289af216751d49e917139729","source":{"kind":"arxiv","id":"2103.09712","version":2},"attestation_state":"computed","paper":{"title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Pheng-Ann Heng, Qi Dou, Xiaojie Gao, Yonghao Long, Yueming Jin","submitted_at":"2021-03-17T15:12:55Z","abstract_excerpt":"Real-time surgical phase recognition is a fundamental task in modern operating rooms. Previous works tackle this task relying on architectures arranged in spatio-temporal order, however, the supportive benefits of intermediate spatial features are not considered. In this paper, we introduce, for the first time in surgical workflow analysis, Transformer to reconsider the ignored complementary effects of spatial and temporal features for accurate surgical phase recognition. Our hybrid embedding aggregation Transformer fuses cleverly designed spatial and temporal embeddings by allowing for active"},"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":"2103.09712","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2021-03-17T15:12:55Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d7340b6f142f9dbf5daecb92d78cc495f3745ec88b52ed5ff9f17e9ccb120ce","abstract_canon_sha256":"34e10669069e2eff945637ca4ea32bdfe2249190690736d7e7f2b3be8626889e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:57.408706Z","signature_b64":"aDb+n27p9MPxQzpdNq49LpExBxUMC3ClBj4WUNpnKqhRbNV96o6xQ+6G8ckwyRDac6ax9Xi5itWDUZps9yaNBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9fba5f3fe98e48c95749a596ce32e7c58b81d121289af216751d49e917139729","last_reissued_at":"2026-07-05T02:56:57.408234Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:57.408234Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Trans-SVNet: Accurate Phase Recognition from Surgical Videos via Hybrid Embedding Aggregation Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Pheng-Ann Heng, Qi Dou, Xiaojie Gao, Yonghao Long, Yueming Jin","submitted_at":"2021-03-17T15:12:55Z","abstract_excerpt":"Real-time surgical phase recognition is a fundamental task in modern operating rooms. Previous works tackle this task relying on architectures arranged in spatio-temporal order, however, the supportive benefits of intermediate spatial features are not considered. In this paper, we introduce, for the first time in surgical workflow analysis, Transformer to reconsider the ignored complementary effects of spatial and temporal features for accurate surgical phase recognition. Our hybrid embedding aggregation Transformer fuses cleverly designed spatial and temporal embeddings by allowing for active"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2103.09712","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/2103.09712/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":"2103.09712","created_at":"2026-07-05T02:56:57.408303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2103.09712v2","created_at":"2026-07-05T02:56:57.408303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2103.09712","created_at":"2026-07-05T02:56:57.408303+00:00"},{"alias_kind":"pith_short_12","alias_value":"T65F6P7JRZEM","created_at":"2026-07-05T02:56:57.408303+00:00"},{"alias_kind":"pith_short_16","alias_value":"T65F6P7JRZEMSV2J","created_at":"2026-07-05T02:56:57.408303+00:00"},{"alias_kind":"pith_short_8","alias_value":"T65F6P7J","created_at":"2026-07-05T02:56:57.408303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.07577","citing_title":"Event-Level Detection of Surgical Instrument Handovers in Videos with Interpretable Vision Models","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW","json":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW.json","graph_json":"https://pith.science/api/pith-number/T65F6P7JRZEMSV2JUWLM4MXHYW/graph.json","events_json":"https://pith.science/api/pith-number/T65F6P7JRZEMSV2JUWLM4MXHYW/events.json","paper":"https://pith.science/paper/T65F6P7J"},"agent_actions":{"view_html":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW","download_json":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW.json","view_paper":"https://pith.science/paper/T65F6P7J","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2103.09712&json=true","fetch_graph":"https://pith.science/api/pith-number/T65F6P7JRZEMSV2JUWLM4MXHYW/graph.json","fetch_events":"https://pith.science/api/pith-number/T65F6P7JRZEMSV2JUWLM4MXHYW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW/action/storage_attestation","attest_author":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW/action/author_attestation","sign_citation":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW/action/citation_signature","submit_replication":"https://pith.science/pith/T65F6P7JRZEMSV2JUWLM4MXHYW/action/replication_record"}},"created_at":"2026-07-05T02:56:57.408303+00:00","updated_at":"2026-07-05T02:56:57.408303+00:00"}