{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:PDK2TSCQUYP3Q6M2T43B5ASLJJ","short_pith_number":"pith:PDK2TSCQ","schema_version":"1.0","canonical_sha256":"78d5a9c850a61fb8799a9f361e824b4a78deea2e2263d13ba02ce7a185f4e449","source":{"kind":"arxiv","id":"2412.14018","version":3},"attestation_state":"computed","paper":{"title":"SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hongliang Ren, Junyi Wang, Long Bai, Luping Zhou, Shuya Yang, Tong Chen","submitted_at":"2024-12-18T16:34:51Z","abstract_excerpt":"Surgical video generation can enhance medical education and research, but existing methods lack fine-grained motion control and realism. We introduce SurgSora, a framework that generates high-fidelity, motion-controllable surgical videos from a single input frame and user-specified motion cues. Unlike prior approaches that treat objects indiscriminately or rely on ground-truth segmentation masks, SurgSora leverages self-predicted object features and depth information to refine RGB appearance and optical flow for precise video synthesis. It consists of three key modules: (1) the Dual Semantic I"},"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":"2412.14018","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-12-18T16:34:51Z","cross_cats_sorted":["cs.AI","cs.MM","cs.RO"],"title_canon_sha256":"76ea2c2781d590f9e74bb1e8f85c0fb954238aa9f728e0b8c0259362ca6925d0","abstract_canon_sha256":"cc4b29b9688a5a6244b0d12f445fd358ec1de37603a790bbfacfeccb165354fb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:25:06.728698Z","signature_b64":"+qh7dEFPiv6BKE2lsSiyPO0/Ip+SQSdFhEc8gGt2bPXINOhQjeTJGOBczCTccj8QcahPYbaJduX+/yE8p/L9Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78d5a9c850a61fb8799a9f361e824b4a78deea2e2263d13ba02ce7a185f4e449","last_reissued_at":"2026-07-05T11:25:06.728048Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:25:06.728048Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SurgSora: Object-Aware Diffusion Model for Controllable Surgical Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM","cs.RO"],"primary_cat":"cs.CV","authors_text":"Hongliang Ren, Junyi Wang, Long Bai, Luping Zhou, Shuya Yang, Tong Chen","submitted_at":"2024-12-18T16:34:51Z","abstract_excerpt":"Surgical video generation can enhance medical education and research, but existing methods lack fine-grained motion control and realism. We introduce SurgSora, a framework that generates high-fidelity, motion-controllable surgical videos from a single input frame and user-specified motion cues. Unlike prior approaches that treat objects indiscriminately or rely on ground-truth segmentation masks, SurgSora leverages self-predicted object features and depth information to refine RGB appearance and optical flow for precise video synthesis. It consists of three key modules: (1) the Dual Semantic I"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.14018","kind":"arxiv","version":3},"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/2412.14018/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":"2412.14018","created_at":"2026-07-05T11:25:06.728142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.14018v3","created_at":"2026-07-05T11:25:06.728142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.14018","created_at":"2026-07-05T11:25:06.728142+00:00"},{"alias_kind":"pith_short_12","alias_value":"PDK2TSCQUYP3","created_at":"2026-07-05T11:25:06.728142+00:00"},{"alias_kind":"pith_short_16","alias_value":"PDK2TSCQUYP3Q6M2","created_at":"2026-07-05T11:25:06.728142+00:00"},{"alias_kind":"pith_short_8","alias_value":"PDK2TSCQ","created_at":"2026-07-05T11:25:06.728142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.05675","citing_title":"MedGen: Unlocking Medical Video Generation by Scaling Granularly-annotated Medical Videos","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ","json":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ.json","graph_json":"https://pith.science/api/pith-number/PDK2TSCQUYP3Q6M2T43B5ASLJJ/graph.json","events_json":"https://pith.science/api/pith-number/PDK2TSCQUYP3Q6M2T43B5ASLJJ/events.json","paper":"https://pith.science/paper/PDK2TSCQ"},"agent_actions":{"view_html":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ","download_json":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ.json","view_paper":"https://pith.science/paper/PDK2TSCQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.14018&json=true","fetch_graph":"https://pith.science/api/pith-number/PDK2TSCQUYP3Q6M2T43B5ASLJJ/graph.json","fetch_events":"https://pith.science/api/pith-number/PDK2TSCQUYP3Q6M2T43B5ASLJJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ/action/storage_attestation","attest_author":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ/action/author_attestation","sign_citation":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ/action/citation_signature","submit_replication":"https://pith.science/pith/PDK2TSCQUYP3Q6M2T43B5ASLJJ/action/replication_record"}},"created_at":"2026-07-05T11:25:06.728142+00:00","updated_at":"2026-07-05T11:25:06.728142+00:00"}