{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:B5LNTNLROVOMW7ZVB5HP6G6L2M","short_pith_number":"pith:B5LNTNLR","schema_version":"1.0","canonical_sha256":"0f56d9b571755ccb7f350f4eff1bcbd31a0eaf7a9cdf9cc0108175e1c4187e2a","source":{"kind":"arxiv","id":"2408.14028","version":3},"attestation_state":"computed","paper":{"title":"SurGen: Text-Guided Diffusion Model for Surgical Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cyril Zakka, Dhamanpreet Kaur, Joseph Cho, Mrudang Mathur, Rohan Shad, Samuel Schmidgall, William Hiesinger","submitted_at":"2024-08-26T05:38:27Z","abstract_excerpt":"Diffusion-based video generation models have made significant strides, producing outputs with improved visual fidelity, temporal coherence, and user control. These advancements hold great promise for improving surgical education by enabling more realistic, diverse, and interactive simulation environments. In this study, we introduce SurGen, a text-guided diffusion model tailored for surgical video synthesis. SurGen produces videos with the highest resolution and longest duration among existing surgical video generation models. We validate the visual and temporal quality of the outputs using st"},"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":"2408.14028","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2024-08-26T05:38:27Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"cc90c4944d8ec2990f1504b0c42f70827c2afe0da5d34aedc13ee23165e9573c","abstract_canon_sha256":"ccd2b6c98291fe0d7fd533deb4b21ea4dc77eb28abcc936b3cf4fcc5400b1560"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:11:28.975617Z","signature_b64":"5cmrGYB0Cxer5elppbxqo06gncgwnR+l3fIeBmMOB9Lu2eelpyCxl/dCEpbT6UDgTtXU2PwHyeywwo+1vm04Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f56d9b571755ccb7f350f4eff1bcbd31a0eaf7a9cdf9cc0108175e1c4187e2a","last_reissued_at":"2026-07-05T09:11:28.975123Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:11:28.975123Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SurGen: Text-Guided Diffusion Model for Surgical Video Generation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CV","authors_text":"Cyril Zakka, Dhamanpreet Kaur, Joseph Cho, Mrudang Mathur, Rohan Shad, Samuel Schmidgall, William Hiesinger","submitted_at":"2024-08-26T05:38:27Z","abstract_excerpt":"Diffusion-based video generation models have made significant strides, producing outputs with improved visual fidelity, temporal coherence, and user control. These advancements hold great promise for improving surgical education by enabling more realistic, diverse, and interactive simulation environments. In this study, we introduce SurGen, a text-guided diffusion model tailored for surgical video synthesis. SurGen produces videos with the highest resolution and longest duration among existing surgical video generation models. We validate the visual and temporal quality of the outputs using st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.14028","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/2408.14028/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":"2408.14028","created_at":"2026-07-05T09:11:28.975181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2408.14028v3","created_at":"2026-07-05T09:11:28.975181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.14028","created_at":"2026-07-05T09:11:28.975181+00:00"},{"alias_kind":"pith_short_12","alias_value":"B5LNTNLROVOM","created_at":"2026-07-05T09:11:28.975181+00:00"},{"alias_kind":"pith_short_16","alias_value":"B5LNTNLROVOMW7ZV","created_at":"2026-07-05T09:11:28.975181+00:00"},{"alias_kind":"pith_short_8","alias_value":"B5LNTNLR","created_at":"2026-07-05T09:11:28.975181+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":14,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M","json":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M.json","graph_json":"https://pith.science/api/pith-number/B5LNTNLROVOMW7ZVB5HP6G6L2M/graph.json","events_json":"https://pith.science/api/pith-number/B5LNTNLROVOMW7ZVB5HP6G6L2M/events.json","paper":"https://pith.science/paper/B5LNTNLR"},"agent_actions":{"view_html":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M","download_json":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M.json","view_paper":"https://pith.science/paper/B5LNTNLR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2408.14028&json=true","fetch_graph":"https://pith.science/api/pith-number/B5LNTNLROVOMW7ZVB5HP6G6L2M/graph.json","fetch_events":"https://pith.science/api/pith-number/B5LNTNLROVOMW7ZVB5HP6G6L2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M/action/storage_attestation","attest_author":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M/action/author_attestation","sign_citation":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M/action/citation_signature","submit_replication":"https://pith.science/pith/B5LNTNLROVOMW7ZVB5HP6G6L2M/action/replication_record"}},"created_at":"2026-07-05T09:11:28.975181+00:00","updated_at":"2026-07-05T09:11:28.975181+00:00"}