{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:Y24PC3DR3TWAWC2NPEAJEP6PVF","short_pith_number":"pith:Y24PC3DR","schema_version":"1.0","canonical_sha256":"c6b8f16c71dcec0b0b4d7900923fcfa95bea357f35c049dcd185874bbd659df2","source":{"kind":"arxiv","id":"2303.17959","version":2},"attestation_state":"computed","paper":{"title":"Diffusion Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"AnhDung Dinh, Chang Xu, Daochang Liu, Mubarak Shah, Qiyue Li, Tingting Jiang","submitted_at":"2023-03-31T10:53:24Z","abstract_excerpt":"Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion models, which nonetheless shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions. To enhance the modeling of three striking characteristics of human actions, including the position prior, the boundary ambiguity, and the relational depend"},"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":"2303.17959","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-03-31T10:53:24Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"39a547af9b647b26948d5876d67b5f276a253d42ff509c677ae3e4498ce9fa3a","abstract_canon_sha256":"beb01e0f226b11a1d472f8a153a12d152d22f39166815c5c85b752f12272ad2a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:40:33.007492Z","signature_b64":"9UchVrjN9dZUbug+Ho7ciZiJNHiyAWfgZ9IhQ5btswHw46CGDXXSlc8eKHQnMAgL0BmQ0roWkcFLC0qcZzX8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6b8f16c71dcec0b0b4d7900923fcfa95bea357f35c049dcd185874bbd659df2","last_reissued_at":"2026-07-05T06:40:33.006980Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:40:33.006980Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Action Segmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"AnhDung Dinh, Chang Xu, Daochang Liu, Mubarak Shah, Qiyue Li, Tingting Jiang","submitted_at":"2023-03-31T10:53:24Z","abstract_excerpt":"Temporal action segmentation is crucial for understanding long-form videos. Previous works on this task commonly adopt an iterative refinement paradigm by using multi-stage models. We propose a novel framework via denoising diffusion models, which nonetheless shares the same inherent spirit of such iterative refinement. In this framework, action predictions are iteratively generated from random noise with input video features as conditions. To enhance the modeling of three striking characteristics of human actions, including the position prior, the boundary ambiguity, and the relational depend"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.17959","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/2303.17959/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":"2303.17959","created_at":"2026-07-05T06:40:33.007049+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.17959v2","created_at":"2026-07-05T06:40:33.007049+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.17959","created_at":"2026-07-05T06:40:33.007049+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y24PC3DR3TWA","created_at":"2026-07-05T06:40:33.007049+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y24PC3DR3TWAWC2N","created_at":"2026-07-05T06:40:33.007049+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y24PC3DR","created_at":"2026-07-05T06:40:33.007049+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/Y24PC3DR3TWAWC2NPEAJEP6PVF","json":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF.json","graph_json":"https://pith.science/api/pith-number/Y24PC3DR3TWAWC2NPEAJEP6PVF/graph.json","events_json":"https://pith.science/api/pith-number/Y24PC3DR3TWAWC2NPEAJEP6PVF/events.json","paper":"https://pith.science/paper/Y24PC3DR"},"agent_actions":{"view_html":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF","download_json":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF.json","view_paper":"https://pith.science/paper/Y24PC3DR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.17959&json=true","fetch_graph":"https://pith.science/api/pith-number/Y24PC3DR3TWAWC2NPEAJEP6PVF/graph.json","fetch_events":"https://pith.science/api/pith-number/Y24PC3DR3TWAWC2NPEAJEP6PVF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF/action/storage_attestation","attest_author":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF/action/author_attestation","sign_citation":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF/action/citation_signature","submit_replication":"https://pith.science/pith/Y24PC3DR3TWAWC2NPEAJEP6PVF/action/replication_record"}},"created_at":"2026-07-05T06:40:33.007049+00:00","updated_at":"2026-07-05T06:40:33.007049+00:00"}