{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:WUBHRAAVTDXBNY66BZ27GYDOIC","short_pith_number":"pith:WUBHRAAV","schema_version":"1.0","canonical_sha256":"b50278801598ee16e3de0e75f3606e40b1acd209f51027b3a536056efd65add6","source":{"kind":"arxiv","id":"2509.03794","version":1},"attestation_state":"computed","paper":{"title":"Fitting Image Diffusion Models on Video Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juhun Lee, Simon S. Woo","submitted_at":"2025-09-04T01:04:54Z","abstract_excerpt":"Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design. This limitation leads to slower convergence, limited distributional coverage, and reduced generalization. In this work, we propose a simple and effective training strategy that leverages the temporal inductive bias present in continuous video frames to improve diffusion training. Notably, the proposed method requires no architectural modification and can be"},"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":"2509.03794","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-09-04T01:04:54Z","cross_cats_sorted":[],"title_canon_sha256":"b92a6be57755915f78b0cfc67be3fd20f1661cabde1a4f0b676fd34000cacc01","abstract_canon_sha256":"574b04471ff635e1ad897c292ee4dd3579adbb0a80dd6d18d26a28aa87bfd8fa"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:04:46.181937Z","signature_b64":"LSVNDH57d3IJ+fcz+eePN9mYcnXrfGRUHSAeL4KL995GNCK1/b0Vyt3vjYX4QwOwyIv1JcasbOyiIjZa99uGAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b50278801598ee16e3de0e75f3606e40b1acd209f51027b3a536056efd65add6","last_reissued_at":"2026-07-05T12:04:46.181465Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:04:46.181465Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fitting Image Diffusion Models on Video Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Juhun Lee, Simon S. Woo","submitted_at":"2025-09-04T01:04:54Z","abstract_excerpt":"Image diffusion models are trained on independently sampled static images. While this is the bedrock task protocol in generative modeling, capturing the temporal world through the lens of static snapshots is information-deficient by design. This limitation leads to slower convergence, limited distributional coverage, and reduced generalization. In this work, we propose a simple and effective training strategy that leverages the temporal inductive bias present in continuous video frames to improve diffusion training. Notably, the proposed method requires no architectural modification and can be"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.03794","kind":"arxiv","version":1},"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/2509.03794/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":"2509.03794","created_at":"2026-07-05T12:04:46.181523+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.03794v1","created_at":"2026-07-05T12:04:46.181523+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.03794","created_at":"2026-07-05T12:04:46.181523+00:00"},{"alias_kind":"pith_short_12","alias_value":"WUBHRAAVTDXB","created_at":"2026-07-05T12:04:46.181523+00:00"},{"alias_kind":"pith_short_16","alias_value":"WUBHRAAVTDXBNY66","created_at":"2026-07-05T12:04:46.181523+00:00"},{"alias_kind":"pith_short_8","alias_value":"WUBHRAAV","created_at":"2026-07-05T12:04:46.181523+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/WUBHRAAVTDXBNY66BZ27GYDOIC","json":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC.json","graph_json":"https://pith.science/api/pith-number/WUBHRAAVTDXBNY66BZ27GYDOIC/graph.json","events_json":"https://pith.science/api/pith-number/WUBHRAAVTDXBNY66BZ27GYDOIC/events.json","paper":"https://pith.science/paper/WUBHRAAV"},"agent_actions":{"view_html":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC","download_json":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC.json","view_paper":"https://pith.science/paper/WUBHRAAV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.03794&json=true","fetch_graph":"https://pith.science/api/pith-number/WUBHRAAVTDXBNY66BZ27GYDOIC/graph.json","fetch_events":"https://pith.science/api/pith-number/WUBHRAAVTDXBNY66BZ27GYDOIC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC/action/storage_attestation","attest_author":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC/action/author_attestation","sign_citation":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC/action/citation_signature","submit_replication":"https://pith.science/pith/WUBHRAAVTDXBNY66BZ27GYDOIC/action/replication_record"}},"created_at":"2026-07-05T12:04:46.181523+00:00","updated_at":"2026-07-05T12:04:46.181523+00:00"}