{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:57QXAFTSRGQ3CLECTFUXCRJJJI","short_pith_number":"pith:57QXAFTS","schema_version":"1.0","canonical_sha256":"efe170167289a1b12c8299697145294a14d708204e5e8e85bcc7fa2af091b96d","source":{"kind":"arxiv","id":"2410.03160","version":1},"attestation_state":"computed","paper":{"title":"Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aitor Artola, Jean-Michel Morel, Raymond H. Chan, Tieyong Zeng, Xiaodong Cun, Yang Liu, Yaofang Liu, Yumeng Ren","submitted_at":"2024-10-04T05:47:39Z","abstract_excerpt":"Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits their ability to model complex temporal dependencies needed for various tasks like image-to-video generation. To address this limitation, we propose a frame-aware video diffusion model~(FVDM), which introduces a novel vectorized timestep variable~(VTV). Unlike conventional VDMs, our approach allows each frame to follow an independent noise schedule, enhancing th"},"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":"2410.03160","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-04T05:47:39Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cb976a2ab0f15f5ae2962380eaac9b8fb26eaacbda0c84930ed10ea6a2cdb596","abstract_canon_sha256":"28716f5859f37f6faaa4feb4fe6900589549813debb3972cff682300c13cec63"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:15:45.469744Z","signature_b64":"HUDuTGM8gNsiay8GFmsJh4lFt6/ES4fcbeyMMNkbjYJwFIUOqm/dp7HJ1DCj/EbNjloxqan6naP12UIbKNjLCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efe170167289a1b12c8299697145294a14d708204e5e8e85bcc7fa2af091b96d","last_reissued_at":"2026-07-05T09:15:45.469258Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:15:45.469258Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Redefining Temporal Modeling in Video Diffusion: The Vectorized Timestep Approach","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Aitor Artola, Jean-Michel Morel, Raymond H. Chan, Tieyong Zeng, Xiaodong Cun, Yang Liu, Yaofang Liu, Yumeng Ren","submitted_at":"2024-10-04T05:47:39Z","abstract_excerpt":"Diffusion models have revolutionized image generation, and their extension to video generation has shown promise. However, current video diffusion models~(VDMs) rely on a scalar timestep variable applied at the clip level, which limits their ability to model complex temporal dependencies needed for various tasks like image-to-video generation. To address this limitation, we propose a frame-aware video diffusion model~(FVDM), which introduces a novel vectorized timestep variable~(VTV). Unlike conventional VDMs, our approach allows each frame to follow an independent noise schedule, enhancing th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.03160","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/2410.03160/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":"2410.03160","created_at":"2026-07-05T09:15:45.469321+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.03160v1","created_at":"2026-07-05T09:15:45.469321+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.03160","created_at":"2026-07-05T09:15:45.469321+00:00"},{"alias_kind":"pith_short_12","alias_value":"57QXAFTSRGQ3","created_at":"2026-07-05T09:15:45.469321+00:00"},{"alias_kind":"pith_short_16","alias_value":"57QXAFTSRGQ3CLEC","created_at":"2026-07-05T09:15:45.469321+00:00"},{"alias_kind":"pith_short_8","alias_value":"57QXAFTS","created_at":"2026-07-05T09:15:45.469321+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.12271","citing_title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09721","citing_title":"FrameDiT: Diffusion Transformer with Matrix Attention for Efficient Video Generation","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12271","citing_title":"Beyond Text Prompts: Visual-to-Visual Generation as A Unified Paradigm","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2506.08009","citing_title":"Self Forcing: Bridging the Train-Test Gap in Autoregressive Video Diffusion","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.07209","citing_title":"INSPATIO-WORLD: A Real-Time 4D World Simulator via Spatiotemporal Autoregressive Modeling","ref_index":56,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI","json":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI.json","graph_json":"https://pith.science/api/pith-number/57QXAFTSRGQ3CLECTFUXCRJJJI/graph.json","events_json":"https://pith.science/api/pith-number/57QXAFTSRGQ3CLECTFUXCRJJJI/events.json","paper":"https://pith.science/paper/57QXAFTS"},"agent_actions":{"view_html":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI","download_json":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI.json","view_paper":"https://pith.science/paper/57QXAFTS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.03160&json=true","fetch_graph":"https://pith.science/api/pith-number/57QXAFTSRGQ3CLECTFUXCRJJJI/graph.json","fetch_events":"https://pith.science/api/pith-number/57QXAFTSRGQ3CLECTFUXCRJJJI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI/action/storage_attestation","attest_author":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI/action/author_attestation","sign_citation":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI/action/citation_signature","submit_replication":"https://pith.science/pith/57QXAFTSRGQ3CLECTFUXCRJJJI/action/replication_record"}},"created_at":"2026-07-05T09:15:45.469321+00:00","updated_at":"2026-07-05T09:15:45.469321+00:00"}