{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:43XJWIZMTQALRDFTVUWDKTD73L","short_pith_number":"pith:43XJWIZM","canonical_record":{"source":{"id":"2605.13724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:06:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53af612fb312196dd64b2d9c814636fb81cf9acc283cd82a90f27d488622547e","abstract_canon_sha256":"0d17f10040eef6d0c79d044c96895c686b2383ca26c9d6d5a87778a88fc26ad6"},"schema_version":"1.0"},"canonical_sha256":"e6ee9b232c9c00b88cb3ad2c354c7fdaca6807416475361653ff503a956678b1","source":{"kind":"arxiv","id":"2605.13724","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13724","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13724v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13724","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"43XJWIZMTQAL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"43XJWIZMTQALRDFT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"43XJWIZM","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:43XJWIZMTQALRDFTVUWDKTD73L","target":"record","payload":{"canonical_record":{"source":{"id":"2605.13724","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:06:34Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"53af612fb312196dd64b2d9c814636fb81cf9acc283cd82a90f27d488622547e","abstract_canon_sha256":"0d17f10040eef6d0c79d044c96895c686b2383ca26c9d6d5a87778a88fc26ad6"},"schema_version":"1.0"},"canonical_sha256":"e6ee9b232c9c00b88cb3ad2c354c7fdaca6807416475361653ff503a956678b1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:44:16.627340Z","signature_b64":"Rno22ew5pTsf6NxCVi4nKSVGCkH6jcfa9APjj4W3WE4D+JO1MJDANKvUpX1mRMimW66a9t3G0rKtRxkxIfosBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e6ee9b232c9c00b88cb3ad2c354c7fdaca6807416475361653ff503a956678b1","last_reissued_at":"2026-05-18T02:44:16.626721Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:44:16.626721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.13724","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jD3VGckajMpibvdATXVD20vfUE5YG1FWHOhi5rkW5PWtxX66X5VnlWtwDSQqzua5TzdFFYDJF8O4/ytHqaOyBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T00:51:21.263635Z"},"content_sha256":"0f44db1733d9e4e581ed9cfc22a114b8f0b232f4d514bb3a7a95376085661e89","schema_version":"1.0","event_id":"sha256:0f44db1733d9e4e581ed9cfc22a114b8f0b232f4d514bb3a7a95376085661e89"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:43XJWIZMTQALRDFTVUWDKTD73L","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"AnyFlow distills video diffusion models to match few-step consistency performance while preserving scaling as sampling steps increase.","cross_cats":["cs.AI"],"primary_cat":"cs.CV","authors_text":"Guian Fang, Han Cai, Mike Zheng Shou, Song Han, Weijia Mao, Yuchao Gu, Yuxin Jiang","submitted_at":"2026-05-13T16:06:34Z","abstract_excerpt":"Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness for any-step video diffusion. This limitation arises because consistency distillation replaces the original probability-flow ODE trajectory with a consistency-sampling trajectory, weakening the desirable test-time scaling behavior of ODE sampling. To address this limitation, we introduce AnyFlow, the first any-step video diffusion distillation framework based"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime, while scaling with sampling step budgets.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That learning flow-map transitions over arbitrary intervals via backward simulation will avoid introducing new discretization or exposure biases that undermine the original ODE scaling behavior.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"AnyFlow distills video diffusion models to match few-step consistency performance while preserving scaling as sampling steps increase.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"9c75f9b65d69ed1e88dba66e6ec31e331582e53eda41b72928838a7b621cac0d"},"source":{"id":"2605.13724","kind":"arxiv","version":1},"verdict":{"id":"cbad793b-6c2d-4915-875e-7b25da481366","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-14T19:59:06.628346Z","strongest_claim":"AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime, while scaling with sampling step budgets.","one_line_summary":"AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That learning flow-map transitions over arbitrary intervals via backward simulation will avoid introducing new discretization or exposure biases that undermine the original ODE scaling behavior.","pith_extraction_headline":"AnyFlow distills video diffusion models to match few-step consistency performance while preserving scaling as sampling steps increase."},"references":{"count":49,"sample":[{"doi":"","year":2025,"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","ref_index":1,"cited_arxiv_id":"2503.20314","is_internal_anchor":true},{"doi":"","year":2025,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","ref_index":2,"cited_arxiv_id":"2501.03575","is_internal_anchor":true},{"doi":"","year":2024,"title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","work_id":"881efa7e-7e73-4c66-9cc3-2803e551061c","ref_index":3,"cited_arxiv_id":"2412.03603","is_internal_anchor":true},{"doi":"","year":2024,"title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","work_id":"f38fc088-12aa-4bf4-9ecd-08d3e797ccb7","ref_index":4,"cited_arxiv_id":"2408.06072","is_internal_anchor":true},{"doi":"","year":2024,"title":"LTX-Video: Realtime Video Latent Diffusion","work_id":"cee5c521-3ce9-466e-a035-1e42f89254f4","ref_index":5,"cited_arxiv_id":"2501.00103","is_internal_anchor":true}],"resolved_work":49,"snapshot_sha256":"228d63d418e474663924e75d3124beef7bd8dac02899682a6c7f1518c34ca082","internal_anchors":17},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d1c34df08b0fa4b0112fd367b48cc42740575cd8054dda9b99747bd5ba6e4ba1"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"cbad793b-6c2d-4915-875e-7b25da481366"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-18T02:44:16Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"U1V9P5T2tzgswmRR5ZZG0WfN3Cx6hRYIitnl+le2O54qiazEw/UzFFwf+k+4xqQb5Yy/SrbbdyXaYmhmq2EGAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-19T00:51:21.264499Z"},"content_sha256":"1bec743ec176dedb02611df3670c9ad2ce3b78dcf4ebdfe21d1ea196517270fd","schema_version":"1.0","event_id":"sha256:1bec743ec176dedb02611df3670c9ad2ce3b78dcf4ebdfe21d1ea196517270fd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/43XJWIZMTQALRDFTVUWDKTD73L/bundle.json","state_url":"https://pith.science/pith/43XJWIZMTQALRDFTVUWDKTD73L/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/43XJWIZMTQALRDFTVUWDKTD73L/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-05-19T00:51:21Z","links":{"resolver":"https://pith.science/pith/43XJWIZMTQALRDFTVUWDKTD73L","bundle":"https://pith.science/pith/43XJWIZMTQALRDFTVUWDKTD73L/bundle.json","state":"https://pith.science/pith/43XJWIZMTQALRDFTVUWDKTD73L/state.json","well_known_bundle":"https://pith.science/.well-known/pith/43XJWIZMTQALRDFTVUWDKTD73L/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:43XJWIZMTQALRDFTVUWDKTD73L","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0d17f10040eef6d0c79d044c96895c686b2383ca26c9d6d5a87778a88fc26ad6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:06:34Z","title_canon_sha256":"53af612fb312196dd64b2d9c814636fb81cf9acc283cd82a90f27d488622547e"},"schema_version":"1.0","source":{"id":"2605.13724","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.13724","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"arxiv_version","alias_value":"2605.13724v1","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.13724","created_at":"2026-05-18T02:44:16Z"},{"alias_kind":"pith_short_12","alias_value":"43XJWIZMTQAL","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"43XJWIZMTQALRDFT","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"43XJWIZM","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:1bec743ec176dedb02611df3670c9ad2ce3b78dcf4ebdfe21d1ea196517270fd","target":"graph","created_at":"2026-05-18T02:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime, while scaling with sampling step budgets."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That learning flow-map transitions over arbitrary intervals via backward simulation will avoid introducing new discretization or exposure biases that undermine the original ODE scaling behavior."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"AnyFlow distills video diffusion models to match few-step consistency performance while preserving scaling as sampling steps increase."}],"snapshot_sha256":"9c75f9b65d69ed1e88dba66e6ec31e331582e53eda41b72928838a7b621cac0d"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"d1c34df08b0fa4b0112fd367b48cc42740575cd8054dda9b99747bd5ba6e4ba1"},"paper":{"abstract_excerpt":"Few-step video generation has been significantly advanced by consistency distillation. However, the performance of consistency-distilled models often degrades as more sampling steps are allocated at test time, limiting their effectiveness for any-step video diffusion. This limitation arises because consistency distillation replaces the original probability-flow ODE trajectory with a consistency-sampling trajectory, weakening the desirable test-time scaling behavior of ODE sampling. To address this limitation, we introduce AnyFlow, the first any-step video diffusion distillation framework based","authors_text":"Guian Fang, Han Cai, Mike Zheng Shou, Song Han, Weijia Mao, Yuchao Gu, Yuxin Jiang","cross_cats":["cs.AI"],"headline":"AnyFlow distills video diffusion models to match few-step consistency performance while preserving scaling as sampling steps increase.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:06:34Z","title":"AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation"},"references":{"count":49,"internal_anchors":17,"resolved_work":49,"sample":[{"cited_arxiv_id":"2503.20314","doi":"","is_internal_anchor":true,"ref_index":1,"title":"Wan: Open and Advanced Large-Scale Video Generative Models","work_id":"ad3ebc3b-4224-46c9-b61d-bcf135da0a7c","year":2025},{"cited_arxiv_id":"2501.03575","doi":"","is_internal_anchor":true,"ref_index":2,"title":"Cosmos World Foundation Model Platform for Physical AI","work_id":"a2dba24c-318d-476a-8b21-4289c265810c","year":2025},{"cited_arxiv_id":"2412.03603","doi":"","is_internal_anchor":true,"ref_index":3,"title":"HunyuanVideo: A Systematic Framework For Large Video Generative Models","work_id":"881efa7e-7e73-4c66-9cc3-2803e551061c","year":2024},{"cited_arxiv_id":"2408.06072","doi":"","is_internal_anchor":true,"ref_index":4,"title":"CogVideoX: Text-to-Video Diffusion Models with An Expert Transformer","work_id":"f38fc088-12aa-4bf4-9ecd-08d3e797ccb7","year":2024},{"cited_arxiv_id":"2501.00103","doi":"","is_internal_anchor":true,"ref_index":5,"title":"LTX-Video: Realtime Video Latent Diffusion","work_id":"cee5c521-3ce9-466e-a035-1e42f89254f4","year":2024}],"snapshot_sha256":"228d63d418e474663924e75d3124beef7bd8dac02899682a6c7f1518c34ca082"},"source":{"id":"2605.13724","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-14T19:59:06.628346Z","id":"cbad793b-6c2d-4915-875e-7b25da481366","model_set":{"reader":"grok-4.3"},"one_line_summary":"AnyFlow enables any-step video diffusion by distilling flow-map transitions over arbitrary time intervals with on-policy backward simulation.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"AnyFlow distills video diffusion models to match few-step consistency performance while preserving scaling as sampling steps increase.","strongest_claim":"AnyFlow achieves performance matches or surpasses consistency-based counterparts in the few-step regime, while scaling with sampling step budgets.","weakest_assumption":"That learning flow-map transitions over arbitrary intervals via backward simulation will avoid introducing new discretization or exposure biases that undermine the original ODE scaling behavior."}},"verdict_id":"cbad793b-6c2d-4915-875e-7b25da481366"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:0f44db1733d9e4e581ed9cfc22a114b8f0b232f4d514bb3a7a95376085661e89","target":"record","created_at":"2026-05-18T02:44:16Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0d17f10040eef6d0c79d044c96895c686b2383ca26c9d6d5a87778a88fc26ad6","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CV","submitted_at":"2026-05-13T16:06:34Z","title_canon_sha256":"53af612fb312196dd64b2d9c814636fb81cf9acc283cd82a90f27d488622547e"},"schema_version":"1.0","source":{"id":"2605.13724","kind":"arxiv","version":1}},"canonical_sha256":"e6ee9b232c9c00b88cb3ad2c354c7fdaca6807416475361653ff503a956678b1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e6ee9b232c9c00b88cb3ad2c354c7fdaca6807416475361653ff503a956678b1","first_computed_at":"2026-05-18T02:44:16.626721Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T02:44:16.626721Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Rno22ew5pTsf6NxCVi4nKSVGCkH6jcfa9APjj4W3WE4D+JO1MJDANKvUpX1mRMimW66a9t3G0rKtRxkxIfosBw==","signature_status":"signed_v1","signed_at":"2026-05-18T02:44:16.627340Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.13724","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0f44db1733d9e4e581ed9cfc22a114b8f0b232f4d514bb3a7a95376085661e89","sha256:1bec743ec176dedb02611df3670c9ad2ce3b78dcf4ebdfe21d1ea196517270fd"],"state_sha256":"f2c6f27e7c8544ffcb36dc9fdb25f5505718ceba8e519d33c5ab0b59993b42dd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y5/2KFujSUWa2BrO7yZtQn61lpiF2X9RtkeyM6yloWjgvO7BPQBAm1kNX3q1fZnItdoKX9yzA50SQ3NkcSN/Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-19T00:51:21.266949Z","bundle_sha256":"3ff12816730da64a1451e0b30c37e2460d64a14100cd6a72740b6502b170f981"}}