{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RXETR5JAR45FORANX4V7DEJX5R","short_pith_number":"pith:RXETR5JA","schema_version":"1.0","canonical_sha256":"8dc938f5208f3a57440dbf2bf19137ec4f2cfda1752225019543cdf5673727bc","source":{"kind":"arxiv","id":"2601.09881","version":2},"attestation_state":"computed","paper":{"title":"Transition Matching Distillation for Fast Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arash Vahdat, Chao Liu, Julius Berner, Nanye Ma, Saining Xie, Weili Nie","submitted_at":"2026-01-14T21:30:03Z","abstract_excerpt":"Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work, we present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators. The central idea of TMD is to match the multi-step denoising trajectory of a diffusion model with a few-step probability transition process, where each transition is modeled as a lightweight conditional flow. To enab"},"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":"2601.09881","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-01-14T21:30:03Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"33830d837c7414e61be8f7133aa681d01c34a930c3bac2c2b318b90137013dd9","abstract_canon_sha256":"484ea70c04495fb6e648bd91fe513491e76c3da625506c9728cdd39ac009fce9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-13T00:17:06.352361Z","signature_b64":"Y/wTreeaKGokshT9Zvmo5EqgzMG9tifJr2vrB16N8YsCOTglU216zPmkv8VEQh09wNqV/AwV7S7aItEOT4LBCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8dc938f5208f3a57440dbf2bf19137ec4f2cfda1752225019543cdf5673727bc","last_reissued_at":"2026-07-13T00:17:06.350827Z","signature_status":"signed_v1","first_computed_at":"2026-07-13T00:17:06.350827Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transition Matching Distillation for Fast Video Generation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Arash Vahdat, Chao Liu, Julius Berner, Nanye Ma, Saining Xie, Weili Nie","submitted_at":"2026-01-14T21:30:03Z","abstract_excerpt":"Large video diffusion and flow models have achieved remarkable success in high-quality video generation, but their use in real-time interactive applications remains limited due to their inefficient multi-step sampling process. In this work, we present Transition Matching Distillation (TMD), a novel framework for distilling video diffusion models into efficient few-step generators. The central idea of TMD is to match the multi-step denoising trajectory of a diffusion model with a few-step probability transition process, where each transition is modeled as a lightweight conditional flow. To enab"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.09881","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/2601.09881/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":"2601.09881","created_at":"2026-07-13T00:17:06.351621+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.09881v2","created_at":"2026-07-13T00:17:06.351621+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.09881","created_at":"2026-07-13T00:17:06.351621+00:00"},{"alias_kind":"pith_short_12","alias_value":"RXETR5JAR45F","created_at":"2026-07-13T00:17:06.351621+00:00"},{"alias_kind":"pith_short_16","alias_value":"RXETR5JAR45FORAN","created_at":"2026-07-13T00:17:06.351621+00:00"},{"alias_kind":"pith_short_8","alias_value":"RXETR5JA","created_at":"2026-07-13T00:17:06.351621+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":12,"internal_anchor_count":12,"sample":[{"citing_arxiv_id":"2607.06631","citing_title":"Dynamic-in-Few-Step: Unifying Dynamic Computation and Few-Step Distillation for Efficient Video Generation","ref_index":24,"is_internal_anchor":true},{"citing_arxiv_id":"2606.25473","citing_title":"Causal-rCM: A Unified Teacher-Forcing and Self-Forcing Open Recipe for Autoregressive Diffusion Distillation in Streaming Video Generation and Interactive World Models","ref_index":46,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":280,"is_internal_anchor":true},{"citing_arxiv_id":"2606.18478","citing_title":"Data-Forcing Distillation: Restoring Diversity and Fidelity in Few-Step Video Generation","ref_index":33,"is_internal_anchor":true},{"citing_arxiv_id":"2605.25659","citing_title":"StreamChar: Long-Horizon Streaming Character Audio-Video Generation with Decoupled Orchestration","ref_index":25,"is_internal_anchor":true},{"citing_arxiv_id":"2605.16515","citing_title":"SeamCam: Quantifying Seamless Camouflage via Multi-Cue Visual Detectability","ref_index":39,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13724","citing_title":"AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation","ref_index":27,"is_internal_anchor":true},{"citing_arxiv_id":"2604.03118","citing_title":"Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation","ref_index":30,"is_internal_anchor":true},{"citing_arxiv_id":"2604.28185","citing_title":"Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling","ref_index":56,"is_internal_anchor":true},{"citing_arxiv_id":"2604.22748","citing_title":"Agentic World Modeling: Foundations, Capabilities, Laws, and Beyond","ref_index":280,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06376","citing_title":"Continuous-Time Distribution Matching for Few-Step Diffusion Distillation","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2605.07661","citing_title":"Stochastic Transition-Map Distillation for Fast Probabilistic Inference","ref_index":192,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R","json":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R.json","graph_json":"https://pith.science/api/pith-number/RXETR5JAR45FORANX4V7DEJX5R/graph.json","events_json":"https://pith.science/api/pith-number/RXETR5JAR45FORANX4V7DEJX5R/events.json","paper":"https://pith.science/paper/RXETR5JA"},"agent_actions":{"view_html":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R","download_json":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R.json","view_paper":"https://pith.science/paper/RXETR5JA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.09881&json=true","fetch_graph":"https://pith.science/api/pith-number/RXETR5JAR45FORANX4V7DEJX5R/graph.json","fetch_events":"https://pith.science/api/pith-number/RXETR5JAR45FORANX4V7DEJX5R/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R/action/storage_attestation","attest_author":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R/action/author_attestation","sign_citation":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R/action/citation_signature","submit_replication":"https://pith.science/pith/RXETR5JAR45FORANX4V7DEJX5R/action/replication_record"}},"created_at":"2026-07-13T00:17:06.351621+00:00","updated_at":"2026-07-13T00:17:06.351621+00:00"}