{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:2DCJOS4E66MBYHYEPWAV2O6VNM","short_pith_number":"pith:2DCJOS4E","schema_version":"1.0","canonical_sha256":"d0c4974b84f7981c1f047d815d3bd56b013f697c493c326f816bf2840cf2c1d2","source":{"kind":"arxiv","id":"2407.02398","version":1},"attestation_state":"computed","paper":{"title":"Consistency Flow Matching: Defining Straight Flows with Velocity Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Cui, Chenlin Meng, Ling Yang, Minkai Xu, Stefano Ermon, Wentao Zhang, Xingchao Liu, Zhilong Zhang, Zixiang Zhang","submitted_at":"2024-07-02T16:15:37Z","abstract_excerpt":"Flow matching (FM) is a general framework for defining probability paths via Ordinary Differential Equations (ODEs) to transform between noise and data samples. Recent approaches attempt to straighten these flow trajectories to generate high-quality samples with fewer function evaluations, typically through iterative rectification methods or optimal transport solutions. In this paper, we introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Consistency-FM directly defines straight flows starting from different t"},"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":"2407.02398","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-07-02T16:15:37Z","cross_cats_sorted":[],"title_canon_sha256":"1e609db105eeb43925480416541eef63bfdfbfec535b7e0661cadb715d129c50","abstract_canon_sha256":"1ebe6c6d412264f5408e724aa358f17fe918c74e852d0c5082a8bccd358b45ca"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:39:23.508953Z","signature_b64":"zOrGEWASfrc2GLMowKpJtdDqxX3lr7poaCqs9QItHWSuX7B0swKxNwsJjcbA3kIT2j35z2nXDdBR8L0Pf5nHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d0c4974b84f7981c1f047d815d3bd56b013f697c493c326f816bf2840cf2c1d2","last_reissued_at":"2026-07-05T08:39:23.508480Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:39:23.508480Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Consistency Flow Matching: Defining Straight Flows with Velocity Consistency","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Bin Cui, Chenlin Meng, Ling Yang, Minkai Xu, Stefano Ermon, Wentao Zhang, Xingchao Liu, Zhilong Zhang, Zixiang Zhang","submitted_at":"2024-07-02T16:15:37Z","abstract_excerpt":"Flow matching (FM) is a general framework for defining probability paths via Ordinary Differential Equations (ODEs) to transform between noise and data samples. Recent approaches attempt to straighten these flow trajectories to generate high-quality samples with fewer function evaluations, typically through iterative rectification methods or optimal transport solutions. In this paper, we introduce Consistency Flow Matching (Consistency-FM), a novel FM method that explicitly enforces self-consistency in the velocity field. Consistency-FM directly defines straight flows starting from different t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.02398","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/2407.02398/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":"2407.02398","created_at":"2026-07-05T08:39:23.508539+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.02398v1","created_at":"2026-07-05T08:39:23.508539+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.02398","created_at":"2026-07-05T08:39:23.508539+00:00"},{"alias_kind":"pith_short_12","alias_value":"2DCJOS4E66MB","created_at":"2026-07-05T08:39:23.508539+00:00"},{"alias_kind":"pith_short_16","alias_value":"2DCJOS4E66MBYHYE","created_at":"2026-07-05T08:39:23.508539+00:00"},{"alias_kind":"pith_short_8","alias_value":"2DCJOS4E","created_at":"2026-07-05T08:39:23.508539+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":23,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.06262","citing_title":"Optimal Transport Q-Learning for Flow Policy Steering and Acceleration","ref_index":38,"is_internal_anchor":true},{"citing_arxiv_id":"2606.04092","citing_title":"Optimal Transport Flow Matching by Design","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12377","citing_title":"Fast Image Super-Resolution via Consistency Rectified Flow","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23087","citing_title":"CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15944","citing_title":"FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15944","citing_title":"FocalPolicy: Frequency-Optimized Chunking and Locally Anchored Flow Matching for Coherent Visuomotor Policy","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23087","citing_title":"CoLA-Flow Policy: Temporally Coherent Imitation Learning via Continuous Latent Action Flow Matching for Robotic Manipulation","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2603.03648","citing_title":"Linearized Coupling Flow with Shortcut Constraints for One-Step Face Restoration","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12939","citing_title":"DirectTryOn: One-Step Virtual Try-On via Straightened Conditional Transport","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12377","citing_title":"Fast Image Super-Resolution via Consistency Rectified Flow","ref_index":56,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08511","citing_title":"Trajectory-Consistent Flow Matching for Robust Visuomotor Policy Learning","ref_index":18,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2604.26065","citing_title":"FlowS: One-Step Motion Prediction via Local Transport Conditioning","ref_index":24,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05975","citing_title":"Physical Fidelity Reconstruction via Improved Consistency-Distilled Flow Matching for Dynamical Systems","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13447","citing_title":"Mean Flows for One-step Generative Modeling","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19238","citing_title":"Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2605.01581","citing_title":"Hyper-DP3: Frequency-Aware Right-Sizing of 3D Diffusion Policies for Visuomotor Control","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04491","citing_title":"Isokinetic Flow Matching for Pathwise Straightening of Generative Flows","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09181","citing_title":"MixFlow: Mixed Source Distributions Improve Rectified Flows","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15009","citing_title":"Towards Faster Language Model Inference Using Mixture-of-Experts Flow Matching","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18168","citing_title":"Extending One-Step Image Generation from Class Labels to Text via Discriminative Text Representation","ref_index":53,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM","json":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM.json","graph_json":"https://pith.science/api/pith-number/2DCJOS4E66MBYHYEPWAV2O6VNM/graph.json","events_json":"https://pith.science/api/pith-number/2DCJOS4E66MBYHYEPWAV2O6VNM/events.json","paper":"https://pith.science/paper/2DCJOS4E"},"agent_actions":{"view_html":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM","download_json":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM.json","view_paper":"https://pith.science/paper/2DCJOS4E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.02398&json=true","fetch_graph":"https://pith.science/api/pith-number/2DCJOS4E66MBYHYEPWAV2O6VNM/graph.json","fetch_events":"https://pith.science/api/pith-number/2DCJOS4E66MBYHYEPWAV2O6VNM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM/action/storage_attestation","attest_author":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM/action/author_attestation","sign_citation":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM/action/citation_signature","submit_replication":"https://pith.science/pith/2DCJOS4E66MBYHYEPWAV2O6VNM/action/replication_record"}},"created_at":"2026-07-05T08:39:23.508539+00:00","updated_at":"2026-07-05T08:39:23.508539+00:00"}