{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:CLNFID3BS6Z4IUJ5SPWC5LHL43","short_pith_number":"pith:CLNFID3B","schema_version":"1.0","canonical_sha256":"12da540f6197b3c4513d93ec2eacebe6d96a387c0ca2de9096caf9a7da082eee","source":{"kind":"arxiv","id":"2406.07507","version":2},"attestation_state":"computed","paper":{"title":"Flow map matching with stochastic interpolants: A mathematical framework for consistency models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS"],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Michael S. Albergo, Nicholas M. Boffi","submitted_at":"2024-06-11T17:41:26Z","abstract_excerpt":"Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inference. The advent of consistency models has enabled efficient one-step or few-step generation, yet despite their practical success, a systematic understanding of their design has been hindered by the lack of a comprehensive theoretical framework. Here we introduce Flow Map Matching (FMM), a principled framework for learning the two-time flow map of an underlying dynamical generative model, thereby providing this mis"},"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":"2406.07507","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-11T17:41:26Z","cross_cats_sorted":["math.DS"],"title_canon_sha256":"af5d93b72598e62b72782046c0fdcd0fdf4c61d261345cf8294f0284402f5b47","abstract_canon_sha256":"9e8a1e2ff4236f35e55388d45e8c9992da9a287e79b736ddccd849547f071190"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:14:23.870173Z","signature_b64":"At3no8hRV8hcZ4/COuCSzmDbW1oHQ4343sE/G2DZufLpDXAQG+z+ZOW0dEb21fdeS8JiTY3UI9HFT0md46utAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12da540f6197b3c4513d93ec2eacebe6d96a387c0ca2de9096caf9a7da082eee","last_reissued_at":"2026-07-05T11:14:23.869744Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:14:23.869744Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow map matching with stochastic interpolants: A mathematical framework for consistency models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["math.DS"],"primary_cat":"cs.LG","authors_text":"Eric Vanden-Eijnden, Michael S. Albergo, Nicholas M. Boffi","submitted_at":"2024-06-11T17:41:26Z","abstract_excerpt":"Generative models based on dynamical equations such as flows and diffusions offer exceptional sample quality, but require computationally expensive numerical integration during inference. The advent of consistency models has enabled efficient one-step or few-step generation, yet despite their practical success, a systematic understanding of their design has been hindered by the lack of a comprehensive theoretical framework. Here we introduce Flow Map Matching (FMM), a principled framework for learning the two-time flow map of an underlying dynamical generative model, thereby providing this mis"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.07507","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/2406.07507/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":"2406.07507","created_at":"2026-07-05T11:14:23.869799+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.07507v2","created_at":"2026-07-05T11:14:23.869799+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.07507","created_at":"2026-07-05T11:14:23.869799+00:00"},{"alias_kind":"pith_short_12","alias_value":"CLNFID3BS6Z4","created_at":"2026-07-05T11:14:23.869799+00:00"},{"alias_kind":"pith_short_16","alias_value":"CLNFID3BS6Z4IUJ5","created_at":"2026-07-05T11:14:23.869799+00:00"},{"alias_kind":"pith_short_8","alias_value":"CLNFID3B","created_at":"2026-07-05T11:14:23.869799+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":25,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.24773","citing_title":"Posterior Refinement: Fast Language Generation via Any-Order Flow Maps","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10613","citing_title":"Fast and Highly Expressive Policy Learning for Offline Reinforcement Learning via Bootstrapped Flow Q-Learning","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2606.08417","citing_title":"Hacking Generative Perplexity: Why Unconditional Text Evaluation Needs Distributional Metrics","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01086","citing_title":"Strong Stochastic Flow Maps","ref_index":20,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2606.29150","citing_title":"Flow Reasoning Models: Scaling Reasoning Through Iterative Self-Refinement","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30414","citing_title":"Diffusion Fine-tuning with Rewarded Moment Matching Distillation","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28075","citing_title":"Measure-to-measure Regression with Transformers","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16813","citing_title":"Flow Map Language Models: One-step Language Modeling via Continuous Denoising","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2603.07514","citing_title":"A Unified View of Score-Based and Drifting Models","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10759","citing_title":"Reinforce Adjoint Matching: Scaling RL Post-Training of Diffusion and Flow-Matching Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21890","citing_title":"The Principles of Diffusion Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2602.10764","citing_title":"Dual-End Consistency Model","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2602.16813","citing_title":"Flow Map Language Models: One-step Language Modeling via Continuous Denoising","ref_index":19,"is_internal_anchor":false},{"citing_arxiv_id":"2410.12557","citing_title":"One Step Diffusion via Shortcut Models","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13724","citing_title":"AnyFlow: Any-Step Video Diffusion Model with On-Policy Flow Map Distillation","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.03118","citing_title":"Salt: Self-Consistent Distribution Matching with Cache-Aware Training for Fast Video Generation","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12183","citing_title":"DriftXpress: Faster Drifting Models via Projected RKHS Fields","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2604.27147","citing_title":"How to Guide Your Flow: Few-Step Alignment via Flow Map Reward Guidance","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2505.13447","citing_title":"Mean Flows for One-step Generative Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04491","citing_title":"Isokinetic Flow Matching for Pathwise Straightening of Generative Flows","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2604.06413","citing_title":"ODE-free Neural Flow Matching for One-Step Generative Modeling","ref_index":3,"is_internal_anchor":false},{"citing_arxiv_id":"2604.15470","citing_title":"Perron-Frobenius Contractive Operator Matching for Data-Driven Reachable Fault Identification and Recovery","ref_index":24,"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":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43","json":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43.json","graph_json":"https://pith.science/api/pith-number/CLNFID3BS6Z4IUJ5SPWC5LHL43/graph.json","events_json":"https://pith.science/api/pith-number/CLNFID3BS6Z4IUJ5SPWC5LHL43/events.json","paper":"https://pith.science/paper/CLNFID3B"},"agent_actions":{"view_html":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43","download_json":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43.json","view_paper":"https://pith.science/paper/CLNFID3B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.07507&json=true","fetch_graph":"https://pith.science/api/pith-number/CLNFID3BS6Z4IUJ5SPWC5LHL43/graph.json","fetch_events":"https://pith.science/api/pith-number/CLNFID3BS6Z4IUJ5SPWC5LHL43/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43/action/storage_attestation","attest_author":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43/action/author_attestation","sign_citation":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43/action/citation_signature","submit_replication":"https://pith.science/pith/CLNFID3BS6Z4IUJ5SPWC5LHL43/action/replication_record"}},"created_at":"2026-07-05T11:14:23.869799+00:00","updated_at":"2026-07-05T11:14:23.869799+00:00"}