{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5NOJLRVATN7OEU44BBWWENKIP3","short_pith_number":"pith:5NOJLRVA","schema_version":"1.0","canonical_sha256":"eb5c95c6a09b7ee2539c086d6235487edd7ccf671aac6854897c7a7ebf5b33ef","source":{"kind":"arxiv","id":"2405.20879","version":2},"attestation_state":"computed","paper":{"title":"Flow matching achieves almost minimax optimal convergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kazusato Oko, Kenji Fukumizu, Masanori Koyama, Noboru Isobe, Taiji Suzuki","submitted_at":"2024-05-31T14:54:51Z","abstract_excerpt":"Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs a simpler approach by solving an ordinary differential equation with an initial condition from a normal distribution, thus streamlining the sample generation process. This paper discusses the convergence properties of FM for large sample size under the $p$-Wasserstein distance, a measure of distributional discrepancy. We establish that FM can achieve an almost minimax optimal convergence rate for $1 \\leq p \\leq 2$, "},"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":"2405.20879","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-31T14:54:51Z","cross_cats_sorted":[],"title_canon_sha256":"90a3e4a8bd9cf2f91f419b0ded5c6cd3fbcc794ef9444533881fb2ed89136538","abstract_canon_sha256":"6397b9d4f712186681b99056e43635bc61b07a88312dedca077c436910f958a6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:18:52.718936Z","signature_b64":"NCC1XJXOV8+AwQ8dBNyFpzktW55wWjM9w1Yy/56ezQg9dUDaReMo9wgBa6DGaKdhPh42XI125tNknUdBuRtiAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb5c95c6a09b7ee2539c086d6235487edd7ccf671aac6854897c7a7ebf5b33ef","last_reissued_at":"2026-07-05T09:18:52.718453Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:18:52.718453Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Flow matching achieves almost minimax optimal convergence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Kazusato Oko, Kenji Fukumizu, Masanori Koyama, Noboru Isobe, Taiji Suzuki","submitted_at":"2024-05-31T14:54:51Z","abstract_excerpt":"Flow matching (FM) has gained significant attention as a simulation-free generative model. Unlike diffusion models, which are based on stochastic differential equations, FM employs a simpler approach by solving an ordinary differential equation with an initial condition from a normal distribution, thus streamlining the sample generation process. This paper discusses the convergence properties of FM for large sample size under the $p$-Wasserstein distance, a measure of distributional discrepancy. We establish that FM can achieve an almost minimax optimal convergence rate for $1 \\leq p \\leq 2$, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.20879","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/2405.20879/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":"2405.20879","created_at":"2026-07-05T09:18:52.718510+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.20879v2","created_at":"2026-07-05T09:18:52.718510+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.20879","created_at":"2026-07-05T09:18:52.718510+00:00"},{"alias_kind":"pith_short_12","alias_value":"5NOJLRVATN7O","created_at":"2026-07-05T09:18:52.718510+00:00"},{"alias_kind":"pith_short_16","alias_value":"5NOJLRVATN7OEU44","created_at":"2026-07-05T09:18:52.718510+00:00"},{"alias_kind":"pith_short_8","alias_value":"5NOJLRVA","created_at":"2026-07-05T09:18:52.718510+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.11138","citing_title":"First-Order Trajectory Matching: Fast Ensemble Predictions of Chaotic, Turbulent, Stochastic Systems","ref_index":25,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3","json":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3.json","graph_json":"https://pith.science/api/pith-number/5NOJLRVATN7OEU44BBWWENKIP3/graph.json","events_json":"https://pith.science/api/pith-number/5NOJLRVATN7OEU44BBWWENKIP3/events.json","paper":"https://pith.science/paper/5NOJLRVA"},"agent_actions":{"view_html":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3","download_json":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3.json","view_paper":"https://pith.science/paper/5NOJLRVA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.20879&json=true","fetch_graph":"https://pith.science/api/pith-number/5NOJLRVATN7OEU44BBWWENKIP3/graph.json","fetch_events":"https://pith.science/api/pith-number/5NOJLRVATN7OEU44BBWWENKIP3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3/action/storage_attestation","attest_author":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3/action/author_attestation","sign_citation":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3/action/citation_signature","submit_replication":"https://pith.science/pith/5NOJLRVATN7OEU44BBWWENKIP3/action/replication_record"}},"created_at":"2026-07-05T09:18:52.718510+00:00","updated_at":"2026-07-05T09:18:52.718510+00:00"}