{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6D5GAC7W3LE3IFO67NMX5EFW2M","short_pith_number":"pith:6D5GAC7W","schema_version":"1.0","canonical_sha256":"f0fa600bf6dac9b415defb597e90b6d3283de187839fef0bb787ea499574d27b","source":{"kind":"arxiv","id":"2403.13117","version":3},"attestation_state":"computed","paper":{"title":"Optimal Flow Matching: Learning Straight Trajectories in Just One Step","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Gasnikov, Alexander Korotin, Nikita Kornilov, Petr Mokrov","submitted_at":"2024-03-19T19:44:54Z","abstract_excerpt":"Over the several recent years, there has been a boom in development of Flow Matching (FM) methods for generative modeling. One intriguing property pursued by the community is the ability to learn flows with straight trajectories which realize the Optimal Transport (OT) displacements. Straightness is crucial for the fast integration (inference) of the learned flow's paths. Unfortunately, most existing flow straightening methods are based on non-trivial iterative FM procedures which accumulate the error during training or exploit heuristics based on minibatch OT. To address these issues, we deve"},"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":"2403.13117","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-03-19T19:44:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6fa93868cce16aa12633e2fb77f30e0186974174eed60db97c27285753d00728","abstract_canon_sha256":"dccafc0f516c323108b4c34a358716a6b4e38b4a8b488051cff0de0232c0a3cb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:32:43.245212Z","signature_b64":"XH3S0K2XrVQou4na5Lv4k7HK+eA0fi5l8yiNlo5Gkte684r0vitCivaJ2EbZaCb85All3qWYqPk6eh/unU/7CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0fa600bf6dac9b415defb597e90b6d3283de187839fef0bb787ea499574d27b","last_reissued_at":"2026-07-05T09:32:43.244692Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:32:43.244692Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Optimal Flow Matching: Learning Straight Trajectories in Just One Step","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alexander Gasnikov, Alexander Korotin, Nikita Kornilov, Petr Mokrov","submitted_at":"2024-03-19T19:44:54Z","abstract_excerpt":"Over the several recent years, there has been a boom in development of Flow Matching (FM) methods for generative modeling. One intriguing property pursued by the community is the ability to learn flows with straight trajectories which realize the Optimal Transport (OT) displacements. Straightness is crucial for the fast integration (inference) of the learned flow's paths. Unfortunately, most existing flow straightening methods are based on non-trivial iterative FM procedures which accumulate the error during training or exploit heuristics based on minibatch OT. To address these issues, we deve"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.13117","kind":"arxiv","version":3},"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/2403.13117/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":"2403.13117","created_at":"2026-07-05T09:32:43.244757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2403.13117v3","created_at":"2026-07-05T09:32:43.244757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.13117","created_at":"2026-07-05T09:32:43.244757+00:00"},{"alias_kind":"pith_short_12","alias_value":"6D5GAC7W3LE3","created_at":"2026-07-05T09:32:43.244757+00:00"},{"alias_kind":"pith_short_16","alias_value":"6D5GAC7W3LE3IFO6","created_at":"2026-07-05T09:32:43.244757+00:00"},{"alias_kind":"pith_short_8","alias_value":"6D5GAC7W","created_at":"2026-07-05T09:32:43.244757+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.19741","citing_title":"Efficient Transferable Optimal Transport via Min-Sliced Transport Plans","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M","json":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M.json","graph_json":"https://pith.science/api/pith-number/6D5GAC7W3LE3IFO67NMX5EFW2M/graph.json","events_json":"https://pith.science/api/pith-number/6D5GAC7W3LE3IFO67NMX5EFW2M/events.json","paper":"https://pith.science/paper/6D5GAC7W"},"agent_actions":{"view_html":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M","download_json":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M.json","view_paper":"https://pith.science/paper/6D5GAC7W","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2403.13117&json=true","fetch_graph":"https://pith.science/api/pith-number/6D5GAC7W3LE3IFO67NMX5EFW2M/graph.json","fetch_events":"https://pith.science/api/pith-number/6D5GAC7W3LE3IFO67NMX5EFW2M/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M/action/storage_attestation","attest_author":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M/action/author_attestation","sign_citation":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M/action/citation_signature","submit_replication":"https://pith.science/pith/6D5GAC7W3LE3IFO67NMX5EFW2M/action/replication_record"}},"created_at":"2026-07-05T09:32:43.244757+00:00","updated_at":"2026-07-05T09:32:43.244757+00:00"}