{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ROQLPDUMORMH6OIDWPBFB347CL","short_pith_number":"pith:ROQLPDUM","schema_version":"1.0","canonical_sha256":"8ba0b78e8c74587f3903b3c250ef9f12c4c1429805aba5d2afda9b66cc1d2166","source":{"kind":"arxiv","id":"2503.09069","version":1},"attestation_state":"computed","paper":{"title":"Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengyue Gong, Jiangxuan Long, Xiaoyu Li, Yingyu Liang, Yu Tian, Zhao Song, Zhenmei Shi","submitted_at":"2025-03-12T05:07:07Z","abstract_excerpt":"Flow matching has emerged as a powerful framework for generative modeling, offering computational advantages over diffusion models by leveraging deterministic Ordinary Differential Equations (ODEs) instead of stochastic dynamics. While prior work established the worst case optimality of standard flow matching under Wasserstein distances, the theoretical guarantees for higher-order flow matching - which incorporates acceleration terms to refine sample trajectories - remain unexplored. In this paper, we bridge this gap by proving that higher-order flow matching preserves worst case optimality as"},"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":"2503.09069","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-12T05:07:07Z","cross_cats_sorted":["cs.AI","cs.CV","stat.ML"],"title_canon_sha256":"1c03f08cce89e57206ef2f486c8834afede2d94d3e1b414d246d5d58ad095273","abstract_canon_sha256":"9e3170186b8485f32f7c0e4af2359747736f449244ec13e84dc2e8c603265b8e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:29:47.727307Z","signature_b64":"sS4hVKtkLNEhhLATv7hyKSkOM4v+UmzWtNNzT9Kh2cjNyypo2/plEkMTDLLO86OoK967+Mzawe5E4hX3wSM8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ba0b78e8c74587f3903b3c250ef9f12c4c1429805aba5d2afda9b66cc1d2166","last_reissued_at":"2026-07-05T10:29:47.726738Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:29:47.726738Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Theoretical Guarantees for High Order Trajectory Refinement in Generative Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CV","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chengyue Gong, Jiangxuan Long, Xiaoyu Li, Yingyu Liang, Yu Tian, Zhao Song, Zhenmei Shi","submitted_at":"2025-03-12T05:07:07Z","abstract_excerpt":"Flow matching has emerged as a powerful framework for generative modeling, offering computational advantages over diffusion models by leveraging deterministic Ordinary Differential Equations (ODEs) instead of stochastic dynamics. While prior work established the worst case optimality of standard flow matching under Wasserstein distances, the theoretical guarantees for higher-order flow matching - which incorporates acceleration terms to refine sample trajectories - remain unexplored. In this paper, we bridge this gap by proving that higher-order flow matching preserves worst case optimality as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.09069","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/2503.09069/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":"2503.09069","created_at":"2026-07-05T10:29:47.726827+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.09069v1","created_at":"2026-07-05T10:29:47.726827+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.09069","created_at":"2026-07-05T10:29:47.726827+00:00"},{"alias_kind":"pith_short_12","alias_value":"ROQLPDUMORMH","created_at":"2026-07-05T10:29:47.726827+00:00"},{"alias_kind":"pith_short_16","alias_value":"ROQLPDUMORMH6OID","created_at":"2026-07-05T10:29:47.726827+00:00"},{"alias_kind":"pith_short_8","alias_value":"ROQLPDUM","created_at":"2026-07-05T10:29:47.726827+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.18107","citing_title":"T2VWorldBench: A Benchmark for Evaluating World Knowledge in Text-to-Video Generation","ref_index":11,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL","json":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL.json","graph_json":"https://pith.science/api/pith-number/ROQLPDUMORMH6OIDWPBFB347CL/graph.json","events_json":"https://pith.science/api/pith-number/ROQLPDUMORMH6OIDWPBFB347CL/events.json","paper":"https://pith.science/paper/ROQLPDUM"},"agent_actions":{"view_html":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL","download_json":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL.json","view_paper":"https://pith.science/paper/ROQLPDUM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.09069&json=true","fetch_graph":"https://pith.science/api/pith-number/ROQLPDUMORMH6OIDWPBFB347CL/graph.json","fetch_events":"https://pith.science/api/pith-number/ROQLPDUMORMH6OIDWPBFB347CL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL/action/storage_attestation","attest_author":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL/action/author_attestation","sign_citation":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL/action/citation_signature","submit_replication":"https://pith.science/pith/ROQLPDUMORMH6OIDWPBFB347CL/action/replication_record"}},"created_at":"2026-07-05T10:29:47.726827+00:00","updated_at":"2026-07-05T10:29:47.726827+00:00"}