{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RCTLJG2EU4OWPQDHAAH5ZFWDTA","short_pith_number":"pith:RCTLJG2E","schema_version":"1.0","canonical_sha256":"88a6b49b44a71d67c067000fdc96c39829c8e2ddc70fb18ce352065a9fec1414","source":{"kind":"arxiv","id":"2605.15419","version":1},"attestation_state":"computed","paper":{"title":"Lagrangian Flow Matching: A Least-Action Framework for Principled Path Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Minimizing a general Lagrangian's action under the continuity equation produces a family of probability paths for flow matching.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junzhe Zhang, Shukai Du, Yiming Li","submitted_at":"2026-05-14T21:05:03Z","abstract_excerpt":"Flow matching trains a neural velocity field by regression against a target velocity associated with a prescribed probability path connecting a simple initial distribution to the data distribution. A central design choice is the path itself. Existing constructions, including rectified and optimal-transport-based paths, transport samples along straight lines between coupled endpoints and thus cover only a narrow class of dynamics. We observe that this corresponds to the simplest case of the least-action principle in classical mechanics, in which the kinetic Lagrangian yields free-particle strai"},"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":true,"formal_links_present":true},"canonical_record":{"source":{"id":"2605.15419","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-14T21:05:03Z","cross_cats_sorted":[],"title_canon_sha256":"8f94b1d4a152b12dd6e95b734af9f9742444f422deed75309cdc13e4e4506dd1","abstract_canon_sha256":"f228cb44b3931ee5f81fcba193e146d068ee4a180fa2b59ee54e2d31ac0b64a2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:00:57.623665Z","signature_b64":"syjfIo12nSmW5GX/Cjyz+6nqSBsBnioT2hEaaRLPtQ4nLTplDeYUa/LjWgFqCKqPPbDNqGnCib0h9p4ou5yHBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"88a6b49b44a71d67c067000fdc96c39829c8e2ddc70fb18ce352065a9fec1414","last_reissued_at":"2026-05-20T00:00:57.622873Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:00:57.622873Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lagrangian Flow Matching: A Least-Action Framework for Principled Path Design","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Minimizing a general Lagrangian's action under the continuity equation produces a family of probability paths for flow matching.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Junzhe Zhang, Shukai Du, Yiming Li","submitted_at":"2026-05-14T21:05:03Z","abstract_excerpt":"Flow matching trains a neural velocity field by regression against a target velocity associated with a prescribed probability path connecting a simple initial distribution to the data distribution. A central design choice is the path itself. Existing constructions, including rectified and optimal-transport-based paths, transport samples along straight lines between coupled endpoints and thus cover only a narrow class of dynamics. We observe that this corresponds to the simplest case of the least-action principle in classical mechanics, in which the kinetic Lagrangian yields free-particle strai"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"We show that this dynamic problem admits an equivalent static optimal transport (OT) formulation, yielding a family of simulation-free training objectives that recover OT-based flow matching as the kinetic special case and the trigonometric variance-preserving diffusion path as the harmonic-oscillator case.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The assumption that minimizing the action of an arbitrary Lagrangian subject to the continuity equation and fixed marginal endpoints produces a valid probability path whose induced velocity field can be regressed by a neural network without introducing inconsistencies or requiring simulation.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Lagrangian flow matching minimizes action of a general Lagrangian subject to continuity equation and endpoints to generate new probability paths and simulation-free training objectives that recover prior flow matching methods as special cases.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Minimizing a general Lagrangian's action under the continuity equation produces a family of probability paths for flow matching.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"7e6f8dabf95526acfeefd9cdbffc147c0be5de4d4416ceb3f3e2647e9571d26c"},"source":{"id":"2605.15419","kind":"arxiv","version":1},"verdict":{"id":"f5bd1302-09a9-41f3-bc4e-09ce28b782cc","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-19T15:49:51.168263Z","strongest_claim":"We show that this dynamic problem admits an equivalent static optimal transport (OT) formulation, yielding a family of simulation-free training objectives that recover OT-based flow matching as the kinetic special case and the trigonometric variance-preserving diffusion path as the harmonic-oscillator case.","one_line_summary":"Lagrangian flow matching minimizes action of a general Lagrangian subject to continuity equation and endpoints to generate new probability paths and simulation-free training objectives that recover prior flow matching methods as special cases.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The assumption that minimizing the action of an arbitrary Lagrangian subject to the continuity equation and fixed marginal endpoints produces a valid probability path whose induced velocity field can be regressed by a neural network without introducing inconsistencies or requiring simulation.","pith_extraction_headline":"Minimizing a general Lagrangian's action under the continuity equation produces a family of probability paths for flow matching."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.15419/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"cited_work_retraction","ran_at":"2026-05-19T16:22:12.760587Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T16:04:39.999601Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_title_agreement","ran_at":"2026-05-19T16:01:17.991806Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"citation_quote_validity","ran_at":"2026-05-19T15:50:43.812513Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T14:21:54.143788Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T13:33:22.705146Z","status":"skipped","version":"1.0.0","findings_count":0}],"snapshot_sha256":"52a0a8190e6e5461db9bb455ea7bf00ea0adbef34f1930688608c34fc45fefbc"},"references":{"count":31,"sample":[{"doi":"","year":2025,"title":"M. S. Albergo, N. M. Boffi, and E. Vanden-Eijnden. Stochastic interpolants: A unifying framework for flows and diffusions.Journal of Machine Learning Research, 26(209):1–80, 2025","work_id":"4a85a9da-2d60-428f-9fe7-d66bc074a919","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2023,"title":"M. S. Albergo and E. Vanden-Eijnden. Building normalizing flows with stochastic interpolants. InThe Eleventh International Conference on Learning Representations (ICLR), 2023","work_id":"215142f4-ac3b-4521-842a-627c67ca1904","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2005,"title":"L. Ambrosio, N. Gigli, and G. Savaré.Gradient Flows: In Metric Spaces and in the Space of Probability Measures. Birkhäuser, Basel, 2005","work_id":"cee8e776-92fa-402c-a7af-c27333127ca0","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":1989,"title":"V . I. Arnold, K. V ogtmann, and A. Weinstein.Mathematical Methods of Classical Mechanics, volume 60 ofGraduate Texts in Mathematics. Springer, New York, 2 edition, 1989","work_id":"30cf9856-0dbc-4ad7-aeaf-e821ebfb6e59","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2025,"title":"arXiv preprint arXiv:2504.10612 , year=","work_id":"d0d065c8-17d7-404d-87f8-af8a3656897d","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":31,"snapshot_sha256":"f684f6838efa533d413cf95c7764a4c22458f6eb842227df82e2fe4e48aea795","internal_anchors":0},"formal_canon":{"evidence_count":2,"snapshot_sha256":"4089b2c0a19547d088830b91c924d1aafe9d3faedeea0f89d4dd0bdbafc2b08d"},"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":"2605.15419","created_at":"2026-05-20T00:00:57.622999+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15419v1","created_at":"2026-05-20T00:00:57.622999+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15419","created_at":"2026-05-20T00:00:57.622999+00:00"},{"alias_kind":"pith_short_12","alias_value":"RCTLJG2EU4OW","created_at":"2026-05-20T00:00:57.622999+00:00"},{"alias_kind":"pith_short_16","alias_value":"RCTLJG2EU4OWPQDH","created_at":"2026-05-20T00:00:57.622999+00:00"},{"alias_kind":"pith_short_8","alias_value":"RCTLJG2E","created_at":"2026-05-20T00:00:57.622999+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA","json":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA.json","graph_json":"https://pith.science/api/pith-number/RCTLJG2EU4OWPQDHAAH5ZFWDTA/graph.json","events_json":"https://pith.science/api/pith-number/RCTLJG2EU4OWPQDHAAH5ZFWDTA/events.json","paper":"https://pith.science/paper/RCTLJG2E"},"agent_actions":{"view_html":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA","download_json":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA.json","view_paper":"https://pith.science/paper/RCTLJG2E","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15419&json=true","fetch_graph":"https://pith.science/api/pith-number/RCTLJG2EU4OWPQDHAAH5ZFWDTA/graph.json","fetch_events":"https://pith.science/api/pith-number/RCTLJG2EU4OWPQDHAAH5ZFWDTA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA/action/storage_attestation","attest_author":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA/action/author_attestation","sign_citation":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA/action/citation_signature","submit_replication":"https://pith.science/pith/RCTLJG2EU4OWPQDHAAH5ZFWDTA/action/replication_record"}},"created_at":"2026-05-20T00:00:57.622999+00:00","updated_at":"2026-05-20T00:00:57.622999+00:00"}