{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:4TNGF6KDJP2XB5TGDUI55EJHZ4","short_pith_number":"pith:4TNGF6KD","schema_version":"1.0","canonical_sha256":"e4da62f9434bf570f6661d11de9127cf1e99aaac046fddb8000997202b1f2a59","source":{"kind":"arxiv","id":"2304.14772","version":2},"attestation_state":"computed","paper":{"title":"Multisample Flow Matching: Straightening Flows with Minibatch Couplings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aram-Alexandre Pooladian, Brandon Amos, Carles Domingo-Enrich, Heli Ben-Hamu, Ricky T. Q. Chen, Yaron Lipman","submitted_at":"2023-04-28T11:33:08Z","abstract_excerpt":"Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, such as Flow Matching, derived paths that are optimal for each data sample. However, these algorithms rely on independent data and noise samples, and do not exploit underlying structure in the data distribution for constructing probability paths. We propose Multisample Flow Matching, a more general framework that uses non-trivial couplings between data and noise samples while satisfying the correct marginal constraints"},"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":"2304.14772","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-04-28T11:33:08Z","cross_cats_sorted":[],"title_canon_sha256":"db0d4ed664169e14c55ea06cf17f339bd8eb750758891af915aed1b09b65dd61","abstract_canon_sha256":"e6049046930418eef118f5d008a644f249c421bb504d7b8f7ea1833fe3fc6708"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:13:39.043426Z","signature_b64":"234IK5RpFZSVRl7kNhJGTyLU6fQhE4T4TFQf6jhV42F+KCASecjxUNPtcgxcDDNfXFck/rmG2HCX4LQnkXGtBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e4da62f9434bf570f6661d11de9127cf1e99aaac046fddb8000997202b1f2a59","last_reissued_at":"2026-07-05T06:13:39.042927Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:13:39.042927Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Multisample Flow Matching: Straightening Flows with Minibatch Couplings","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Aram-Alexandre Pooladian, Brandon Amos, Carles Domingo-Enrich, Heli Ben-Hamu, Ricky T. Q. Chen, Yaron Lipman","submitted_at":"2023-04-28T11:33:08Z","abstract_excerpt":"Simulation-free methods for training continuous-time generative models construct probability paths that go between noise distributions and individual data samples. Recent works, such as Flow Matching, derived paths that are optimal for each data sample. However, these algorithms rely on independent data and noise samples, and do not exploit underlying structure in the data distribution for constructing probability paths. We propose Multisample Flow Matching, a more general framework that uses non-trivial couplings between data and noise samples while satisfying the correct marginal constraints"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.14772","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/2304.14772/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":"2304.14772","created_at":"2026-07-05T06:13:39.042986+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.14772v2","created_at":"2026-07-05T06:13:39.042986+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.14772","created_at":"2026-07-05T06:13:39.042986+00:00"},{"alias_kind":"pith_short_12","alias_value":"4TNGF6KDJP2X","created_at":"2026-07-05T06:13:39.042986+00:00"},{"alias_kind":"pith_short_16","alias_value":"4TNGF6KDJP2XB5TG","created_at":"2026-07-05T06:13:39.042986+00:00"},{"alias_kind":"pith_short_8","alias_value":"4TNGF6KD","created_at":"2026-07-05T06:13:39.042986+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23489","citing_title":"MeshFlow: Mesh Generation with Equivariant Flow Matching","ref_index":114,"is_internal_anchor":false},{"citing_arxiv_id":"2606.04092","citing_title":"Optimal Transport Flow Matching by Design","ref_index":44,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12951","citing_title":"Coreset-Induced Conditional Velocity Flow Matching","ref_index":22,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14819","citing_title":"The Velocity Deficit: Initial Energy Injection for Flow Matching","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.22340","citing_title":"From Snapshots to Trajectories: Learning Single-Cell Gene Expression Dynamics via Conditional Flow Matching","ref_index":34,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17733","citing_title":"Divergence-Suppressing Couplings for Rectified Flow","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.21831","citing_title":"Generative Modeling of Discrete Data Using Geometric Latent Subspaces","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2601.23072","citing_title":"SplineFlow: Flow Matching for Dynamical Systems with B-Spline Interpolants","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12951","citing_title":"Coreset-Induced Conditional Velocity Flow Matching","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02222","citing_title":"Generative Modeling with Orbit-Space Particle Flow Matching","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4","json":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4.json","graph_json":"https://pith.science/api/pith-number/4TNGF6KDJP2XB5TGDUI55EJHZ4/graph.json","events_json":"https://pith.science/api/pith-number/4TNGF6KDJP2XB5TGDUI55EJHZ4/events.json","paper":"https://pith.science/paper/4TNGF6KD"},"agent_actions":{"view_html":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4","download_json":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4.json","view_paper":"https://pith.science/paper/4TNGF6KD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.14772&json=true","fetch_graph":"https://pith.science/api/pith-number/4TNGF6KDJP2XB5TGDUI55EJHZ4/graph.json","fetch_events":"https://pith.science/api/pith-number/4TNGF6KDJP2XB5TGDUI55EJHZ4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4/action/storage_attestation","attest_author":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4/action/author_attestation","sign_citation":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4/action/citation_signature","submit_replication":"https://pith.science/pith/4TNGF6KDJP2XB5TGDUI55EJHZ4/action/replication_record"}},"created_at":"2026-07-05T06:13:39.042986+00:00","updated_at":"2026-07-05T06:13:39.042986+00:00"}