{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:M3SPIKVT6VAIEPPILMFJQY2WSC","short_pith_number":"pith:M3SPIKVT","schema_version":"1.0","canonical_sha256":"66e4f42ab3f540823de85b0a98635690b043eb863f60094a9af95b0ddabdd376","source":{"kind":"arxiv","id":"2410.02548","version":4},"attestation_state":"computed","paper":{"title":"Local Flow Matching Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chen Xu, Xiuyuan Cheng, Yao Xie","submitted_at":"2024-10-03T14:53:10Z","abstract_excerpt":"Flow Matching (FM) is a simulation-free method for learning a continuous, invertible flow that interpolates between two distributions, and in particular generates data from noise. Inspired by the variational nature of the diffusion process as a gradient flow, we introduce a stepwise FM model, Local Flow Matching (LFM), which sequentially learns a sequence of FM submodels, each matching a diffusion process up to the time-step size in the data-to-noise direction. In each step, the two distributions to be interpolated by the sub-flow model are closer than those in the full-flow matching model, wh"},"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":"2410.02548","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-10-03T14:53:10Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fbfdf64f072e3f51329577635f11ede5db594314534444ee6b2a467d4730d5bd","abstract_canon_sha256":"2aca226339651cc9ca6a0a544952baf2b24203e199ab27e22e7b74b4cf1fac7d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T02:13:13.187446Z","signature_b64":"Cy0rF82dcVK+XxBgWp2E5TzqJN7NNqztahBwS64BWUXFFsjMSd8HnUCdonkQ8uMiXjmppBQO9715JOk5s9VLDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"66e4f42ab3f540823de85b0a98635690b043eb863f60094a9af95b0ddabdd376","last_reissued_at":"2026-06-23T02:13:13.186954Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T02:13:13.186954Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Local Flow Matching Generative Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Chen Xu, Xiuyuan Cheng, Yao Xie","submitted_at":"2024-10-03T14:53:10Z","abstract_excerpt":"Flow Matching (FM) is a simulation-free method for learning a continuous, invertible flow that interpolates between two distributions, and in particular generates data from noise. Inspired by the variational nature of the diffusion process as a gradient flow, we introduce a stepwise FM model, Local Flow Matching (LFM), which sequentially learns a sequence of FM submodels, each matching a diffusion process up to the time-step size in the data-to-noise direction. In each step, the two distributions to be interpolated by the sub-flow model are closer than those in the full-flow matching model, wh"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.02548","kind":"arxiv","version":4},"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/2410.02548/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":"2410.02548","created_at":"2026-06-23T02:13:13.187010+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.02548v4","created_at":"2026-06-23T02:13:13.187010+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.02548","created_at":"2026-06-23T02:13:13.187010+00:00"},{"alias_kind":"pith_short_12","alias_value":"M3SPIKVT6VAI","created_at":"2026-06-23T02:13:13.187010+00:00"},{"alias_kind":"pith_short_16","alias_value":"M3SPIKVT6VAIEPPI","created_at":"2026-06-23T02:13:13.187010+00:00"},{"alias_kind":"pith_short_8","alias_value":"M3SPIKVT","created_at":"2026-06-23T02:13:13.187010+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.16024","citing_title":"Toward Theoretical Insights into Diffusion Trajectory Distillation via Operator Merging","ref_index":37,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC","json":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC.json","graph_json":"https://pith.science/api/pith-number/M3SPIKVT6VAIEPPILMFJQY2WSC/graph.json","events_json":"https://pith.science/api/pith-number/M3SPIKVT6VAIEPPILMFJQY2WSC/events.json","paper":"https://pith.science/paper/M3SPIKVT"},"agent_actions":{"view_html":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC","download_json":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC.json","view_paper":"https://pith.science/paper/M3SPIKVT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.02548&json=true","fetch_graph":"https://pith.science/api/pith-number/M3SPIKVT6VAIEPPILMFJQY2WSC/graph.json","fetch_events":"https://pith.science/api/pith-number/M3SPIKVT6VAIEPPILMFJQY2WSC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC/action/storage_attestation","attest_author":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC/action/author_attestation","sign_citation":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC/action/citation_signature","submit_replication":"https://pith.science/pith/M3SPIKVT6VAIEPPILMFJQY2WSC/action/replication_record"}},"created_at":"2026-06-23T02:13:13.187010+00:00","updated_at":"2026-06-23T02:13:13.187010+00:00"}