{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PHWANY5IOHWITGDQWADUSQT3MP","short_pith_number":"pith:PHWANY5I","schema_version":"1.0","canonical_sha256":"79ec06e3a871ec899870b00749427b63f3145d967aaf1fbec51976ecf9bdc638","source":{"kind":"arxiv","id":"2512.23956","version":2},"attestation_state":"computed","paper":{"title":"Implicit geometric regularization in flow matching via density weighted Stein operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Shinto Eguchi","submitted_at":"2025-12-30T03:08:00Z","abstract_excerpt":"Flow Matching (FM) has emerged as a powerful paradigm for continuous normalizing flows, yet standard FM implicitly performs an unweighted $L^2$ regression over the entire ambient space. In high dimensions, this leads to a fundamental inefficiency: the vast majority of the integration domain consists of low-density ``void'' regions where the target velocity fields are often chaotic or ill-defined. In this paper, we propose {$\\gamma$-Flow Matching ($\\gamma$-FM)}, a density-weighted variant that aligns the regression geometry with the underlying probability flow. While density weighting is desira"},"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":"2512.23956","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-12-30T03:08:00Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c19fdbde82f5a3085f923c567402435187e8979f5fc90b55b4e6d4984d01f807","abstract_canon_sha256":"7a2d6e091e8712111445d9a3d19797c52c86871ddccbbff42471ffdd43c76958"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T01:03:21.359529Z","signature_b64":"zChU70NT9cy69Xa7JUjmnuEivqXnvSiGxoD81PGb/Kn7gJdZB1bIKEX6UVZdu/6Q3jrBXvtghZpbEF7hxuLkAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"79ec06e3a871ec899870b00749427b63f3145d967aaf1fbec51976ecf9bdc638","last_reissued_at":"2026-05-26T01:03:21.358534Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T01:03:21.358534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Implicit geometric regularization in flow matching via density weighted Stein operators","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Shinto Eguchi","submitted_at":"2025-12-30T03:08:00Z","abstract_excerpt":"Flow Matching (FM) has emerged as a powerful paradigm for continuous normalizing flows, yet standard FM implicitly performs an unweighted $L^2$ regression over the entire ambient space. In high dimensions, this leads to a fundamental inefficiency: the vast majority of the integration domain consists of low-density ``void'' regions where the target velocity fields are often chaotic or ill-defined. In this paper, we propose {$\\gamma$-Flow Matching ($\\gamma$-FM)}, a density-weighted variant that aligns the regression geometry with the underlying probability flow. While density weighting is desira"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.23956","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/2512.23956/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":"2512.23956","created_at":"2026-05-26T01:03:21.358659+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.23956v2","created_at":"2026-05-26T01:03:21.358659+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.23956","created_at":"2026-05-26T01:03:21.358659+00:00"},{"alias_kind":"pith_short_12","alias_value":"PHWANY5IOHWI","created_at":"2026-05-26T01:03:21.358659+00:00"},{"alias_kind":"pith_short_16","alias_value":"PHWANY5IOHWITGDQ","created_at":"2026-05-26T01:03:21.358659+00:00"},{"alias_kind":"pith_short_8","alias_value":"PHWANY5I","created_at":"2026-05-26T01:03:21.358659+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.06680","citing_title":"On the Role of Strain and Vorticity in Numerical Integration Error for Flow Matching","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP","json":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP.json","graph_json":"https://pith.science/api/pith-number/PHWANY5IOHWITGDQWADUSQT3MP/graph.json","events_json":"https://pith.science/api/pith-number/PHWANY5IOHWITGDQWADUSQT3MP/events.json","paper":"https://pith.science/paper/PHWANY5I"},"agent_actions":{"view_html":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP","download_json":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP.json","view_paper":"https://pith.science/paper/PHWANY5I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.23956&json=true","fetch_graph":"https://pith.science/api/pith-number/PHWANY5IOHWITGDQWADUSQT3MP/graph.json","fetch_events":"https://pith.science/api/pith-number/PHWANY5IOHWITGDQWADUSQT3MP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP/action/storage_attestation","attest_author":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP/action/author_attestation","sign_citation":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP/action/citation_signature","submit_replication":"https://pith.science/pith/PHWANY5IOHWITGDQWADUSQT3MP/action/replication_record"}},"created_at":"2026-05-26T01:03:21.358659+00:00","updated_at":"2026-05-26T01:03:21.358659+00:00"}