{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:BQP4UGST3BSFJ25TC27GUGOPKS","short_pith_number":"pith:BQP4UGST","schema_version":"1.0","canonical_sha256":"0c1fca1a53d86454ebb316be6a19cf54b0e8cf14e30a6a46bd5fa963ce75f8eb","source":{"kind":"arxiv","id":"2602.22265","version":2},"attestation_state":"computed","paper":{"title":"Entropy-Controlled Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chika Maduabuchi","submitted_at":"2026-02-25T06:07:01Z","abstract_excerpt":"Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives do not directly control the information geometry of the trajectory, allowing low-entropy bottlenecks that can transiently deplete semantic modes. We propose Entropy-Controlled Flow Matching (ECFM): a constrained variational principle over continuity-equation paths enforcing a global entropy-rate budget d/dt H(mu_t) >= -lambda. ECFM is a convex optimization "},"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":"2602.22265","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-02-25T06:07:01Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"8d9a8d4da782383014f271bdbfeb1cc8154a482e19d746ffec95b07f2b7955c3","abstract_canon_sha256":"8b11263e6660a357e8810b3b1cccdc6086c02c4a0fb3b32710efefb7f6e8f546"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-25T00:18:13.166593Z","signature_b64":"0K3pB6nA+0jydy0TuY/HgWmziKurRVL/Wr5uMpXzUlC5ucs2Ak3KBHTVITIxvT2dRoGhcV7+LKR2qnpt6MiaBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0c1fca1a53d86454ebb316be6a19cf54b0e8cf14e30a6a46bd5fa963ce75f8eb","last_reissued_at":"2026-06-25T00:18:13.166087Z","signature_status":"signed_v1","first_computed_at":"2026-06-25T00:18:13.166087Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Entropy-Controlled Flow Matching","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Chika Maduabuchi","submitted_at":"2026-02-25T06:07:01Z","abstract_excerpt":"Modern vision generators transport a base distribution to data through time-indexed measures, implemented as deterministic flows (ODEs) or stochastic diffusions (SDEs). Despite strong empirical performance, standard flow-matching objectives do not directly control the information geometry of the trajectory, allowing low-entropy bottlenecks that can transiently deplete semantic modes. We propose Entropy-Controlled Flow Matching (ECFM): a constrained variational principle over continuity-equation paths enforcing a global entropy-rate budget d/dt H(mu_t) >= -lambda. ECFM is a convex optimization "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2602.22265","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/2602.22265/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":"2602.22265","created_at":"2026-06-25T00:18:13.166145+00:00"},{"alias_kind":"arxiv_version","alias_value":"2602.22265v2","created_at":"2026-06-25T00:18:13.166145+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2602.22265","created_at":"2026-06-25T00:18:13.166145+00:00"},{"alias_kind":"pith_short_12","alias_value":"BQP4UGST3BSF","created_at":"2026-06-25T00:18:13.166145+00:00"},{"alias_kind":"pith_short_16","alias_value":"BQP4UGST3BSFJ25T","created_at":"2026-06-25T00:18:13.166145+00:00"},{"alias_kind":"pith_short_8","alias_value":"BQP4UGST","created_at":"2026-06-25T00:18:13.166145+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.12112","citing_title":"When Policy Entropy Constraint Fails: Preserving Diversity in Flow-based RLHF via Perceptual Entropy","ref_index":45,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS","json":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS.json","graph_json":"https://pith.science/api/pith-number/BQP4UGST3BSFJ25TC27GUGOPKS/graph.json","events_json":"https://pith.science/api/pith-number/BQP4UGST3BSFJ25TC27GUGOPKS/events.json","paper":"https://pith.science/paper/BQP4UGST"},"agent_actions":{"view_html":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS","download_json":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS.json","view_paper":"https://pith.science/paper/BQP4UGST","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2602.22265&json=true","fetch_graph":"https://pith.science/api/pith-number/BQP4UGST3BSFJ25TC27GUGOPKS/graph.json","fetch_events":"https://pith.science/api/pith-number/BQP4UGST3BSFJ25TC27GUGOPKS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS/action/storage_attestation","attest_author":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS/action/author_attestation","sign_citation":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS/action/citation_signature","submit_replication":"https://pith.science/pith/BQP4UGST3BSFJ25TC27GUGOPKS/action/replication_record"}},"created_at":"2026-06-25T00:18:13.166145+00:00","updated_at":"2026-06-25T00:18:13.166145+00:00"}