{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CVHPEDH774SXRMSX7YD6HR5TB2","short_pith_number":"pith:CVHPEDH7","schema_version":"1.0","canonical_sha256":"154ef20cffff2578b257fe07e3c7b30e90e7580b09d8ac5365546d0caefe68c4","source":{"kind":"arxiv","id":"2509.01543","version":1},"attestation_state":"computed","paper":{"title":"Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Esther Heid, Konstantin Mark, Leonard Galustian, Maximilian P.-P. Kovar","submitted_at":"2025-09-01T15:18:03Z","abstract_excerpt":"Conditional Flow Matching(CFM) represents a fast and high-quality approach to generative modelling, but in many applications it is of interest to steer the generated samples towards precise requirements. While steering approaches like gradient-based guidance, sequential Monte Carlo steering or Feynman-Kac steering are well established for diffusion models, they have not been extended to flow matching approaches yet. In this work, we formulate this requirement as tilting the output with an energy potential. We derive, for the first time, Feynman-Kac steering for CFM. We evaluate our approach on"},"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":"2509.01543","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-01T15:18:03Z","cross_cats_sorted":[],"title_canon_sha256":"ef8b0359afc7c410b6b657524e4ea78c85553d6d800625746b4030dad26b9a27","abstract_canon_sha256":"e91068740f4c9dc8736bf1b9c4f9902a0d889874a720f81817084a2d54ce0527"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:03:02.874804Z","signature_b64":"/dky9ocyxEqVwfkVQWUsmd1g7Y/nCzViCn/TlxtKNTyj5+cQWsCM05SmSXgmcnezp4pBBhRmFiE/jdCR7lx/BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"154ef20cffff2578b257fe07e3c7b30e90e7580b09d8ac5365546d0caefe68c4","last_reissued_at":"2026-07-05T12:03:02.874280Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:03:02.874280Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Feynman-Kac-Flow: Inference Steering of Conditional Flow Matching to an Energy-Tilted Posterior","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Esther Heid, Konstantin Mark, Leonard Galustian, Maximilian P.-P. Kovar","submitted_at":"2025-09-01T15:18:03Z","abstract_excerpt":"Conditional Flow Matching(CFM) represents a fast and high-quality approach to generative modelling, but in many applications it is of interest to steer the generated samples towards precise requirements. While steering approaches like gradient-based guidance, sequential Monte Carlo steering or Feynman-Kac steering are well established for diffusion models, they have not been extended to flow matching approaches yet. In this work, we formulate this requirement as tilting the output with an energy potential. We derive, for the first time, Feynman-Kac steering for CFM. We evaluate our approach on"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.01543","kind":"arxiv","version":1},"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/2509.01543/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":"2509.01543","created_at":"2026-07-05T12:03:02.874355+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.01543v1","created_at":"2026-07-05T12:03:02.874355+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.01543","created_at":"2026-07-05T12:03:02.874355+00:00"},{"alias_kind":"pith_short_12","alias_value":"CVHPEDH774SX","created_at":"2026-07-05T12:03:02.874355+00:00"},{"alias_kind":"pith_short_16","alias_value":"CVHPEDH774SXRMSX","created_at":"2026-07-05T12:03:02.874355+00:00"},{"alias_kind":"pith_short_8","alias_value":"CVHPEDH7","created_at":"2026-07-05T12:03:02.874355+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12475","citing_title":"Learning to Assist: Collaborative VLAs for Implicit Human-Robot Collaboration","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2606.10089","citing_title":"A Theory on Flow Matching with Neural Networks","ref_index":295,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2","json":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2.json","graph_json":"https://pith.science/api/pith-number/CVHPEDH774SXRMSX7YD6HR5TB2/graph.json","events_json":"https://pith.science/api/pith-number/CVHPEDH774SXRMSX7YD6HR5TB2/events.json","paper":"https://pith.science/paper/CVHPEDH7"},"agent_actions":{"view_html":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2","download_json":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2.json","view_paper":"https://pith.science/paper/CVHPEDH7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.01543&json=true","fetch_graph":"https://pith.science/api/pith-number/CVHPEDH774SXRMSX7YD6HR5TB2/graph.json","fetch_events":"https://pith.science/api/pith-number/CVHPEDH774SXRMSX7YD6HR5TB2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2/action/storage_attestation","attest_author":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2/action/author_attestation","sign_citation":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2/action/citation_signature","submit_replication":"https://pith.science/pith/CVHPEDH774SXRMSX7YD6HR5TB2/action/replication_record"}},"created_at":"2026-07-05T12:03:02.874355+00:00","updated_at":"2026-07-05T12:03:02.874355+00:00"}