{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:UE4JHSZFFUZEF54KDM4IEBDFW6","short_pith_number":"pith:UE4JHSZF","schema_version":"1.0","canonical_sha256":"a13893cb252d3242f78a1b38820465b7ac421c22f5585d41811bfb9f82941656","source":{"kind":"arxiv","id":"2606.21014","version":1},"attestation_state":"computed","paper":{"title":"BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fabio Ramos, Sreevardhan Sirigiri, Weiming Zhi","submitted_at":"2026-06-19T00:55:24Z","abstract_excerpt":"Robots must generate trajectories that remain faithful to learned expert behavior while satisfying safety constraints and task-specific objectives specified only at inference time. We formulate constrained trajectory generation for pretrained diffusion and flow-matching policies as Bayesian posterior sampling, with the learned demonstration distribution as a prior and an inference-time, cost-derived likelihood tilting it toward feasible, optimal trajectories. To sample from this posterior without any retraining of the base policy, we leverage the Feynman--Kac corrector framework, originally fo"},"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":"2606.21014","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.RO","submitted_at":"2026-06-19T00:55:24Z","cross_cats_sorted":[],"title_canon_sha256":"6dd092e62b300b92027e8c1034473ce85b45a27d672f5b3749cd73fc32acbf72","abstract_canon_sha256":"acd6b4c57b7b72eca8c2942fb8249e2a5ef5791e6560b452fb739b987375f8d7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-23T01:12:26.881347Z","signature_b64":"IgyGfj59/aSJ+YP4XN2lv1ZWzz65kezLzhR7ssF3FWChZFXBYHBNZbx13n7FpzcbI2bIGL3YQnIcgUMmj5m1BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a13893cb252d3242f78a1b38820465b7ac421c22f5585d41811bfb9f82941656","last_reissued_at":"2026-06-23T01:12:26.880829Z","signature_status":"signed_v1","first_computed_at":"2026-06-23T01:12:26.880829Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"BayesFP: Posterior Estimation for Flow-Based Policies via Feynman-Kac Sampling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.RO","authors_text":"Fabio Ramos, Sreevardhan Sirigiri, Weiming Zhi","submitted_at":"2026-06-19T00:55:24Z","abstract_excerpt":"Robots must generate trajectories that remain faithful to learned expert behavior while satisfying safety constraints and task-specific objectives specified only at inference time. We formulate constrained trajectory generation for pretrained diffusion and flow-matching policies as Bayesian posterior sampling, with the learned demonstration distribution as a prior and an inference-time, cost-derived likelihood tilting it toward feasible, optimal trajectories. To sample from this posterior without any retraining of the base policy, we leverage the Feynman--Kac corrector framework, originally fo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.21014","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/2606.21014/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":"2606.21014","created_at":"2026-06-23T01:12:26.880895+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.21014v1","created_at":"2026-06-23T01:12:26.880895+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.21014","created_at":"2026-06-23T01:12:26.880895+00:00"},{"alias_kind":"pith_short_12","alias_value":"UE4JHSZFFUZE","created_at":"2026-06-23T01:12:26.880895+00:00"},{"alias_kind":"pith_short_16","alias_value":"UE4JHSZFFUZEF54K","created_at":"2026-06-23T01:12:26.880895+00:00"},{"alias_kind":"pith_short_8","alias_value":"UE4JHSZF","created_at":"2026-06-23T01:12:26.880895+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6","json":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6.json","graph_json":"https://pith.science/api/pith-number/UE4JHSZFFUZEF54KDM4IEBDFW6/graph.json","events_json":"https://pith.science/api/pith-number/UE4JHSZFFUZEF54KDM4IEBDFW6/events.json","paper":"https://pith.science/paper/UE4JHSZF"},"agent_actions":{"view_html":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6","download_json":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6.json","view_paper":"https://pith.science/paper/UE4JHSZF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.21014&json=true","fetch_graph":"https://pith.science/api/pith-number/UE4JHSZFFUZEF54KDM4IEBDFW6/graph.json","fetch_events":"https://pith.science/api/pith-number/UE4JHSZFFUZEF54KDM4IEBDFW6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6/action/storage_attestation","attest_author":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6/action/author_attestation","sign_citation":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6/action/citation_signature","submit_replication":"https://pith.science/pith/UE4JHSZFFUZEF54KDM4IEBDFW6/action/replication_record"}},"created_at":"2026-06-23T01:12:26.880895+00:00","updated_at":"2026-06-23T01:12:26.880895+00:00"}