{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PXHSAMG3QQTBBRLSGAW4V656D6","short_pith_number":"pith:PXHSAMG3","schema_version":"1.0","canonical_sha256":"7dcf2030db842610c572302dcafbbe1fac4688f4554b8557b809c5363210d0a5","source":{"kind":"arxiv","id":"2503.01375","version":2},"attestation_state":"computed","paper":{"title":"Bayesian Inverse Problems Meet Flow Matching: Efficient and Flexible Inference via Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniil Sherki, Ekaterina Muravleva, Ivan Oseledets","submitted_at":"2025-03-03T10:17:56Z","abstract_excerpt":"The efficient resolution of Bayesian inverse problems remains challenging due to the high computational cost of traditional sampling methods. In this paper, we propose a novel framework that integrates Conditional Flow Matching (CFM) with a transformer-based architecture to enable fast and flexible sampling from complex posterior distributions. The proposed methodology involves the direct learning of conditional probability trajectories from the data, leveraging CFM's ability to bypass iterative simulation and transformers' capacity to process arbitrary numbers of observations. The efficacy of"},"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":"2503.01375","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T10:17:56Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c31c6b25aa0ce19f03ef3b44746d0caf79ceb8ed30178b1bdd5ff2f81cb2389f","abstract_canon_sha256":"939395d3a958cc565d04f525498b8dcf74a900b48cb861585d98fe39951dec44"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:04:21.309409Z","signature_b64":"Y5DEjm3HcU3gjBGP2Da7p2Puu2yMPf2/wYMP2OyuvPij6iuUsXr4hJzj0D2R+EoFnyRF1Kc4L927ftFAhQaIDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7dcf2030db842610c572302dcafbbe1fac4688f4554b8557b809c5363210d0a5","last_reissued_at":"2026-07-05T11:04:21.308877Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:04:21.308877Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Bayesian Inverse Problems Meet Flow Matching: Efficient and Flexible Inference via Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Daniil Sherki, Ekaterina Muravleva, Ivan Oseledets","submitted_at":"2025-03-03T10:17:56Z","abstract_excerpt":"The efficient resolution of Bayesian inverse problems remains challenging due to the high computational cost of traditional sampling methods. In this paper, we propose a novel framework that integrates Conditional Flow Matching (CFM) with a transformer-based architecture to enable fast and flexible sampling from complex posterior distributions. The proposed methodology involves the direct learning of conditional probability trajectories from the data, leveraging CFM's ability to bypass iterative simulation and transformers' capacity to process arbitrary numbers of observations. The efficacy of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01375","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/2503.01375/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":"2503.01375","created_at":"2026-07-05T11:04:21.308944+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01375v2","created_at":"2026-07-05T11:04:21.308944+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01375","created_at":"2026-07-05T11:04:21.308944+00:00"},{"alias_kind":"pith_short_12","alias_value":"PXHSAMG3QQTB","created_at":"2026-07-05T11:04:21.308944+00:00"},{"alias_kind":"pith_short_16","alias_value":"PXHSAMG3QQTBBRLS","created_at":"2026-07-05T11:04:21.308944+00:00"},{"alias_kind":"pith_short_8","alias_value":"PXHSAMG3","created_at":"2026-07-05T11:04:21.308944+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.24534","citing_title":"Amortized Posteriors for Estimation of Material Constitutive Parameters from Multimodal Measurements on Small Punch Tests","ref_index":38,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6","json":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6.json","graph_json":"https://pith.science/api/pith-number/PXHSAMG3QQTBBRLSGAW4V656D6/graph.json","events_json":"https://pith.science/api/pith-number/PXHSAMG3QQTBBRLSGAW4V656D6/events.json","paper":"https://pith.science/paper/PXHSAMG3"},"agent_actions":{"view_html":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6","download_json":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6.json","view_paper":"https://pith.science/paper/PXHSAMG3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01375&json=true","fetch_graph":"https://pith.science/api/pith-number/PXHSAMG3QQTBBRLSGAW4V656D6/graph.json","fetch_events":"https://pith.science/api/pith-number/PXHSAMG3QQTBBRLSGAW4V656D6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6/action/storage_attestation","attest_author":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6/action/author_attestation","sign_citation":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6/action/citation_signature","submit_replication":"https://pith.science/pith/PXHSAMG3QQTBBRLSGAW4V656D6/action/replication_record"}},"created_at":"2026-07-05T11:04:21.308944+00:00","updated_at":"2026-07-05T11:04:21.308944+00:00"}