{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:QRD6IIZU2BXJIX4LR2EYXZ4ZZ7","short_pith_number":"pith:QRD6IIZU","schema_version":"1.0","canonical_sha256":"8447e42334d06e945f8b8e898be799cff8ee1b6704922dabb592e85b0a4a7e95","source":{"kind":"arxiv","id":"2405.14392","version":2},"attestation_state":"computed","paper":{"title":"Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Alberto Cabezas, Christopher Nemeth, Louis Sharrock","submitted_at":"2024-05-23T10:08:19Z","abstract_excerpt":"Continuous normalizing flows (CNFs) learn the probability path between a reference distribution and a target distribution by modeling the vector field generating said path using neural networks. Recently, Lipman et al. (2022) introduced a simple and inexpensive method for training CNFs in generative modeling, termed flow matching (FM). In this paper, we repurpose this method for probabilistic inference by incorporating Markovian sampling methods in evaluating the FM objective, and using the learned CNF to improve Monte Carlo sampling. Specifically, we propose an adaptive Markov chain Monte Car"},"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":"2405.14392","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ME","submitted_at":"2024-05-23T10:08:19Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"17e267c039060ce60ca646fb569afce1d33be03ecedd25393119ca2c3ccf1af5","abstract_canon_sha256":"95a6758e8abc13b77e4ce10bae77f25cdfada56571034efeecb2a450a6bcc050"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:00.723162Z","signature_b64":"9pYYRIfm5xjo9VUuQo7FE4jvlWflI/TNDt1vs24VaKimzw/ay64uSPvWtZH8JD85X0bpEOqbMLLhKUJ+OQfaBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8447e42334d06e945f8b8e898be799cff8ee1b6704922dabb592e85b0a4a7e95","last_reissued_at":"2026-07-05T09:27:00.722728Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:00.722728Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Markovian Flow Matching: Accelerating MCMC with Continuous Normalizing Flows","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"stat.ME","authors_text":"Alberto Cabezas, Christopher Nemeth, Louis Sharrock","submitted_at":"2024-05-23T10:08:19Z","abstract_excerpt":"Continuous normalizing flows (CNFs) learn the probability path between a reference distribution and a target distribution by modeling the vector field generating said path using neural networks. Recently, Lipman et al. (2022) introduced a simple and inexpensive method for training CNFs in generative modeling, termed flow matching (FM). In this paper, we repurpose this method for probabilistic inference by incorporating Markovian sampling methods in evaluating the FM objective, and using the learned CNF to improve Monte Carlo sampling. Specifically, we propose an adaptive Markov chain Monte Car"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.14392","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/2405.14392/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":"2405.14392","created_at":"2026-07-05T09:27:00.722784+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.14392v2","created_at":"2026-07-05T09:27:00.722784+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.14392","created_at":"2026-07-05T09:27:00.722784+00:00"},{"alias_kind":"pith_short_12","alias_value":"QRD6IIZU2BXJ","created_at":"2026-07-05T09:27:00.722784+00:00"},{"alias_kind":"pith_short_16","alias_value":"QRD6IIZU2BXJIX4L","created_at":"2026-07-05T09:27:00.722784+00:00"},{"alias_kind":"pith_short_8","alias_value":"QRD6IIZU","created_at":"2026-07-05T09:27:00.722784+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.04791","citing_title":"Approximating non-Gaussian Bayesian partitions with normalising flows: statistics, inference and application to cosmology","ref_index":22,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7","json":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7.json","graph_json":"https://pith.science/api/pith-number/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/graph.json","events_json":"https://pith.science/api/pith-number/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/events.json","paper":"https://pith.science/paper/QRD6IIZU"},"agent_actions":{"view_html":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7","download_json":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7.json","view_paper":"https://pith.science/paper/QRD6IIZU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.14392&json=true","fetch_graph":"https://pith.science/api/pith-number/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/graph.json","fetch_events":"https://pith.science/api/pith-number/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/action/storage_attestation","attest_author":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/action/author_attestation","sign_citation":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/action/citation_signature","submit_replication":"https://pith.science/pith/QRD6IIZU2BXJIX4LR2EYXZ4ZZ7/action/replication_record"}},"created_at":"2026-07-05T09:27:00.722784+00:00","updated_at":"2026-07-05T09:27:00.722784+00:00"}