{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:WE3VNBB75NUWR4U5LQRMHB4CGW","short_pith_number":"pith:WE3VNBB7","schema_version":"1.0","canonical_sha256":"b13756843feb6968f29d5c22c3878235bbb26a9c00a0f20ed80ea46a7cdaf527","source":{"kind":"arxiv","id":"2605.00337","version":2},"attestation_state":"computed","paper":{"title":"FES-FM: Free Energy Surface Sampling via Reduced Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Training a flow matching model directly in collective variable space allows efficient sampling of free energy surfaces.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tiejun Li, Zichen Liu","submitted_at":"2026-05-01T01:35:48Z","abstract_excerpt":"Sampling the distribution of collective variables (CVs) and estimating the associated free energy surface are crucial problems in statistical physics, as they underpin a better understanding of chemical reactions and conformational transitions. Traditional methods usually rely on simulations in high-dimensional configuration space and project the resulting configurations onto the CV space. To improve sampling speed, we propose FES-FM, a reduced flow matching (FM) method for free energy surface (FES) sampling. We train a dynamical transport map in the CV space, thereby enabling direct sampling "},"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":"2605.00337","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-01T01:35:48Z","cross_cats_sorted":[],"title_canon_sha256":"743f7715ce165a482183dac5dfe113915d102183130e9491ef923e615f79b21b","abstract_canon_sha256":"67bf4bfd37eb876dd28f9d9c332e7396a05a1c149f979115eaa439488c256d89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-23T00:23:40.457223Z","signature_b64":"5tzMzEZcM80u5FeemaIGhwaORbPLboF6MkDPQ2VKmkIN3ME/7l7Fjdiog4K6PYYjGsDIH3Qt+lIPGFCp/R07Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b13756843feb6968f29d5c22c3878235bbb26a9c00a0f20ed80ea46a7cdaf527","last_reissued_at":"2026-07-23T00:23:40.456324Z","signature_status":"signed_v1","first_computed_at":"2026-07-23T00:23:40.456324Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FES-FM: Free Energy Surface Sampling via Reduced Flow Matching","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Training a flow matching model directly in collective variable space allows efficient sampling of free energy surfaces.","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Tiejun Li, Zichen Liu","submitted_at":"2026-05-01T01:35:48Z","abstract_excerpt":"Sampling the distribution of collective variables (CVs) and estimating the associated free energy surface are crucial problems in statistical physics, as they underpin a better understanding of chemical reactions and conformational transitions. Traditional methods usually rely on simulations in high-dimensional configuration space and project the resulting configurations onto the CV space. To improve sampling speed, we propose FES-FM, a reduced flow matching (FM) method for free energy surface (FES) sampling. We train a dynamical transport map in the CV space, thereby enabling direct sampling "},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Comparative experiments demonstrate that our approach drastically reduces computational costs while delivering superior accuracy per unit sampling time.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That a dynamical transport map trained only in collective variable space, even with the Hessian prior, fully captures the free energy distribution without missing important high-dimensional correlations or rare events.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"FES-FM applies reduced flow matching with a Hessian-derived prior to directly sample free energy surfaces in collective variable space, claiming lower computational cost and higher accuracy per unit time than standard methods.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Training a flow matching model directly in collective variable space allows efficient sampling of free energy surfaces.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"79d67fcf49de1d77bad0257b3a3e3cfb91a8030d02fcfb7d7a6f072e41c77823"},"source":{"id":"2605.00337","kind":"arxiv","version":2},"verdict":{"id":"b0281679-26d7-4ea4-ae07-83faefed3c0e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T20:23:53.937208Z","strongest_claim":"Comparative experiments demonstrate that our approach drastically reduces computational costs while delivering superior accuracy per unit sampling time.","one_line_summary":"FES-FM applies reduced flow matching with a Hessian-derived prior to directly sample free energy surfaces in collective variable space, claiming lower computational cost and higher accuracy per unit time than standard methods.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That a dynamical transport map trained only in collective variable space, even with the Hessian prior, fully captures the free energy distribution without missing important high-dimensional correlations or rare events.","pith_extraction_headline":"Training a flow matching model directly in collective variable space allows efficient sampling of free energy surfaces."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.00337/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T20:34:12.295910Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T18:15:54.509647Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"94ed9aba5a8dbafe7cb461ccc4514751c51a9a6c7a0e7cec5f72a22f93dad817"},"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":"2605.00337","created_at":"2026-07-23T00:23:40.456755+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.00337v2","created_at":"2026-07-23T00:23:40.456755+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.00337","created_at":"2026-07-23T00:23:40.456755+00:00"},{"alias_kind":"pith_short_12","alias_value":"WE3VNBB75NUW","created_at":"2026-07-23T00:23:40.456755+00:00"},{"alias_kind":"pith_short_16","alias_value":"WE3VNBB75NUWR4U5","created_at":"2026-07-23T00:23:40.456755+00:00"},{"alias_kind":"pith_short_8","alias_value":"WE3VNBB7","created_at":"2026-07-23T00:23:40.456755+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/WE3VNBB75NUWR4U5LQRMHB4CGW","json":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW.json","graph_json":"https://pith.science/api/pith-number/WE3VNBB75NUWR4U5LQRMHB4CGW/graph.json","events_json":"https://pith.science/api/pith-number/WE3VNBB75NUWR4U5LQRMHB4CGW/events.json","paper":"https://pith.science/paper/WE3VNBB7"},"agent_actions":{"view_html":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW","download_json":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW.json","view_paper":"https://pith.science/paper/WE3VNBB7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.00337&json=true","fetch_graph":"https://pith.science/api/pith-number/WE3VNBB75NUWR4U5LQRMHB4CGW/graph.json","fetch_events":"https://pith.science/api/pith-number/WE3VNBB75NUWR4U5LQRMHB4CGW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW/action/storage_attestation","attest_author":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW/action/author_attestation","sign_citation":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW/action/citation_signature","submit_replication":"https://pith.science/pith/WE3VNBB75NUWR4U5LQRMHB4CGW/action/replication_record"}},"created_at":"2026-07-23T00:23:40.456755+00:00","updated_at":"2026-07-23T00:23:40.456755+00:00"}