{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:RSDJJ4T43VCKXQFYUBAKHPFY73","short_pith_number":"pith:RSDJJ4T4","schema_version":"1.0","canonical_sha256":"8c8694f27cdd44abc0b8a040a3bcb8feeca18e814f8748eb7a11004ecaf241d0","source":{"kind":"arxiv","id":"2406.02313","version":4},"attestation_state":"computed","paper":{"title":"Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.stat-mech","authors_text":"B\\'alint M\\'at\\'e, Fran\\c{c}ois Fleuret, Tristan Bereau","submitted_at":"2024-06-04T13:42:42Z","abstract_excerpt":"Thermodynamic integration (TI) offers a rigorous method for estimating free-energy differences by integrating over a sequence of interpolating conformational ensembles. However, TI calculations are computationally expensive and typically limited to coupling a small number of degrees of freedom due to the need to sample numerous intermediate ensembles with sufficient conformational-space overlap. In this work, we propose to perform TI along an alchemical pathway represented by a trainable neural network, which we term Neural TI. Critically, we parametrize a time-dependent Hamiltonian interpolat"},"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":"2406.02313","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cond-mat.stat-mech","submitted_at":"2024-06-04T13:42:42Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"d1cadc395d754f66cd0aae0c0093c677823b96ee886f2078d6b48d90429a92a6","abstract_canon_sha256":"21d03d6d4d92b25ac52d35ed8fb34ddfb052514df967e02f2fff42992b887665"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:43:29.984135Z","signature_b64":"bvon16fesZpS1TTobeoqNkrhFG1kE9zqdeSEtYFTikVjhzxCkLkXpRJwuP/DW4h78R5yQBcs04uiFKSwb+O2BA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8c8694f27cdd44abc0b8a040a3bcb8feeca18e814f8748eb7a11004ecaf241d0","last_reissued_at":"2026-07-05T09:43:29.983586Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:43:29.983586Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neural Thermodynamic Integration: Free Energies from Energy-based Diffusion Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cond-mat.stat-mech","authors_text":"B\\'alint M\\'at\\'e, Fran\\c{c}ois Fleuret, Tristan Bereau","submitted_at":"2024-06-04T13:42:42Z","abstract_excerpt":"Thermodynamic integration (TI) offers a rigorous method for estimating free-energy differences by integrating over a sequence of interpolating conformational ensembles. However, TI calculations are computationally expensive and typically limited to coupling a small number of degrees of freedom due to the need to sample numerous intermediate ensembles with sufficient conformational-space overlap. In this work, we propose to perform TI along an alchemical pathway represented by a trainable neural network, which we term Neural TI. Critically, we parametrize a time-dependent Hamiltonian interpolat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.02313","kind":"arxiv","version":4},"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/2406.02313/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":"2406.02313","created_at":"2026-07-05T09:43:29.983660+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.02313v4","created_at":"2026-07-05T09:43:29.983660+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.02313","created_at":"2026-07-05T09:43:29.983660+00:00"},{"alias_kind":"pith_short_12","alias_value":"RSDJJ4T43VCK","created_at":"2026-07-05T09:43:29.983660+00:00"},{"alias_kind":"pith_short_16","alias_value":"RSDJJ4T43VCKXQFY","created_at":"2026-07-05T09:43:29.983660+00:00"},{"alias_kind":"pith_short_8","alias_value":"RSDJJ4T4","created_at":"2026-07-05T09:43:29.983660+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.10075","citing_title":"Thermodynamic Interpolation: A generative approach to molecular thermodynamics and kinetics","ref_index":10,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73","json":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73.json","graph_json":"https://pith.science/api/pith-number/RSDJJ4T43VCKXQFYUBAKHPFY73/graph.json","events_json":"https://pith.science/api/pith-number/RSDJJ4T43VCKXQFYUBAKHPFY73/events.json","paper":"https://pith.science/paper/RSDJJ4T4"},"agent_actions":{"view_html":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73","download_json":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73.json","view_paper":"https://pith.science/paper/RSDJJ4T4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.02313&json=true","fetch_graph":"https://pith.science/api/pith-number/RSDJJ4T43VCKXQFYUBAKHPFY73/graph.json","fetch_events":"https://pith.science/api/pith-number/RSDJJ4T43VCKXQFYUBAKHPFY73/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73/action/storage_attestation","attest_author":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73/action/author_attestation","sign_citation":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73/action/citation_signature","submit_replication":"https://pith.science/pith/RSDJJ4T43VCKXQFYUBAKHPFY73/action/replication_record"}},"created_at":"2026-07-05T09:43:29.983660+00:00","updated_at":"2026-07-05T09:43:29.983660+00:00"}