{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:2F4WIFWB5WT24KVRRJVTJFOAL5","short_pith_number":"pith:2F4WIFWB","schema_version":"1.0","canonical_sha256":"d1796416c1eda7ae2ab18a6b3495c05f5dabafbf84b3167bdf95efe45f5d91ca","source":{"kind":"arxiv","id":"2501.19077","version":2},"attestation_state":"computed","paper":{"title":"Temperature-Annealed Boltzmann Generators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Henrik Schopmans, Pascal Friederich","submitted_at":"2025-01-31T12:09:40Z","abstract_excerpt":"Efficient sampling of unnormalized probability densities such as the Boltzmann distribution of molecular systems is a longstanding challenge. Next to conventional approaches like molecular dynamics or Markov chain Monte Carlo, variational approaches, such as training normalizing flows with the reverse Kullback-Leibler divergence, have been introduced. However, such methods are prone to mode collapse and often do not learn to sample the full configurational space. Here, we present temperature-annealed Boltzmann generators (TA-BG) to address this challenge. First, we demonstrate that training a "},"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":"2501.19077","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-01-31T12:09:40Z","cross_cats_sorted":[],"title_canon_sha256":"2fb7d34247c7c0779096b28510d7f239abc93cce1c7ab6ed929bc9bd66ac1ef8","abstract_canon_sha256":"9fc851eff455ca73b180fea62404010df153656c13990a34a1442cb2ff136628"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:36.195056Z","signature_b64":"gQXXYY69WTQ0iZW7MGZwUDINL7BJ/vwxvDjQ43MryOzXqlyJDL3/dklf0TVXHb0Cz8mBSotULydKAFjg1nK2Dw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d1796416c1eda7ae2ab18a6b3495c05f5dabafbf84b3167bdf95efe45f5d91ca","last_reissued_at":"2026-07-05T11:22:36.194566Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:36.194566Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Temperature-Annealed Boltzmann Generators","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Henrik Schopmans, Pascal Friederich","submitted_at":"2025-01-31T12:09:40Z","abstract_excerpt":"Efficient sampling of unnormalized probability densities such as the Boltzmann distribution of molecular systems is a longstanding challenge. Next to conventional approaches like molecular dynamics or Markov chain Monte Carlo, variational approaches, such as training normalizing flows with the reverse Kullback-Leibler divergence, have been introduced. However, such methods are prone to mode collapse and often do not learn to sample the full configurational space. Here, we present temperature-annealed Boltzmann generators (TA-BG) to address this challenge. First, we demonstrate that training a "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.19077","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/2501.19077/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":"2501.19077","created_at":"2026-07-05T11:22:36.194628+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.19077v2","created_at":"2026-07-05T11:22:36.194628+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.19077","created_at":"2026-07-05T11:22:36.194628+00:00"},{"alias_kind":"pith_short_12","alias_value":"2F4WIFWB5WT2","created_at":"2026-07-05T11:22:36.194628+00:00"},{"alias_kind":"pith_short_16","alias_value":"2F4WIFWB5WT24KVR","created_at":"2026-07-05T11:22:36.194628+00:00"},{"alias_kind":"pith_short_8","alias_value":"2F4WIFWB","created_at":"2026-07-05T11:22:36.194628+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.31498","citing_title":"Scalable Inference-Time Annealing with Surrogate Likelihood Estimators","ref_index":40,"is_internal_anchor":false},{"citing_arxiv_id":"2509.03726","citing_title":"Energy-Weighted Flow Matching: Unlocking Continuous Normalizing Flows for Efficient and Scalable Boltzmann Sampling","ref_index":36,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5","json":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5.json","graph_json":"https://pith.science/api/pith-number/2F4WIFWB5WT24KVRRJVTJFOAL5/graph.json","events_json":"https://pith.science/api/pith-number/2F4WIFWB5WT24KVRRJVTJFOAL5/events.json","paper":"https://pith.science/paper/2F4WIFWB"},"agent_actions":{"view_html":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5","download_json":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5.json","view_paper":"https://pith.science/paper/2F4WIFWB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.19077&json=true","fetch_graph":"https://pith.science/api/pith-number/2F4WIFWB5WT24KVRRJVTJFOAL5/graph.json","fetch_events":"https://pith.science/api/pith-number/2F4WIFWB5WT24KVRRJVTJFOAL5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5/action/storage_attestation","attest_author":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5/action/author_attestation","sign_citation":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5/action/citation_signature","submit_replication":"https://pith.science/pith/2F4WIFWB5WT24KVRRJVTJFOAL5/action/replication_record"}},"created_at":"2026-07-05T11:22:36.194628+00:00","updated_at":"2026-07-05T11:22:36.194628+00:00"}