{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:UKKIVNV3MLR6GDKXADFU5PUSTI","short_pith_number":"pith:UKKIVNV3","schema_version":"1.0","canonical_sha256":"a2948ab6bb62e3e30d5700cb4ebe929a060d83daa7a5b0879debddb32508b0aa","source":{"kind":"arxiv","id":"2409.07323","version":1},"attestation_state":"computed","paper":{"title":"Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fengzhe Zhang, Javier Antor\\'an, Jiajun He, Jos\\'e Miguel Hern\\'andez-Lobato, Laurence I. Midgley","submitted_at":"2024-09-11T15:02:52Z","abstract_excerpt":"Diffusion models have shown promising potential for advancing Boltzmann Generators. However, two critical challenges persist: (1) inherent errors in samples due to model imperfections, and (2) the requirement of hundreds of functional evaluations (NFEs) to achieve high-quality samples. While existing solutions like importance sampling and distillation address these issues separately, they are often incompatible, as most distillation models lack the necessary density information for importance sampling. This paper introduces a novel sampling method that effectively combines Consistency Models ("},"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":"2409.07323","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-09-11T15:02:52Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"82ad9d775ecbe26bdd28fb7d41f30a2f0f2cbf57d6f97c6125c9364dc73c3e10","abstract_canon_sha256":"95709d64ff5fa30306c8d9e33ac4d21846737ed56ffb2d14b73c87be9b41ef65"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:05:56.273675Z","signature_b64":"iM6sYSWt022vPnNNkkUyUvE1qpsK8qACVzuGdbnmKoVHPSoCCrj2ba9dWwvTEGSjxV/hJ98g5v364X2hfARsAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2948ab6bb62e3e30d5700cb4ebe929a060d83daa7a5b0879debddb32508b0aa","last_reissued_at":"2026-07-05T09:05:56.273296Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:05:56.273296Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Efficient and Unbiased Sampling of Boltzmann Distributions via Consistency Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Fengzhe Zhang, Javier Antor\\'an, Jiajun He, Jos\\'e Miguel Hern\\'andez-Lobato, Laurence I. Midgley","submitted_at":"2024-09-11T15:02:52Z","abstract_excerpt":"Diffusion models have shown promising potential for advancing Boltzmann Generators. However, two critical challenges persist: (1) inherent errors in samples due to model imperfections, and (2) the requirement of hundreds of functional evaluations (NFEs) to achieve high-quality samples. While existing solutions like importance sampling and distillation address these issues separately, they are often incompatible, as most distillation models lack the necessary density information for importance sampling. This paper introduces a novel sampling method that effectively combines Consistency Models ("},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.07323","kind":"arxiv","version":1},"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/2409.07323/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":"2409.07323","created_at":"2026-07-05T09:05:56.273364+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.07323v1","created_at":"2026-07-05T09:05:56.273364+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.07323","created_at":"2026-07-05T09:05:56.273364+00:00"},{"alias_kind":"pith_short_12","alias_value":"UKKIVNV3MLR6","created_at":"2026-07-05T09:05:56.273364+00:00"},{"alias_kind":"pith_short_16","alias_value":"UKKIVNV3MLR6GDKX","created_at":"2026-07-05T09:05:56.273364+00:00"},{"alias_kind":"pith_short_8","alias_value":"UKKIVNV3","created_at":"2026-07-05T09:05:56.273364+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.17808","citing_title":"A Unified Framework for Data-Free One-Step Sampling via Wasserstein Gradient Flows","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI","json":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI.json","graph_json":"https://pith.science/api/pith-number/UKKIVNV3MLR6GDKXADFU5PUSTI/graph.json","events_json":"https://pith.science/api/pith-number/UKKIVNV3MLR6GDKXADFU5PUSTI/events.json","paper":"https://pith.science/paper/UKKIVNV3"},"agent_actions":{"view_html":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI","download_json":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI.json","view_paper":"https://pith.science/paper/UKKIVNV3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.07323&json=true","fetch_graph":"https://pith.science/api/pith-number/UKKIVNV3MLR6GDKXADFU5PUSTI/graph.json","fetch_events":"https://pith.science/api/pith-number/UKKIVNV3MLR6GDKXADFU5PUSTI/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI/action/storage_attestation","attest_author":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI/action/author_attestation","sign_citation":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI/action/citation_signature","submit_replication":"https://pith.science/pith/UKKIVNV3MLR6GDKXADFU5PUSTI/action/replication_record"}},"created_at":"2026-07-05T09:05:56.273364+00:00","updated_at":"2026-07-05T09:05:56.273364+00:00"}