{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:DPPVBZTNLIWFJAYWI36BIF2DD5","short_pith_number":"pith:DPPVBZTN","schema_version":"1.0","canonical_sha256":"1bdf50e66d5a2c54831646fc1417431f44fccbc3b06c43978ab53f5017d8717a","source":{"kind":"arxiv","id":"2502.04575","version":3},"attestation_state":"computed","paper":{"title":"Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","physics.comp-ph","stat.CO"],"primary_cat":"stat.ML","authors_text":"Molei Tao, Wei Guo, Yongxin Chen","submitted_at":"2025-02-07T00:05:28Z","abstract_excerpt":"Given an unnormalized probability density $\\pi\\propto\\mathrm{e}^{-V}$, estimating its normalizing constant $Z=\\int_{\\mathbb{R}^d}\\mathrm{e}^{-V(x)}\\mathrm{d}x$ or free energy $F=-\\log Z$ is a crucial problem in Bayesian statistics, statistical mechanics, and machine learning. It is challenging especially in high dimensions or when $\\pi$ is multimodal. To mitigate the high variance of conventional importance sampling estimators, annealing-based methods such as Jarzynski equality and annealed importance sampling are commonly adopted, yet their quantitative complexity guarantees remain largely un"},"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":"2502.04575","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2025-02-07T00:05:28Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","physics.comp-ph","stat.CO"],"title_canon_sha256":"9cacca24a0d6664ca7582e5659a7c58889ffa15cc3f1e5ddb12960acfecd94b6","abstract_canon_sha256":"74535d266f8515c08705e0f258ccc0a7a43e16fa22386bed09925095c3d364bc"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T01:04:52.009801Z","signature_b64":"z+B44r8Rtr2wrD0rEi/vmhOfvV7FGriamaxTUxlgkwUr5kwntGCrChpBGTVYZx5r38BAM0/HF9FEGIyIhTshAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1bdf50e66d5a2c54831646fc1417431f44fccbc3b06c43978ab53f5017d8717a","last_reissued_at":"2026-05-20T01:04:52.008944Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T01:04:52.008944Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Complexity Analysis of Normalizing Constant Estimation: from Jarzynski Equality to Annealed Importance Sampling and beyond","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","physics.comp-ph","stat.CO"],"primary_cat":"stat.ML","authors_text":"Molei Tao, Wei Guo, Yongxin Chen","submitted_at":"2025-02-07T00:05:28Z","abstract_excerpt":"Given an unnormalized probability density $\\pi\\propto\\mathrm{e}^{-V}$, estimating its normalizing constant $Z=\\int_{\\mathbb{R}^d}\\mathrm{e}^{-V(x)}\\mathrm{d}x$ or free energy $F=-\\log Z$ is a crucial problem in Bayesian statistics, statistical mechanics, and machine learning. It is challenging especially in high dimensions or when $\\pi$ is multimodal. To mitigate the high variance of conventional importance sampling estimators, annealing-based methods such as Jarzynski equality and annealed importance sampling are commonly adopted, yet their quantitative complexity guarantees remain largely un"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.04575","kind":"arxiv","version":3},"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/2502.04575/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":"2502.04575","created_at":"2026-05-20T01:04:52.009056+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.04575v3","created_at":"2026-05-20T01:04:52.009056+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.04575","created_at":"2026-05-20T01:04:52.009056+00:00"},{"alias_kind":"pith_short_12","alias_value":"DPPVBZTNLIWF","created_at":"2026-05-20T01:04:52.009056+00:00"},{"alias_kind":"pith_short_16","alias_value":"DPPVBZTNLIWFJAYW","created_at":"2026-05-20T01:04:52.009056+00:00"},{"alias_kind":"pith_short_8","alias_value":"DPPVBZTN","created_at":"2026-05-20T01:04:52.009056+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2602.20549","citing_title":"Sample-efficient evidence estimation of score based priors for model selection","ref_index":6,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5","json":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5.json","graph_json":"https://pith.science/api/pith-number/DPPVBZTNLIWFJAYWI36BIF2DD5/graph.json","events_json":"https://pith.science/api/pith-number/DPPVBZTNLIWFJAYWI36BIF2DD5/events.json","paper":"https://pith.science/paper/DPPVBZTN"},"agent_actions":{"view_html":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5","download_json":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5.json","view_paper":"https://pith.science/paper/DPPVBZTN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.04575&json=true","fetch_graph":"https://pith.science/api/pith-number/DPPVBZTNLIWFJAYWI36BIF2DD5/graph.json","fetch_events":"https://pith.science/api/pith-number/DPPVBZTNLIWFJAYWI36BIF2DD5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5/action/storage_attestation","attest_author":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5/action/author_attestation","sign_citation":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5/action/citation_signature","submit_replication":"https://pith.science/pith/DPPVBZTNLIWFJAYWI36BIF2DD5/action/replication_record"}},"created_at":"2026-05-20T01:04:52.009056+00:00","updated_at":"2026-05-20T01:04:52.009056+00:00"}