{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:RKRKPBGBZRSDQKVIHMJSY3ZTOE","short_pith_number":"pith:RKRKPBGB","schema_version":"1.0","canonical_sha256":"8aa2a784c1cc64382aa83b132c6f33711f309a1976a210a9a73620863b94de97","source":{"kind":"arxiv","id":"1710.02736","version":2},"attestation_state":"computed","paper":{"title":"Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrej Risteski, Holden Lee, Rong Ge","submitted_at":"2017-10-07T19:55:51Z","abstract_excerpt":"A key task in Bayesian statistics is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). However, without any assumptions, sampling (even approximately) can be #P-hard, and few works have provided \"beyond worst-case\" guarantees for such settings.\n  For log-concave distributions, classical results going back to Bakry and \\'Emery (1985) show that natural continuous-time Markov chains called Langevin diffusions mix in polynomial time. The most salient feature of log-concavity violated in practice is uni-modality: commonly, the distri"},"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":"1710.02736","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2017-10-07T19:55:51Z","cross_cats_sorted":["cs.DS","math.PR","stat.ML"],"title_canon_sha256":"b58916b38d29fa426fe5c8b61f5739e79c80a01890b69be197adb9ea4496cd64","abstract_canon_sha256":"a86c455634c71ecdefe4356585977d81f5118d493fd3ec0632e43d75f05220b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:59:33.135571Z","signature_b64":"LgPyWNGB3utnOlioFBZ5Ozbtp0fQ4WP002XEFw0DL/CmBAvXiqAMLxzrG63kUyYgb3XZcOJQBTN7uL1GqcKADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8aa2a784c1cc64382aa83b132c6f33711f309a1976a210a9a73620863b94de97","last_reissued_at":"2026-05-17T23:59:33.134724Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:59:33.134724Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Beyond Log-concavity: Provable Guarantees for Sampling Multi-modal Distributions using Simulated Tempering Langevin Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DS","math.PR","stat.ML"],"primary_cat":"cs.LG","authors_text":"Andrej Risteski, Holden Lee, Rong Ge","submitted_at":"2017-10-07T19:55:51Z","abstract_excerpt":"A key task in Bayesian statistics is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). However, without any assumptions, sampling (even approximately) can be #P-hard, and few works have provided \"beyond worst-case\" guarantees for such settings.\n  For log-concave distributions, classical results going back to Bakry and \\'Emery (1985) show that natural continuous-time Markov chains called Langevin diffusions mix in polynomial time. The most salient feature of log-concavity violated in practice is uni-modality: commonly, the distri"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1710.02736","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":""},"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":"1710.02736","created_at":"2026-05-17T23:59:33.134890+00:00"},{"alias_kind":"arxiv_version","alias_value":"1710.02736v2","created_at":"2026-05-17T23:59:33.134890+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1710.02736","created_at":"2026-05-17T23:59:33.134890+00:00"},{"alias_kind":"pith_short_12","alias_value":"RKRKPBGBZRSD","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_16","alias_value":"RKRKPBGBZRSDQKVI","created_at":"2026-05-18T12:31:39.905425+00:00"},{"alias_kind":"pith_short_8","alias_value":"RKRKPBGB","created_at":"2026-05-18T12:31:39.905425+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":80,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE","json":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE.json","graph_json":"https://pith.science/api/pith-number/RKRKPBGBZRSDQKVIHMJSY3ZTOE/graph.json","events_json":"https://pith.science/api/pith-number/RKRKPBGBZRSDQKVIHMJSY3ZTOE/events.json","paper":"https://pith.science/paper/RKRKPBGB"},"agent_actions":{"view_html":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE","download_json":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE.json","view_paper":"https://pith.science/paper/RKRKPBGB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1710.02736&json=true","fetch_graph":"https://pith.science/api/pith-number/RKRKPBGBZRSDQKVIHMJSY3ZTOE/graph.json","fetch_events":"https://pith.science/api/pith-number/RKRKPBGBZRSDQKVIHMJSY3ZTOE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE/action/storage_attestation","attest_author":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE/action/author_attestation","sign_citation":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE/action/citation_signature","submit_replication":"https://pith.science/pith/RKRKPBGBZRSDQKVIHMJSY3ZTOE/action/replication_record"}},"created_at":"2026-05-17T23:59:33.134890+00:00","updated_at":"2026-05-17T23:59:33.134890+00:00"}