{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2018:GZLFDPRBZIS5UNXJOV3VANMWID","short_pith_number":"pith:GZLFDPRB","schema_version":"1.0","canonical_sha256":"365651be21ca25da36e9757750359640c8b52e0d18dce318e9fa5853355621ed","source":{"kind":"arxiv","id":"1812.00793","version":3},"attestation_state":"computed","paper":{"title":"Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition","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":"2018-11-29T19:27:33Z","abstract_excerpt":"A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). One prevalent example of this is sampling posteriors in parametric distributions, such as latent-variable generative models. However sampling (even very approximately) can be #P-hard.\n  Classical results going back to Bakry and \\'Emery (1985) on sampling focus on log-concave distributions, and show a natural Markov chain called Langevin diffusion mixes in polynomial time. However, all log-concave distributions are uni-modal, while in pra"},"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":"1812.00793","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-11-29T19:27:33Z","cross_cats_sorted":["cs.DS","math.PR","stat.ML"],"title_canon_sha256":"900f8a6c3c4c267d15977cf4d2580bf990642fef534a9dea57c1f084462c765a","abstract_canon_sha256":"f7780d8b0292af9f5eec3658b97a5a2d08994ba3ce982d9cbc1add19a59eefe0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:34:03.779413Z","signature_b64":"2JZaDidUm3MiIXyomA6HwSkcnp6kS6EOhADKIdcoOdttEBe+t7vNdVgT0htYuZdDVod+7fl4UfaISgk4yVdZDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"365651be21ca25da36e9757750359640c8b52e0d18dce318e9fa5853355621ed","last_reissued_at":"2026-07-05T01:34:03.779005Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:34:03.779005Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Simulated Tempering Langevin Monte Carlo II: An Improved Proof using Soft Markov Chain Decomposition","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":"2018-11-29T19:27:33Z","abstract_excerpt":"A key task in Bayesian machine learning is sampling from distributions that are only specified up to a partition function (i.e., constant of proportionality). One prevalent example of this is sampling posteriors in parametric distributions, such as latent-variable generative models. However sampling (even very approximately) can be #P-hard.\n  Classical results going back to Bakry and \\'Emery (1985) on sampling focus on log-concave distributions, and show a natural Markov chain called Langevin diffusion mixes in polynomial time. However, all log-concave distributions are uni-modal, while in pra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1812.00793","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/1812.00793/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":"1812.00793","created_at":"2026-07-05T01:34:03.779060+00:00"},{"alias_kind":"arxiv_version","alias_value":"1812.00793v3","created_at":"2026-07-05T01:34:03.779060+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1812.00793","created_at":"2026-07-05T01:34:03.779060+00:00"},{"alias_kind":"pith_short_12","alias_value":"GZLFDPRBZIS5","created_at":"2026-07-05T01:34:03.779060+00:00"},{"alias_kind":"pith_short_16","alias_value":"GZLFDPRBZIS5UNXJ","created_at":"2026-07-05T01:34:03.779060+00:00"},{"alias_kind":"pith_short_8","alias_value":"GZLFDPRB","created_at":"2026-07-05T01:34:03.779060+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.11361","citing_title":"The tractability landscape of diffusion alignment: regularization, rewards, and computational primitives","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2605.07950","citing_title":"Slowly Annealed Langevin Dynamics: Theory and Applications to Training-Free Guided Generation","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2604.04823","citing_title":"Rapid convergence of tempering chains to multimodal Gibbs measures","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID","json":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID.json","graph_json":"https://pith.science/api/pith-number/GZLFDPRBZIS5UNXJOV3VANMWID/graph.json","events_json":"https://pith.science/api/pith-number/GZLFDPRBZIS5UNXJOV3VANMWID/events.json","paper":"https://pith.science/paper/GZLFDPRB"},"agent_actions":{"view_html":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID","download_json":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID.json","view_paper":"https://pith.science/paper/GZLFDPRB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1812.00793&json=true","fetch_graph":"https://pith.science/api/pith-number/GZLFDPRBZIS5UNXJOV3VANMWID/graph.json","fetch_events":"https://pith.science/api/pith-number/GZLFDPRBZIS5UNXJOV3VANMWID/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID/action/storage_attestation","attest_author":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID/action/author_attestation","sign_citation":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID/action/citation_signature","submit_replication":"https://pith.science/pith/GZLFDPRBZIS5UNXJOV3VANMWID/action/replication_record"}},"created_at":"2026-07-05T01:34:03.779060+00:00","updated_at":"2026-07-05T01:34:03.779060+00:00"}