{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:642ZQDOEUU4DYYPZ33VGA5NVJH","short_pith_number":"pith:642ZQDOE","schema_version":"1.0","canonical_sha256":"f735980dc4a5383c61f9deea6075b549e9e5a6ec731dcc3b45e5a2ffce797727","source":{"kind":"arxiv","id":"2307.02037","version":3},"attestation_state":"computed","paper":{"title":"Reverse Diffusion Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"HanZe Dong, Tong Zhang, Xunpeng Huang, Yi-An Ma, Yifan Hao","submitted_at":"2023-07-05T05:42:03Z","abstract_excerpt":"We propose a Monte Carlo sampler from the reverse diffusion process. Unlike the practice of diffusion models, where the intermediary updates -- the score functions -- are learned with a neural network, we transform the score matching problem into a mean estimation one. By estimating the means of the regularized posterior distributions, we derive a novel Monte Carlo sampling algorithm called reverse diffusion Monte Carlo (rdMC), which is distinct from the Markov chain Monte Carlo (MCMC) methods. We determine the sample size from the error tolerance and the properties of the posterior distributi"},"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":"2307.02037","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-07-05T05:42:03Z","cross_cats_sorted":["cs.LG","math.OC"],"title_canon_sha256":"1f2997a8c462e52289c3bfd7c410d6cd7011d4be6645e6529a6b9a934b724f74","abstract_canon_sha256":"935c4b77263f6bc913a7b6d897ac54d51002ad91128d97177865feb45c0ae1d4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:55:22.876226Z","signature_b64":"zqRTQPcySJVCLNvfxc4L1QHsc/Kl7Lueh73H0cN07IR2dawgrCzfpw++fWAwfGtdn0qC/M3bmH/WtbN+mdcSBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f735980dc4a5383c61f9deea6075b549e9e5a6ec731dcc3b45e5a2ffce797727","last_reissued_at":"2026-07-05T07:55:22.875726Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:55:22.875726Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reverse Diffusion Monte Carlo","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","math.OC"],"primary_cat":"stat.ML","authors_text":"HanZe Dong, Tong Zhang, Xunpeng Huang, Yi-An Ma, Yifan Hao","submitted_at":"2023-07-05T05:42:03Z","abstract_excerpt":"We propose a Monte Carlo sampler from the reverse diffusion process. Unlike the practice of diffusion models, where the intermediary updates -- the score functions -- are learned with a neural network, we transform the score matching problem into a mean estimation one. By estimating the means of the regularized posterior distributions, we derive a novel Monte Carlo sampling algorithm called reverse diffusion Monte Carlo (rdMC), which is distinct from the Markov chain Monte Carlo (MCMC) methods. We determine the sample size from the error tolerance and the properties of the posterior distributi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02037","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/2307.02037/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":"2307.02037","created_at":"2026-07-05T07:55:22.875790+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02037v3","created_at":"2026-07-05T07:55:22.875790+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02037","created_at":"2026-07-05T07:55:22.875790+00:00"},{"alias_kind":"pith_short_12","alias_value":"642ZQDOEUU4D","created_at":"2026-07-05T07:55:22.875790+00:00"},{"alias_kind":"pith_short_16","alias_value":"642ZQDOEUU4DYYPZ","created_at":"2026-07-05T07:55:22.875790+00:00"},{"alias_kind":"pith_short_8","alias_value":"642ZQDOE","created_at":"2026-07-05T07:55:22.875790+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16520","citing_title":"Global Convergence of Sampling-Based Nonconvex Optimization through Diffusion-Style Smoothing","ref_index":106,"is_internal_anchor":false},{"citing_arxiv_id":"2602.20549","citing_title":"Sample-efficient evidence estimation of score based priors for model selection","ref_index":7,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH","json":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH.json","graph_json":"https://pith.science/api/pith-number/642ZQDOEUU4DYYPZ33VGA5NVJH/graph.json","events_json":"https://pith.science/api/pith-number/642ZQDOEUU4DYYPZ33VGA5NVJH/events.json","paper":"https://pith.science/paper/642ZQDOE"},"agent_actions":{"view_html":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH","download_json":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH.json","view_paper":"https://pith.science/paper/642ZQDOE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02037&json=true","fetch_graph":"https://pith.science/api/pith-number/642ZQDOEUU4DYYPZ33VGA5NVJH/graph.json","fetch_events":"https://pith.science/api/pith-number/642ZQDOEUU4DYYPZ33VGA5NVJH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH/action/storage_attestation","attest_author":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH/action/author_attestation","sign_citation":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH/action/citation_signature","submit_replication":"https://pith.science/pith/642ZQDOEUU4DYYPZ33VGA5NVJH/action/replication_record"}},"created_at":"2026-07-05T07:55:22.875790+00:00","updated_at":"2026-07-05T07:55:22.875790+00:00"}