{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:GJRCYYHODJZID7UBFP4IJAFXCH","short_pith_number":"pith:GJRCYYHO","schema_version":"1.0","canonical_sha256":"32622c60ee1a7281fe812bf88480b711caf62b7e2af5af201bbf4116bf4dbe66","source":{"kind":"arxiv","id":"2409.08551","version":1},"attestation_state":"computed","paper":{"title":"Think Twice Before You Act: Improving Inverse Problem Solving With MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Haoxin Zheng, Ruiqi Gao, Yasi Zhang, Yaxuan Zhu, Ying Nian Wu, Zehao Dou","submitted_at":"2024-09-13T06:10:54Z","abstract_excerpt":"Recent studies demonstrate that diffusion models can serve as a strong prior for solving inverse problems. A prominent example is Diffusion Posterior Sampling (DPS), which approximates the posterior distribution of data given the measure using Tweedie's formula. Despite the merits of being versatile in solving various inverse problems without re-training, the performance of DPS is hindered by the fact that this posterior approximation can be inaccurate especially for high noise levels. Therefore, we propose \\textbf{D}iffusion \\textbf{P}osterior \\textbf{MC}MC (\\textbf{DPMC}), a novel inference "},"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":"2409.08551","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2024-09-13T06:10:54Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"fce2df252bc1193f024d1c84ade93429dc2ee6366a9c59a9f7b96b3ef6364ed3","abstract_canon_sha256":"3836aa47d624be0f44eb3a23d0a4f28b65b214483755169c3492ece562806e5e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:06:33.025675Z","signature_b64":"w+BRJmNInVRPfVUrpZx22/s1I+RyIN6pPLOrH0VS93ppDTNuoj2nZYIyf6/73e7jNjzsLs2yQkKd3bJRqEbJBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"32622c60ee1a7281fe812bf88480b711caf62b7e2af5af201bbf4116bf4dbe66","last_reissued_at":"2026-07-05T09:06:33.025246Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:06:33.025246Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Think Twice Before You Act: Improving Inverse Problem Solving With MCMC","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Haoxin Zheng, Ruiqi Gao, Yasi Zhang, Yaxuan Zhu, Ying Nian Wu, Zehao Dou","submitted_at":"2024-09-13T06:10:54Z","abstract_excerpt":"Recent studies demonstrate that diffusion models can serve as a strong prior for solving inverse problems. A prominent example is Diffusion Posterior Sampling (DPS), which approximates the posterior distribution of data given the measure using Tweedie's formula. Despite the merits of being versatile in solving various inverse problems without re-training, the performance of DPS is hindered by the fact that this posterior approximation can be inaccurate especially for high noise levels. Therefore, we propose \\textbf{D}iffusion \\textbf{P}osterior \\textbf{MC}MC (\\textbf{DPMC}), a novel inference "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.08551","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/2409.08551/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":"2409.08551","created_at":"2026-07-05T09:06:33.025303+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.08551v1","created_at":"2026-07-05T09:06:33.025303+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.08551","created_at":"2026-07-05T09:06:33.025303+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJRCYYHODJZI","created_at":"2026-07-05T09:06:33.025303+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJRCYYHODJZID7UB","created_at":"2026-07-05T09:06:33.025303+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJRCYYHO","created_at":"2026-07-05T09:06:33.025303+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.21066","citing_title":"Optimizing Diffusion Priors in Image Reconstruction from a Single Observation","ref_index":41,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH","json":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH.json","graph_json":"https://pith.science/api/pith-number/GJRCYYHODJZID7UBFP4IJAFXCH/graph.json","events_json":"https://pith.science/api/pith-number/GJRCYYHODJZID7UBFP4IJAFXCH/events.json","paper":"https://pith.science/paper/GJRCYYHO"},"agent_actions":{"view_html":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH","download_json":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH.json","view_paper":"https://pith.science/paper/GJRCYYHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.08551&json=true","fetch_graph":"https://pith.science/api/pith-number/GJRCYYHODJZID7UBFP4IJAFXCH/graph.json","fetch_events":"https://pith.science/api/pith-number/GJRCYYHODJZID7UBFP4IJAFXCH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH/action/storage_attestation","attest_author":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH/action/author_attestation","sign_citation":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH/action/citation_signature","submit_replication":"https://pith.science/pith/GJRCYYHODJZID7UBFP4IJAFXCH/action/replication_record"}},"created_at":"2026-07-05T09:06:33.025303+00:00","updated_at":"2026-07-05T09:06:33.025303+00:00"}