{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GD7DSRBIH464HHXZDQZHBORKC5","short_pith_number":"pith:GD7DSRBI","schema_version":"1.0","canonical_sha256":"30fe3944283f3dc39ef91c3270ba2a175330606a622d1bff3ef7042f64469190","source":{"kind":"arxiv","id":"2512.08022","version":2},"attestation_state":"computed","paper":{"title":"Provable Diffusion Posterior Sampling for Bayesian Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chenguang Duan, Cheng Yuan, Jerry Zhijian Yang, Jinyuan Chang, Ruoxuan Li, Yuling Jiao","submitted_at":"2025-12-08T20:34:05Z","abstract_excerpt":"We propose a novel diffusion-based posterior sampling method within a plug-and-play framework. Our approach constructs a probability transport from an easy-to-sample distribution to the target posterior via a diffusion process. To initialize the sampler efficiently, we introduce a warm-start strategy for the particles. The posterior score is then approximated using a Monte Carlo estimator in which samples are generated via Langevin dynamics, avoiding the heuristic approximations prevalent in prior work. The score function driving the Langevin dynamics is learned from data, enabling the model t"},"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":"2512.08022","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-12-08T20:34:05Z","cross_cats_sorted":["cs.LG","cs.NA","math.NA","math.PR","math.ST","stat.TH"],"title_canon_sha256":"6c9c0cab1289dc21404efc3fadae2b81b8cd8550e73299782a6b27119a7ca5d4","abstract_canon_sha256":"09e2d9df38e7b703270333eba1c305795dd5b29b30ae0eaf2c3fdcfc09f111bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-03T01:27:06.843854Z","signature_b64":"YkiFsx+h21z9gAG5hKTpXXjSV3d6hiPOx8OBm1n1e0ZU2p6KCXcQyEXxg1BL0YwsAWVHgr3YxkGS3jsZKPGvCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"30fe3944283f3dc39ef91c3270ba2a175330606a622d1bff3ef7042f64469190","last_reissued_at":"2026-08-03T01:27:06.841993Z","signature_status":"signed_v1","first_computed_at":"2026-08-03T01:27:06.841993Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Provable Diffusion Posterior Sampling for Bayesian Inversion","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.NA","math.NA","math.PR","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Chenguang Duan, Cheng Yuan, Jerry Zhijian Yang, Jinyuan Chang, Ruoxuan Li, Yuling Jiao","submitted_at":"2025-12-08T20:34:05Z","abstract_excerpt":"We propose a novel diffusion-based posterior sampling method within a plug-and-play framework. Our approach constructs a probability transport from an easy-to-sample distribution to the target posterior via a diffusion process. To initialize the sampler efficiently, we introduce a warm-start strategy for the particles. The posterior score is then approximated using a Monte Carlo estimator in which samples are generated via Langevin dynamics, avoiding the heuristic approximations prevalent in prior work. The score function driving the Langevin dynamics is learned from data, enabling the model t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2512.08022","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2512.08022/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":"2512.08022","created_at":"2026-08-03T01:27:06.843046+00:00"},{"alias_kind":"arxiv_version","alias_value":"2512.08022v2","created_at":"2026-08-03T01:27:06.843046+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2512.08022","created_at":"2026-08-03T01:27:06.843046+00:00"},{"alias_kind":"pith_short_12","alias_value":"GD7DSRBIH464","created_at":"2026-08-03T01:27:06.843046+00:00"},{"alias_kind":"pith_short_16","alias_value":"GD7DSRBIH464HHXZ","created_at":"2026-08-03T01:27:06.843046+00:00"},{"alias_kind":"pith_short_8","alias_value":"GD7DSRBI","created_at":"2026-08-03T01:27:06.843046+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":4,"sample":[{"citing_arxiv_id":"2606.06236","citing_title":"Tracing the Oracle: Improving Diffusion Timestep Scheduling for 3D CT Reconstruction","ref_index":19,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14267","citing_title":"Image Restoration via Diffusion Models with Dynamic Resolution","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":81,"is_internal_anchor":true},{"citing_arxiv_id":"2604.21849","citing_title":"Beyond Expected Information Gain: Stable Bayesian Optimal Experimental Design with Integral Probability Metrics and Plug-and-Play Extensions","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5","json":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5.json","graph_json":"https://pith.science/api/pith-number/GD7DSRBIH464HHXZDQZHBORKC5/graph.json","events_json":"https://pith.science/api/pith-number/GD7DSRBIH464HHXZDQZHBORKC5/events.json","paper":"https://pith.science/paper/GD7DSRBI"},"agent_actions":{"view_html":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5","download_json":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5.json","view_paper":"https://pith.science/paper/GD7DSRBI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2512.08022&json=true","fetch_graph":"https://pith.science/api/pith-number/GD7DSRBIH464HHXZDQZHBORKC5/graph.json","fetch_events":"https://pith.science/api/pith-number/GD7DSRBIH464HHXZDQZHBORKC5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5/action/storage_attestation","attest_author":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5/action/author_attestation","sign_citation":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5/action/citation_signature","submit_replication":"https://pith.science/pith/GD7DSRBIH464HHXZDQZHBORKC5/action/replication_record"}},"created_at":"2026-08-03T01:27:06.843046+00:00","updated_at":"2026-08-03T01:27:06.843046+00:00"}