{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JR2T4MNGAD6ZBW3FWHUWEZSPM6","short_pith_number":"pith:JR2T4MNG","schema_version":"1.0","canonical_sha256":"4c753e31a600fd90db65b1e962664f6785be078503a9bc5396774d23c6dcef12","source":{"kind":"arxiv","id":"2211.12343","version":4},"attestation_state":"computed","paper":{"title":"Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Xiangming Meng, Yoshiyuki Kabashima","submitted_at":"2022-11-20T01:09:49Z","abstract_excerpt":"With the rapid development of diffusion models and flow-based generative models, there has been a surge of interests in solving noisy linear inverse problems, e.g., super-resolution, deblurring, denoising, colorization, etc, with generative models. However, while remarkable reconstruction performances have been achieved, their inference time is typically too slow since most of them rely on the seminal diffusion posterior sampling (DPS) framework and thus to approximate the intractable likelihood score, time-consuming gradient calculation through back-propagation is needed. To address this issu"},"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":"2211.12343","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-11-20T01:09:49Z","cross_cats_sorted":["cs.CV","cs.IT","math.IT","stat.ML"],"title_canon_sha256":"3fdea7a2ec84433c6f0c8d11e52b71d34e84309dea5536062c99cb4758e0ea1b","abstract_canon_sha256":"de06c69ab6ea0db9dba05077554e42f39e3a5d2f7e989b44b24e63f6cdd7254a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:58.233040Z","signature_b64":"ZIktSP5jRl9U91bYE8h17YH0RiRX6cDtxDDf1kL249CMKqpFrcVQ/7ZuV9JKV/0nFu+goOuwgrgQVw9tDwTMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c753e31a600fd90db65b1e962664f6785be078503a9bc5396774d23c6dcef12","last_reissued_at":"2026-07-05T09:22:58.232619Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:58.232619Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion Model Based Posterior Sampling for Noisy Linear Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.IT","math.IT","stat.ML"],"primary_cat":"cs.LG","authors_text":"Xiangming Meng, Yoshiyuki Kabashima","submitted_at":"2022-11-20T01:09:49Z","abstract_excerpt":"With the rapid development of diffusion models and flow-based generative models, there has been a surge of interests in solving noisy linear inverse problems, e.g., super-resolution, deblurring, denoising, colorization, etc, with generative models. However, while remarkable reconstruction performances have been achieved, their inference time is typically too slow since most of them rely on the seminal diffusion posterior sampling (DPS) framework and thus to approximate the intractable likelihood score, time-consuming gradient calculation through back-propagation is needed. To address this issu"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.12343","kind":"arxiv","version":4},"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/2211.12343/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":"2211.12343","created_at":"2026-07-05T09:22:58.232677+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.12343v4","created_at":"2026-07-05T09:22:58.232677+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.12343","created_at":"2026-07-05T09:22:58.232677+00:00"},{"alias_kind":"pith_short_12","alias_value":"JR2T4MNGAD6Z","created_at":"2026-07-05T09:22:58.232677+00:00"},{"alias_kind":"pith_short_16","alias_value":"JR2T4MNGAD6ZBW3F","created_at":"2026-07-05T09:22:58.232677+00:00"},{"alias_kind":"pith_short_8","alias_value":"JR2T4MNG","created_at":"2026-07-05T09:22:58.232677+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.15643","citing_title":"An Unconditional Representation of the Conditional Score in Infinite-Dimensional Linear Inverse Problems","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.18325","citing_title":"Mixture-of-Experts Diffusion Models for Adaptive Massive MIMO Channel Estimation via Variational Bayesian Inference","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":88,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11311","citing_title":"Couple to Control: Joint Initial Noise Design in Diffusion Models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2604.09039","citing_title":"Diffusion Inpainting MIMO-OFDM Channels with Limited Noisy Observations","ref_index":26,"is_internal_anchor":false},{"citing_arxiv_id":"2604.20494","citing_title":"Near-Field Wideband Channel Estimation for XL-MIMO Systems via Denoising Diffusion Model","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6","json":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6.json","graph_json":"https://pith.science/api/pith-number/JR2T4MNGAD6ZBW3FWHUWEZSPM6/graph.json","events_json":"https://pith.science/api/pith-number/JR2T4MNGAD6ZBW3FWHUWEZSPM6/events.json","paper":"https://pith.science/paper/JR2T4MNG"},"agent_actions":{"view_html":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6","download_json":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6.json","view_paper":"https://pith.science/paper/JR2T4MNG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.12343&json=true","fetch_graph":"https://pith.science/api/pith-number/JR2T4MNGAD6ZBW3FWHUWEZSPM6/graph.json","fetch_events":"https://pith.science/api/pith-number/JR2T4MNGAD6ZBW3FWHUWEZSPM6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6/action/storage_attestation","attest_author":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6/action/author_attestation","sign_citation":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6/action/citation_signature","submit_replication":"https://pith.science/pith/JR2T4MNGAD6ZBW3FWHUWEZSPM6/action/replication_record"}},"created_at":"2026-07-05T09:22:58.232677+00:00","updated_at":"2026-07-05T09:22:58.232677+00:00"}