{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:3YGSJGZLX3MVFRZ2QLLULJ65K6","short_pith_number":"pith:3YGSJGZL","schema_version":"1.0","canonical_sha256":"de0d249b2bbed952c73a82d745a7dd57a94b22d16cfac6c609ac26cad15f2323","source":{"kind":"arxiv","id":"2410.04479","version":2},"attestation_state":"computed","paper":{"title":"SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Cheng-Han Huang, Ismail Alkhouri, Jimmy Dai, Qing Qu, Rongrong Wang, Saiprasad Ravishankar, Shijun Liang","submitted_at":"2024-10-06T13:39:36Z","abstract_excerpt":"Diffusion models (DMs) are a class of generative models that allow sampling from a distribution learned over a training set. When applied to solving inverse problems, the reverse sampling steps are modified to approximately sample from a measurement-conditioned distribution. However, these modifications may be unsuitable for certain settings (e.g., presence of measurement noise) and non-linear tasks, as they often struggle to correct errors from earlier steps and generally require a large number of optimization and/or sampling steps. To address these challenges, we state three conditions for a"},"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":"2410.04479","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"eess.IV","submitted_at":"2024-10-06T13:39:36Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"9dc8842c545df674e1f922a31547e3aae5e0854a07accabefdc75ee8ed530852","abstract_canon_sha256":"d91440bc3a9972645c76e48b75869df424765a7a7809dbc4ae4cdf8035b72ce3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:43.524062Z","signature_b64":"kkScqktUhKIR0PP0Fdo572AuUl6F57O5js7mTfffqy3PxsU1rl1+elgOkSnxm0skigUwisVJNIs2HWTpSQ49AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"de0d249b2bbed952c73a82d745a7dd57a94b22d16cfac6c609ac26cad15f2323","last_reissued_at":"2026-07-05T11:09:43.523410Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:43.523410Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SITCOM: Step-wise Triple-Consistent Diffusion Sampling for Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"eess.IV","authors_text":"Cheng-Han Huang, Ismail Alkhouri, Jimmy Dai, Qing Qu, Rongrong Wang, Saiprasad Ravishankar, Shijun Liang","submitted_at":"2024-10-06T13:39:36Z","abstract_excerpt":"Diffusion models (DMs) are a class of generative models that allow sampling from a distribution learned over a training set. When applied to solving inverse problems, the reverse sampling steps are modified to approximately sample from a measurement-conditioned distribution. However, these modifications may be unsuitable for certain settings (e.g., presence of measurement noise) and non-linear tasks, as they often struggle to correct errors from earlier steps and generally require a large number of optimization and/or sampling steps. To address these challenges, we state three conditions for a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.04479","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/2410.04479/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":"2410.04479","created_at":"2026-07-05T11:09:43.523522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.04479v2","created_at":"2026-07-05T11:09:43.523522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.04479","created_at":"2026-07-05T11:09:43.523522+00:00"},{"alias_kind":"pith_short_12","alias_value":"3YGSJGZLX3MV","created_at":"2026-07-05T11:09:43.523522+00:00"},{"alias_kind":"pith_short_16","alias_value":"3YGSJGZLX3MVFRZ2","created_at":"2026-07-05T11:09:43.523522+00:00"},{"alias_kind":"pith_short_8","alias_value":"3YGSJGZL","created_at":"2026-07-05T11:09:43.523522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13278","citing_title":"Proximal-Based Generative Modeling for Bayesian Inverse Problems","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6","json":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6.json","graph_json":"https://pith.science/api/pith-number/3YGSJGZLX3MVFRZ2QLLULJ65K6/graph.json","events_json":"https://pith.science/api/pith-number/3YGSJGZLX3MVFRZ2QLLULJ65K6/events.json","paper":"https://pith.science/paper/3YGSJGZL"},"agent_actions":{"view_html":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6","download_json":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6.json","view_paper":"https://pith.science/paper/3YGSJGZL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.04479&json=true","fetch_graph":"https://pith.science/api/pith-number/3YGSJGZLX3MVFRZ2QLLULJ65K6/graph.json","fetch_events":"https://pith.science/api/pith-number/3YGSJGZLX3MVFRZ2QLLULJ65K6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6/action/storage_attestation","attest_author":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6/action/author_attestation","sign_citation":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6/action/citation_signature","submit_replication":"https://pith.science/pith/3YGSJGZLX3MVFRZ2QLLULJ65K6/action/replication_record"}},"created_at":"2026-07-05T11:09:43.523522+00:00","updated_at":"2026-07-05T11:09:43.523522+00:00"}