{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:F2HCGQSJGP6SZLZ5W44VOJ7H7B","short_pith_number":"pith:F2HCGQSJ","schema_version":"1.0","canonical_sha256":"2e8e23424933fd2caf3db7395727e7f86d9fa44231a5170d484a830022f7c6b6","source":{"kind":"arxiv","id":"2206.09012","version":3},"attestation_state":"computed","paper":{"title":"Diffusion models as plug-and-play priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alexandros Graikos, Dimitris Samaras, Nebojsa Jojic, Nikolay Malkin","submitted_at":"2022-06-17T21:11:36Z","abstract_excerpt":"We consider the problem of inferring high-dimensional data $\\mathbf{x}$ in a model that consists of a prior $p(\\mathbf{x})$ and an auxiliary differentiable constraint $c(\\mathbf{x},\\mathbf{y})$ on $x$ given some additional information $\\mathbf{y}$. In this paper, the prior is an independently trained denoising diffusion generative model. The auxiliary constraint is expected to have a differentiable form, but can come from diverse sources. The possibility of such inference turns diffusion models into plug-and-play modules, thereby allowing a range of potential applications in adapting models to"},"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":"2206.09012","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2022-06-17T21:11:36Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"56fb2fdbd3835fd4ca30619c3790e3aace6f5ca09158864127fd17ccc3012059","abstract_canon_sha256":"fb519543957c97df98a357b327b592ee5807e668330b048af02d4a5dad8939ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:31:15.101896Z","signature_b64":"8TFOYWbzqYvZO4WFPZowemlX1UQLSU0Lhi6fwaDFHbHSHUxDI1nXKtyN7ky5jOEIqH/lGoQWIG7yukXHvYOcAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2e8e23424933fd2caf3db7395727e7f86d9fa44231a5170d484a830022f7c6b6","last_reissued_at":"2026-07-05T05:31:15.101458Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:31:15.101458Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Diffusion models as plug-and-play priors","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.LG","authors_text":"Alexandros Graikos, Dimitris Samaras, Nebojsa Jojic, Nikolay Malkin","submitted_at":"2022-06-17T21:11:36Z","abstract_excerpt":"We consider the problem of inferring high-dimensional data $\\mathbf{x}$ in a model that consists of a prior $p(\\mathbf{x})$ and an auxiliary differentiable constraint $c(\\mathbf{x},\\mathbf{y})$ on $x$ given some additional information $\\mathbf{y}$. In this paper, the prior is an independently trained denoising diffusion generative model. The auxiliary constraint is expected to have a differentiable form, but can come from diverse sources. The possibility of such inference turns diffusion models into plug-and-play modules, thereby allowing a range of potential applications in adapting models to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.09012","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/2206.09012/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":"2206.09012","created_at":"2026-07-05T05:31:15.101521+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.09012v3","created_at":"2026-07-05T05:31:15.101521+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.09012","created_at":"2026-07-05T05:31:15.101521+00:00"},{"alias_kind":"pith_short_12","alias_value":"F2HCGQSJGP6S","created_at":"2026-07-05T05:31:15.101521+00:00"},{"alias_kind":"pith_short_16","alias_value":"F2HCGQSJGP6SZLZ5","created_at":"2026-07-05T05:31:15.101521+00:00"},{"alias_kind":"pith_short_8","alias_value":"F2HCGQSJ","created_at":"2026-07-05T05:31:15.101521+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2510.21697","citing_title":"Visual Diffusion Models are Geometric Solvers","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10830","citing_title":"Predicting 3D structure by latent posterior sampling","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2209.14988","citing_title":"DreamFusion: Text-to-3D using 2D Diffusion","ref_index":101,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B","json":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B.json","graph_json":"https://pith.science/api/pith-number/F2HCGQSJGP6SZLZ5W44VOJ7H7B/graph.json","events_json":"https://pith.science/api/pith-number/F2HCGQSJGP6SZLZ5W44VOJ7H7B/events.json","paper":"https://pith.science/paper/F2HCGQSJ"},"agent_actions":{"view_html":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B","download_json":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B.json","view_paper":"https://pith.science/paper/F2HCGQSJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.09012&json=true","fetch_graph":"https://pith.science/api/pith-number/F2HCGQSJGP6SZLZ5W44VOJ7H7B/graph.json","fetch_events":"https://pith.science/api/pith-number/F2HCGQSJGP6SZLZ5W44VOJ7H7B/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B/action/timestamp_anchor","attest_storage":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B/action/storage_attestation","attest_author":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B/action/author_attestation","sign_citation":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B/action/citation_signature","submit_replication":"https://pith.science/pith/F2HCGQSJGP6SZLZ5W44VOJ7H7B/action/replication_record"}},"created_at":"2026-07-05T05:31:15.101521+00:00","updated_at":"2026-07-05T05:31:15.101521+00:00"}