{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:66J3WSHOHBPABY2LK6KPQMBCRK","short_pith_number":"pith:66J3WSHO","schema_version":"1.0","canonical_sha256":"f793bb48ee385e00e34b5794f830228a8d7e4c1d1202c9433a13bb745c9ac125","source":{"kind":"arxiv","id":"2212.03221","version":2},"attestation_state":"computed","paper":{"title":"ADIR: Adaptive Diffusion for Image Reconstruction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Raja Giryes, Shady Abu-Hussein, Tom Tirer","submitted_at":"2022-12-06T18:39:58Z","abstract_excerpt":"Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promising for image reconstruction, where the goal is to recover a clean image from a degraded observation. In this work, we introduce a conditional sampling framework that leverages the powerful priors learned by diffusion models while enforcing consistency with the available measurements. To further adapt pre-trained diffusion models to the specific degradation at hand, we propose a novel fine-tuning strategy. In particula"},"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":"2212.03221","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CV","submitted_at":"2022-12-06T18:39:58Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"468cc726aeb3a4bdd1eb800a6b899287094c771b6fe3b54b5dba02f86bb5e54a","abstract_canon_sha256":"ab4cf36369cffee11721c9d8fe94fe79e2471aa4dfccac28cf7b0d913797bc73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T12:05:56.441641Z","signature_b64":"gkmNxopqAsVXmj2KFlfUdGIlMW/f7TllT8+AL9EKFE0K+Gpj7MuTm4nDXk/8UNciZCc+uZws2t9pmVJTxg9oCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f793bb48ee385e00e34b5794f830228a8d7e4c1d1202c9433a13bb745c9ac125","last_reissued_at":"2026-07-05T12:05:56.441053Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T12:05:56.441053Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ADIR: Adaptive Diffusion for Image Reconstruction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Raja Giryes, Shady Abu-Hussein, Tom Tirer","submitted_at":"2022-12-06T18:39:58Z","abstract_excerpt":"Denoising diffusion models have recently achieved remarkable success in image generation, capturing rich information about natural image statistics. This makes them highly promising for image reconstruction, where the goal is to recover a clean image from a degraded observation. In this work, we introduce a conditional sampling framework that leverages the powerful priors learned by diffusion models while enforcing consistency with the available measurements. To further adapt pre-trained diffusion models to the specific degradation at hand, we propose a novel fine-tuning strategy. In particula"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2212.03221","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/2212.03221/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":"2212.03221","created_at":"2026-07-05T12:05:56.441115+00:00"},{"alias_kind":"arxiv_version","alias_value":"2212.03221v2","created_at":"2026-07-05T12:05:56.441115+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2212.03221","created_at":"2026-07-05T12:05:56.441115+00:00"},{"alias_kind":"pith_short_12","alias_value":"66J3WSHOHBPA","created_at":"2026-07-05T12:05:56.441115+00:00"},{"alias_kind":"pith_short_16","alias_value":"66J3WSHOHBPABY2L","created_at":"2026-07-05T12:05:56.441115+00:00"},{"alias_kind":"pith_short_8","alias_value":"66J3WSHO","created_at":"2026-07-05T12:05:56.441115+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.19170","citing_title":"Reducing Diffusion Model Memorization with Higher Order Langevin Dynamics","ref_index":63,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK","json":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK.json","graph_json":"https://pith.science/api/pith-number/66J3WSHOHBPABY2LK6KPQMBCRK/graph.json","events_json":"https://pith.science/api/pith-number/66J3WSHOHBPABY2LK6KPQMBCRK/events.json","paper":"https://pith.science/paper/66J3WSHO"},"agent_actions":{"view_html":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK","download_json":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK.json","view_paper":"https://pith.science/paper/66J3WSHO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2212.03221&json=true","fetch_graph":"https://pith.science/api/pith-number/66J3WSHOHBPABY2LK6KPQMBCRK/graph.json","fetch_events":"https://pith.science/api/pith-number/66J3WSHOHBPABY2LK6KPQMBCRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK/action/storage_attestation","attest_author":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK/action/author_attestation","sign_citation":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK/action/citation_signature","submit_replication":"https://pith.science/pith/66J3WSHOHBPABY2LK6KPQMBCRK/action/replication_record"}},"created_at":"2026-07-05T12:05:56.441115+00:00","updated_at":"2026-07-05T12:05:56.441115+00:00"}