{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:OB6K3VYN4WUEMVZRVHT7MVUVJB","short_pith_number":"pith:OB6K3VYN","schema_version":"1.0","canonical_sha256":"707cadd70de5a8465731a9e7f656954870bedf7f00a3dcff6ba2fa2bd9663063","source":{"kind":"arxiv","id":"2308.14409","version":3},"attestation_state":"computed","paper":{"title":"Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Denker, Bangti Jin, Hyungjin Chung, Jong Chul Ye, Peter Maass, Riccardo Barbano, Simon Arridge, Tae Hoon Roh","submitted_at":"2023-08-28T08:47:06Z","abstract_excerpt":"Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored challenge. Using a diffusion model on an out-of-distribution dataset, realistic reconstructions can be generated, but with hallucinating image features that are uniquely present in the training dataset. To address this discrepancy during train-test time and improve reconstruction accuracy, we introduce a novel sampling framework called Steerable Conditional "},"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":"2308.14409","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-08-28T08:47:06Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"da42d1ba9db764cda89a53449f4eb271cc910a8953d2d61a59bcb03f1745992b","abstract_canon_sha256":"f8098af0eb653bd0f187a29fe37600d0067051aa3bb5bf334510e98607ac1112"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:01.512985Z","signature_b64":"8QInqKXRf47IR70sWUvxbxRHG828eZS6l1QsmFXi1EDcJOJ9sh2alMXWhII9UxDlM+xEWridmBhMy+gD0M+yBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"707cadd70de5a8465731a9e7f656954870bedf7f00a3dcff6ba2fa2bd9663063","last_reissued_at":"2026-07-05T10:06:01.512449Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:01.512449Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Steerable Conditional Diffusion for Out-of-Distribution Adaptation in Medical Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander Denker, Bangti Jin, Hyungjin Chung, Jong Chul Ye, Peter Maass, Riccardo Barbano, Simon Arridge, Tae Hoon Roh","submitted_at":"2023-08-28T08:47:06Z","abstract_excerpt":"Denoising diffusion models have emerged as the go-to generative framework for solving inverse problems in imaging. A critical concern regarding these models is their performance on out-of-distribution tasks, which remains an under-explored challenge. Using a diffusion model on an out-of-distribution dataset, realistic reconstructions can be generated, but with hallucinating image features that are uniquely present in the training dataset. To address this discrepancy during train-test time and improve reconstruction accuracy, we introduce a novel sampling framework called Steerable Conditional "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.14409","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/2308.14409/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":"2308.14409","created_at":"2026-07-05T10:06:01.512522+00:00"},{"alias_kind":"arxiv_version","alias_value":"2308.14409v3","created_at":"2026-07-05T10:06:01.512522+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.14409","created_at":"2026-07-05T10:06:01.512522+00:00"},{"alias_kind":"pith_short_12","alias_value":"OB6K3VYN4WUE","created_at":"2026-07-05T10:06:01.512522+00:00"},{"alias_kind":"pith_short_16","alias_value":"OB6K3VYN4WUEMVZR","created_at":"2026-07-05T10:06:01.512522+00:00"},{"alias_kind":"pith_short_8","alias_value":"OB6K3VYN","created_at":"2026-07-05T10:06:01.512522+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2501.13692","citing_title":"Training-Free, Identity-Preserving Image Editing for Fashion Pose Alignment and Normalization","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB","json":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB.json","graph_json":"https://pith.science/api/pith-number/OB6K3VYN4WUEMVZRVHT7MVUVJB/graph.json","events_json":"https://pith.science/api/pith-number/OB6K3VYN4WUEMVZRVHT7MVUVJB/events.json","paper":"https://pith.science/paper/OB6K3VYN"},"agent_actions":{"view_html":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB","download_json":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB.json","view_paper":"https://pith.science/paper/OB6K3VYN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2308.14409&json=true","fetch_graph":"https://pith.science/api/pith-number/OB6K3VYN4WUEMVZRVHT7MVUVJB/graph.json","fetch_events":"https://pith.science/api/pith-number/OB6K3VYN4WUEMVZRVHT7MVUVJB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB/action/storage_attestation","attest_author":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB/action/author_attestation","sign_citation":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB/action/citation_signature","submit_replication":"https://pith.science/pith/OB6K3VYN4WUEMVZRVHT7MVUVJB/action/replication_record"}},"created_at":"2026-07-05T10:06:01.512522+00:00","updated_at":"2026-07-05T10:06:01.512522+00:00"}