{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:VS7ZBAKG7XJHMD7RSV6RFESQV6","short_pith_number":"pith:VS7ZBAKG","schema_version":"1.0","canonical_sha256":"acbf908146fdd2760ff1957d129250af9959b8d99dfa3cf8acdbe08afa682062","source":{"kind":"arxiv","id":"2410.11730","version":1},"attestation_state":"computed","paper":{"title":"Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bowen Song, Jason Hu, Jeffrey A. Fessler, Liyue Shen","submitted_at":"2024-10-15T16:02:08Z","abstract_excerpt":"Diffusion models have achieved excellent success in solving inverse problems due to their ability to learn strong image priors, but existing approaches require a large training dataset of images that should come from the same distribution as the test dataset. When the training and test distributions are mismatched, artifacts and hallucinations can occur in reconstructed images due to the incorrect priors. In this work, we systematically study out of distribution (OOD) problems where a known training distribution is first provided. We first study the setting where only a single measurement obta"},"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":"2410.11730","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2024-10-15T16:02:08Z","cross_cats_sorted":["cs.AI","eess.IV"],"title_canon_sha256":"05782cdbaeaa600a6484304e3df00948cc0eb0a14af9e23245aa35cd45dd9089","abstract_canon_sha256":"3037dbe55097bee078b8c586d370a961761774dac19c4bc7b3d4f770521920da"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:20:58.121129Z","signature_b64":"pGk/4h1JOVNZaFbtRJT2ApMmTi4ykenFTW6bux15fZF+fjdiLoWIxz8O/QTfAHL+Htwgx677Agze9cMTBmCGCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"acbf908146fdd2760ff1957d129250af9959b8d99dfa3cf8acdbe08afa682062","last_reissued_at":"2026-07-05T09:20:58.120673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:20:58.120673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Patch-Based Diffusion Models Beat Whole-Image Models for Mismatched Distribution Inverse Problems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","eess.IV"],"primary_cat":"cs.CV","authors_text":"Bowen Song, Jason Hu, Jeffrey A. Fessler, Liyue Shen","submitted_at":"2024-10-15T16:02:08Z","abstract_excerpt":"Diffusion models have achieved excellent success in solving inverse problems due to their ability to learn strong image priors, but existing approaches require a large training dataset of images that should come from the same distribution as the test dataset. When the training and test distributions are mismatched, artifacts and hallucinations can occur in reconstructed images due to the incorrect priors. In this work, we systematically study out of distribution (OOD) problems where a known training distribution is first provided. We first study the setting where only a single measurement obta"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11730","kind":"arxiv","version":1},"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/2410.11730/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":"2410.11730","created_at":"2026-07-05T09:20:58.120731+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11730v1","created_at":"2026-07-05T09:20:58.120731+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11730","created_at":"2026-07-05T09:20:58.120731+00:00"},{"alias_kind":"pith_short_12","alias_value":"VS7ZBAKG7XJH","created_at":"2026-07-05T09:20:58.120731+00:00"},{"alias_kind":"pith_short_16","alias_value":"VS7ZBAKG7XJHMD7R","created_at":"2026-07-05T09:20:58.120731+00:00"},{"alias_kind":"pith_short_8","alias_value":"VS7ZBAKG","created_at":"2026-07-05T09:20:58.120731+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.10642","citing_title":"Composing diffusion priors with explicit physical context via generative Gibbs sampling","ref_index":10,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6","json":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6.json","graph_json":"https://pith.science/api/pith-number/VS7ZBAKG7XJHMD7RSV6RFESQV6/graph.json","events_json":"https://pith.science/api/pith-number/VS7ZBAKG7XJHMD7RSV6RFESQV6/events.json","paper":"https://pith.science/paper/VS7ZBAKG"},"agent_actions":{"view_html":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6","download_json":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6.json","view_paper":"https://pith.science/paper/VS7ZBAKG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11730&json=true","fetch_graph":"https://pith.science/api/pith-number/VS7ZBAKG7XJHMD7RSV6RFESQV6/graph.json","fetch_events":"https://pith.science/api/pith-number/VS7ZBAKG7XJHMD7RSV6RFESQV6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6/action/storage_attestation","attest_author":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6/action/author_attestation","sign_citation":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6/action/citation_signature","submit_replication":"https://pith.science/pith/VS7ZBAKG7XJHMD7RSV6RFESQV6/action/replication_record"}},"created_at":"2026-07-05T09:20:58.120731+00:00","updated_at":"2026-07-05T09:20:58.120731+00:00"}