{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:JAWBR4XGTNMMYWYYLM23QFUH2X","short_pith_number":"pith:JAWBR4XG","schema_version":"1.0","canonical_sha256":"482c18f2e69b58cc5b185b35b81687d5de2bab9e1955e326edd4c3fa155ad5a1","source":{"kind":"arxiv","id":"2303.09642","version":2},"attestation_state":"computed","paper":{"title":"SUD$^2$: Supervision by Denoising Diffusion Models for Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Christopher A. Metzler, Matthew A. Chan, Sean I. Young","submitted_at":"2023-03-16T20:42:24Z","abstract_excerpt":"Many imaging inverse problems$\\unicode{x2014}$such as image-dependent in-painting and dehazing$\\unicode{x2014}$are challenging because their forward models are unknown or depend on unknown latent parameters. While one can solve such problems by training a neural network with vast quantities of paired training data, such paired training data is often unavailable. In this paper, we propose a generalized framework for training image reconstruction networks when paired training data is scarce. In particular, we demonstrate the ability of image denoising algorithms and, by extension, denoising diff"},"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":"2303.09642","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-03-16T20:42:24Z","cross_cats_sorted":["cs.LG","eess.IV"],"title_canon_sha256":"8540ccf0ba7edfbb111af545e215a6bd99e5e1f1a3a0a723354e8d875cac11d6","abstract_canon_sha256":"acd57523c5d6ddc6710985578bdd79d0f6897ff49ccf2d8855b3d84809c155c7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:57:16.731706Z","signature_b64":"F5rD173hzRlo6nQ7m5i+Kmpji2xVSFnjBiJcdgRkm04KUsb0sO5pz4GA6zbZ31GKSjbMCI0g1o7rW4EpRPJaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"482c18f2e69b58cc5b185b35b81687d5de2bab9e1955e326edd4c3fa155ad5a1","last_reissued_at":"2026-07-05T05:57:16.731251Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:57:16.731251Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SUD$^2$: Supervision by Denoising Diffusion Models for Image Reconstruction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","eess.IV"],"primary_cat":"cs.CV","authors_text":"Christopher A. Metzler, Matthew A. Chan, Sean I. Young","submitted_at":"2023-03-16T20:42:24Z","abstract_excerpt":"Many imaging inverse problems$\\unicode{x2014}$such as image-dependent in-painting and dehazing$\\unicode{x2014}$are challenging because their forward models are unknown or depend on unknown latent parameters. While one can solve such problems by training a neural network with vast quantities of paired training data, such paired training data is often unavailable. In this paper, we propose a generalized framework for training image reconstruction networks when paired training data is scarce. In particular, we demonstrate the ability of image denoising algorithms and, by extension, denoising diff"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.09642","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/2303.09642/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":"2303.09642","created_at":"2026-07-05T05:57:16.731326+00:00"},{"alias_kind":"arxiv_version","alias_value":"2303.09642v2","created_at":"2026-07-05T05:57:16.731326+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.09642","created_at":"2026-07-05T05:57:16.731326+00:00"},{"alias_kind":"pith_short_12","alias_value":"JAWBR4XGTNMM","created_at":"2026-07-05T05:57:16.731326+00:00"},{"alias_kind":"pith_short_16","alias_value":"JAWBR4XGTNMMYWYY","created_at":"2026-07-05T05:57:16.731326+00:00"},{"alias_kind":"pith_short_8","alias_value":"JAWBR4XG","created_at":"2026-07-05T05:57:16.731326+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2411.09850","citing_title":"Enhancing Diffusion Posterior Sampling for Inverse Problems by Integrating Crafted Measurements","ref_index":5,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X","json":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X.json","graph_json":"https://pith.science/api/pith-number/JAWBR4XGTNMMYWYYLM23QFUH2X/graph.json","events_json":"https://pith.science/api/pith-number/JAWBR4XGTNMMYWYYLM23QFUH2X/events.json","paper":"https://pith.science/paper/JAWBR4XG"},"agent_actions":{"view_html":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X","download_json":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X.json","view_paper":"https://pith.science/paper/JAWBR4XG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2303.09642&json=true","fetch_graph":"https://pith.science/api/pith-number/JAWBR4XGTNMMYWYYLM23QFUH2X/graph.json","fetch_events":"https://pith.science/api/pith-number/JAWBR4XGTNMMYWYYLM23QFUH2X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X/action/storage_attestation","attest_author":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X/action/author_attestation","sign_citation":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X/action/citation_signature","submit_replication":"https://pith.science/pith/JAWBR4XGTNMMYWYYLM23QFUH2X/action/replication_record"}},"created_at":"2026-07-05T05:57:16.731326+00:00","updated_at":"2026-07-05T05:57:16.731326+00:00"}