{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7V3XNIPY6S7XB6B6XBN5HT2H5Y","short_pith_number":"pith:7V3XNIPY","schema_version":"1.0","canonical_sha256":"fd7776a1f8f4bf70f83eb85bd3cf47ee1fc7096e049bf3df39de3c27cbadd527","source":{"kind":"arxiv","id":"2302.01217","version":1},"attestation_state":"computed","paper":{"title":"A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Advait Parulekar, Constantine Caramanis, Litu Rout, Sanjay Shakkottai","submitted_at":"2023-02-02T16:55:03Z","abstract_excerpt":"We provide a theoretical justification for sample recovery using diffusion based image inpainting in a linear model setting. While most inpainting algorithms require retraining with each new mask, we prove that diffusion based inpainting generalizes well to unseen masks without retraining. We analyze a recently proposed popular diffusion based inpainting algorithm called RePaint (Lugmayr et al., 2022), and show that it has a bias due to misalignment that hampers sample recovery even in a two-state diffusion process. Motivated by our analysis, we propose a modified RePaint algorithm we call ReP"},"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":"2302.01217","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"stat.ML","submitted_at":"2023-02-02T16:55:03Z","cross_cats_sorted":["cs.AI","cs.LG","math.ST","stat.TH"],"title_canon_sha256":"0d781b8b1b44a9ff5efad05138ed878d95afe6acc31ecffceafc12896246259a","abstract_canon_sha256":"013015aba2d7f27bb07fd41b4bf0f2f352996c30882a504122a53f73ccb9da5f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:38:24.172026Z","signature_b64":"NHfOHHVEljypEukQJoLH/C7T7CEwWkbLx+2abCQko85GzVQKCEBmXwEg3fs6ljB/yUj9EOso7nyE9pwPvxxjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd7776a1f8f4bf70f83eb85bd3cf47ee1fc7096e049bf3df39de3c27cbadd527","last_reissued_at":"2026-07-05T05:38:24.171561Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:38:24.171561Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Theoretical Justification for Image Inpainting using Denoising Diffusion Probabilistic Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG","math.ST","stat.TH"],"primary_cat":"stat.ML","authors_text":"Advait Parulekar, Constantine Caramanis, Litu Rout, Sanjay Shakkottai","submitted_at":"2023-02-02T16:55:03Z","abstract_excerpt":"We provide a theoretical justification for sample recovery using diffusion based image inpainting in a linear model setting. While most inpainting algorithms require retraining with each new mask, we prove that diffusion based inpainting generalizes well to unseen masks without retraining. We analyze a recently proposed popular diffusion based inpainting algorithm called RePaint (Lugmayr et al., 2022), and show that it has a bias due to misalignment that hampers sample recovery even in a two-state diffusion process. Motivated by our analysis, we propose a modified RePaint algorithm we call ReP"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.01217","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/2302.01217/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":"2302.01217","created_at":"2026-07-05T05:38:24.171619+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.01217v1","created_at":"2026-07-05T05:38:24.171619+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.01217","created_at":"2026-07-05T05:38:24.171619+00:00"},{"alias_kind":"pith_short_12","alias_value":"7V3XNIPY6S7X","created_at":"2026-07-05T05:38:24.171619+00:00"},{"alias_kind":"pith_short_16","alias_value":"7V3XNIPY6S7XB6B6","created_at":"2026-07-05T05:38:24.171619+00:00"},{"alias_kind":"pith_short_8","alias_value":"7V3XNIPY","created_at":"2026-07-05T05:38:24.171619+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.00078","citing_title":"Flow-Based Generative Modeling for Optimizing Sampling Policies in Compressed Sensing Applications","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2410.00083","citing_title":"A Survey on Diffusion Models for Inverse Problems","ref_index":125,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24913","citing_title":"Generative diffusion models for spatiotemporal influenza forecasting","ref_index":19,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y","json":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y.json","graph_json":"https://pith.science/api/pith-number/7V3XNIPY6S7XB6B6XBN5HT2H5Y/graph.json","events_json":"https://pith.science/api/pith-number/7V3XNIPY6S7XB6B6XBN5HT2H5Y/events.json","paper":"https://pith.science/paper/7V3XNIPY"},"agent_actions":{"view_html":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y","download_json":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y.json","view_paper":"https://pith.science/paper/7V3XNIPY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.01217&json=true","fetch_graph":"https://pith.science/api/pith-number/7V3XNIPY6S7XB6B6XBN5HT2H5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7V3XNIPY6S7XB6B6XBN5HT2H5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y/action/storage_attestation","attest_author":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y/action/author_attestation","sign_citation":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y/action/citation_signature","submit_replication":"https://pith.science/pith/7V3XNIPY6S7XB6B6XBN5HT2H5Y/action/replication_record"}},"created_at":"2026-07-05T05:38:24.171619+00:00","updated_at":"2026-07-05T05:38:24.171619+00:00"}