{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:HPYS5OA342ME6LCTTG7M2YVZRT","short_pith_number":"pith:HPYS5OA3","schema_version":"1.0","canonical_sha256":"3bf12eb81be6984f2c5399becd62b98cc6fc9a8e848477ae2929040068ea5713","source":{"kind":"arxiv","id":"2304.03322","version":1},"attestation_state":"computed","paper":{"title":"Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guanhua Zhang, Jiabao Ji, Mo Yu, Shiyu Chang, Tommi Jaakkola, Yang Zhang","submitted_at":"2023-04-06T18:35:13Z","abstract_excerpt":"Image inpainting refers to the task of generating a complete, natural image based on a partially revealed reference image. Recently, many research interests have been focused on addressing this problem using fixed diffusion models. These approaches typically directly replace the revealed region of the intermediate or final generated images with that of the reference image or its variants. However, since the unrevealed regions are not directly modified to match the context, it results in incoherence between revealed and unrevealed regions. To address the incoherence problem, a small number of m"},"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":"2304.03322","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2023-04-06T18:35:13Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"cf0de2422fccb41d855bca3a525254ee4c4a969de4966c4665506702fef4d9b8","abstract_canon_sha256":"18abcbf048017c68fb654a5ecf2a6dea544855cc4d8e22339d298fc846d72958"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:54.798488Z","signature_b64":"oVG1iZcPxPRJOqdlWsAZxwVRC5x+Xy+JW2u0aXQjcoSJKjSISvE8rxOivGlOYDt49l9aJHUciPvT+EceM9JICg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3bf12eb81be6984f2c5399becd62b98cc6fc9a8e848477ae2929040068ea5713","last_reissued_at":"2026-07-05T05:58:54.798085Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:54.798085Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Guanhua Zhang, Jiabao Ji, Mo Yu, Shiyu Chang, Tommi Jaakkola, Yang Zhang","submitted_at":"2023-04-06T18:35:13Z","abstract_excerpt":"Image inpainting refers to the task of generating a complete, natural image based on a partially revealed reference image. Recently, many research interests have been focused on addressing this problem using fixed diffusion models. These approaches typically directly replace the revealed region of the intermediate or final generated images with that of the reference image or its variants. However, since the unrevealed regions are not directly modified to match the context, it results in incoherence between revealed and unrevealed regions. To address the incoherence problem, a small number of m"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03322","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/2304.03322/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":"2304.03322","created_at":"2026-07-05T05:58:54.798142+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03322v1","created_at":"2026-07-05T05:58:54.798142+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03322","created_at":"2026-07-05T05:58:54.798142+00:00"},{"alias_kind":"pith_short_12","alias_value":"HPYS5OA342ME","created_at":"2026-07-05T05:58:54.798142+00:00"},{"alias_kind":"pith_short_16","alias_value":"HPYS5OA342ME6LCT","created_at":"2026-07-05T05:58:54.798142+00:00"},{"alias_kind":"pith_short_8","alias_value":"HPYS5OA3","created_at":"2026-07-05T05:58:54.798142+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2411.18929","citing_title":"VIPaint: Image Inpainting with Pre-Trained Diffusion Models via Variational Inference","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2504.18361","citing_title":"COCO-Inpaint: A Benchmark for Detecting and Localizing Inpainting-Based Image Manipulations","ref_index":73,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24913","citing_title":"Generative diffusion models for spatiotemporal influenza forecasting","ref_index":24,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT","json":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT.json","graph_json":"https://pith.science/api/pith-number/HPYS5OA342ME6LCTTG7M2YVZRT/graph.json","events_json":"https://pith.science/api/pith-number/HPYS5OA342ME6LCTTG7M2YVZRT/events.json","paper":"https://pith.science/paper/HPYS5OA3"},"agent_actions":{"view_html":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT","download_json":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT.json","view_paper":"https://pith.science/paper/HPYS5OA3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03322&json=true","fetch_graph":"https://pith.science/api/pith-number/HPYS5OA342ME6LCTTG7M2YVZRT/graph.json","fetch_events":"https://pith.science/api/pith-number/HPYS5OA342ME6LCTTG7M2YVZRT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT/action/storage_attestation","attest_author":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT/action/author_attestation","sign_citation":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT/action/citation_signature","submit_replication":"https://pith.science/pith/HPYS5OA342ME6LCTTG7M2YVZRT/action/replication_record"}},"created_at":"2026-07-05T05:58:54.798142+00:00","updated_at":"2026-07-05T05:58:54.798142+00:00"}