{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YPTZKVVO4XM4T4JUBZ36RO7NGT","short_pith_number":"pith:YPTZKVVO","schema_version":"1.0","canonical_sha256":"c3e79556aee5d9c9f1340e77e8bbed34d145181b7a86896932b17a69e2ec569c","source":{"kind":"arxiv","id":"2307.02457","version":1},"attestation_state":"computed","paper":{"title":"DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Gen Li, Jiantao Zhou, Liangbin Xie, Xiangyu Chen, Xintao Wang, Ying Shan","submitted_at":"2023-07-05T17:31:44Z","abstract_excerpt":"Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models will inevitably produce unpleasant and undesirable artifacts, especially in practical scenarios. Previous works typically suppress artifacts with an extra loss penalty in the training phase. They only work for in-distribution artifact types generated during training. When applied in real-world scenarios, we observe that those improved methods still generate obviously annoying artifacts during inference. In this paper"},"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":"2307.02457","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-07-05T17:31:44Z","cross_cats_sorted":["cs.AI","cs.MM"],"title_canon_sha256":"600245804b651d94ac7a9cb8032efc142785c3dfa63a9ed3109b907e4533aeb1","abstract_canon_sha256":"b11ba9892e016913cae448c5309e17106722a84f13a4741f0066f8a3c3af444b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:28:09.328662Z","signature_b64":"7o/LODDEnYsvL4RgD17tr6MeAbpbTQxkaRG4Vc4+q23F01Jr0g7zLIq3LxA+v3sNloXoNOvx3JM7lAInOB9RBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c3e79556aee5d9c9f1340e77e8bbed34d145181b7a86896932b17a69e2ec569c","last_reissued_at":"2026-07-05T06:28:09.328210Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:28:09.328210Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeSRA: Detect and Delete the Artifacts of GAN-based Real-World Super-Resolution Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.MM"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Gen Li, Jiantao Zhou, Liangbin Xie, Xiangyu Chen, Xintao Wang, Ying Shan","submitted_at":"2023-07-05T17:31:44Z","abstract_excerpt":"Image super-resolution (SR) with generative adversarial networks (GAN) has achieved great success in restoring realistic details. However, it is notorious that GAN-based SR models will inevitably produce unpleasant and undesirable artifacts, especially in practical scenarios. Previous works typically suppress artifacts with an extra loss penalty in the training phase. They only work for in-distribution artifact types generated during training. When applied in real-world scenarios, we observe that those improved methods still generate obviously annoying artifacts during inference. In this paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02457","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/2307.02457/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":"2307.02457","created_at":"2026-07-05T06:28:09.328269+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02457v1","created_at":"2026-07-05T06:28:09.328269+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02457","created_at":"2026-07-05T06:28:09.328269+00:00"},{"alias_kind":"pith_short_12","alias_value":"YPTZKVVO4XM4","created_at":"2026-07-05T06:28:09.328269+00:00"},{"alias_kind":"pith_short_16","alias_value":"YPTZKVVO4XM4T4JU","created_at":"2026-07-05T06:28:09.328269+00:00"},{"alias_kind":"pith_short_8","alias_value":"YPTZKVVO","created_at":"2026-07-05T06:28:09.328269+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":6,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2606.31363","citing_title":"Language-Assisted Super-Resolution from Real-World Low-Resolution Patches","ref_index":97,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14847","citing_title":"SR-Prominence: A Crowdsourced Protocol and Dataset Suite for Perceptually-Weighted Super-Resolution Artifact Evaluation","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15682","citing_title":"DreamSR: Towards Ultra-High-Resolution Image Super-Resolution via a Receptive-Field Enhanced Diffusion Transformer","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25457","citing_title":"GramSR: Visual Feature Conditioning for Diffusion-Based Super-Resolution","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2604.19238","citing_title":"Allo{SR}$^2$: Rectifying One-Step Super-Resolution to Stay Real via Allomorphic Generative Flows","ref_index":49,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT","json":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT.json","graph_json":"https://pith.science/api/pith-number/YPTZKVVO4XM4T4JUBZ36RO7NGT/graph.json","events_json":"https://pith.science/api/pith-number/YPTZKVVO4XM4T4JUBZ36RO7NGT/events.json","paper":"https://pith.science/paper/YPTZKVVO"},"agent_actions":{"view_html":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT","download_json":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT.json","view_paper":"https://pith.science/paper/YPTZKVVO","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02457&json=true","fetch_graph":"https://pith.science/api/pith-number/YPTZKVVO4XM4T4JUBZ36RO7NGT/graph.json","fetch_events":"https://pith.science/api/pith-number/YPTZKVVO4XM4T4JUBZ36RO7NGT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT/action/storage_attestation","attest_author":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT/action/author_attestation","sign_citation":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT/action/citation_signature","submit_replication":"https://pith.science/pith/YPTZKVVO4XM4T4JUBZ36RO7NGT/action/replication_record"}},"created_at":"2026-07-05T06:28:09.328269+00:00","updated_at":"2026-07-05T06:28:09.328269+00:00"}