{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:QM35XZ72IYE27SVQ5XAHHO4J5J","short_pith_number":"pith:QM35XZ72","schema_version":"1.0","canonical_sha256":"8337dbe7fa4609afcab0edc073bb89ea70f3383ddb7206d785ffc47e8e2b3e6e","source":{"kind":"arxiv","id":"2603.05010","version":2},"attestation_state":"computed","paper":{"title":"How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jinfan Hu, Jinjin Gu, Kainan Yan, Xiang Yin, Yu Tang, Zhiyuan You","submitted_at":"2026-03-05T09:57:45Z","abstract_excerpt":"Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with previous methods? To answer this, we present a large-scale study grounded in a new multi-dimensional evaluation pipeline that assesses models on detail, sharpness, semantic correctness, and overall quality. Our analysis covers diverse architectures, including diffusion-based, GAN-based, PSNR-oriented, and general-purpose generation models, revealing critical performance disparities. Furthermore, our analysis uncovers a key evolution in failure "},"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":"2603.05010","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2026-03-05T09:57:45Z","cross_cats_sorted":[],"title_canon_sha256":"af2da3e9f396a8a5fd415d8980adbf74e629de48cac48081d73a1c00bc2624c4","abstract_canon_sha256":"392c647a563d1c52efb475d85dc2b0e6aa76d16261d9d586388108bb22cc1ac3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:10:54.957713Z","signature_b64":"+hez6cSNF79DR/Dzk02wtiMf4tvBMPXTXfq3ULPN66rFWyuyL1zdmpYdTKZkDG7WsMucXO/RCteG4j3yUAesDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8337dbe7fa4609afcab0edc073bb89ea70f3383ddb7206d785ffc47e8e2b3e6e","last_reissued_at":"2026-06-19T16:10:54.957289Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:10:54.957289Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"How far have we gone in Generative Image Restoration? A study on its capability, limitations and evaluation practices","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Chao Dong, Jinfan Hu, Jinjin Gu, Kainan Yan, Xiang Yin, Yu Tang, Zhiyuan You","submitted_at":"2026-03-05T09:57:45Z","abstract_excerpt":"Generative Image Restoration (GIR) has achieved impressive perceptual realism, but how far have its practical capabilities truly advanced compared with previous methods? To answer this, we present a large-scale study grounded in a new multi-dimensional evaluation pipeline that assesses models on detail, sharpness, semantic correctness, and overall quality. Our analysis covers diverse architectures, including diffusion-based, GAN-based, PSNR-oriented, and general-purpose generation models, revealing critical performance disparities. Furthermore, our analysis uncovers a key evolution in failure "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.05010","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/2603.05010/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":"2603.05010","created_at":"2026-06-19T16:10:54.957359+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.05010v2","created_at":"2026-06-19T16:10:54.957359+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.05010","created_at":"2026-06-19T16:10:54.957359+00:00"},{"alias_kind":"pith_short_12","alias_value":"QM35XZ72IYE2","created_at":"2026-06-19T16:10:54.957359+00:00"},{"alias_kind":"pith_short_16","alias_value":"QM35XZ72IYE27SVQ","created_at":"2026-06-19T16:10:54.957359+00:00"},{"alias_kind":"pith_short_8","alias_value":"QM35XZ72","created_at":"2026-06-19T16:10:54.957359+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2604.03061","citing_title":"Can Nano Banana 2 Replace Traditional Image Restoration Models? An Evaluation of Its Performance on Image Restoration Tasks","ref_index":28,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J","json":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J.json","graph_json":"https://pith.science/api/pith-number/QM35XZ72IYE27SVQ5XAHHO4J5J/graph.json","events_json":"https://pith.science/api/pith-number/QM35XZ72IYE27SVQ5XAHHO4J5J/events.json","paper":"https://pith.science/paper/QM35XZ72"},"agent_actions":{"view_html":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J","download_json":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J.json","view_paper":"https://pith.science/paper/QM35XZ72","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.05010&json=true","fetch_graph":"https://pith.science/api/pith-number/QM35XZ72IYE27SVQ5XAHHO4J5J/graph.json","fetch_events":"https://pith.science/api/pith-number/QM35XZ72IYE27SVQ5XAHHO4J5J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J/action/storage_attestation","attest_author":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J/action/author_attestation","sign_citation":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J/action/citation_signature","submit_replication":"https://pith.science/pith/QM35XZ72IYE27SVQ5XAHHO4J5J/action/replication_record"}},"created_at":"2026-06-19T16:10:54.957359+00:00","updated_at":"2026-06-19T16:10:54.957359+00:00"}