{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Z7SKC2FQHCDXRTXFRYK7EYBSE6","short_pith_number":"pith:Z7SKC2FQ","schema_version":"1.0","canonical_sha256":"cfe4a168b0388778cee58e15f26032278908ed38b4c1210810f7d5bf941bac0a","source":{"kind":"arxiv","id":"2410.18666","version":2},"attestation_state":"computed","paper":{"title":"DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxia Yang, Huaibo Huang, Quanzeng You, Xiaoqiang Zhou, Xiaotian Han, Yuang Ai, Zhengyu Chen","submitted_at":"2024-10-24T11:57:20Z","abstract_excerpt":"Image restoration (IR) in real-world scenarios presents significant challenges due to the lack of high-capacity models and comprehensive datasets. To tackle these issues, we present a dual strategy: GenIR, an innovative data curation pipeline, and DreamClear, a cutting-edge Diffusion Transformer (DiT)-based image restoration model. GenIR, our pioneering contribution, is a dual-prompt learning pipeline that overcomes the limitations of existing datasets, which typically comprise only a few thousand images and thus offer limited generalizability for larger models. GenIR streamlines the process i"},"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":"2410.18666","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-10-24T11:57:20Z","cross_cats_sorted":[],"title_canon_sha256":"ff249db19daf38c8af36d5af2f25fd321acb833f1843d0312570a80fc4e9bfa3","abstract_canon_sha256":"cbba336cddb81d5d1ca3464f9bd91ded2b9c5b642c457343d1efea15a7c2ccf0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:27:25.584907Z","signature_b64":"02eKQJrqVS7bLu402Jsbnku07dVgCIVbaQYx1bx48z7YJ4lBl8zWG1w+E1p9i8HdPn3wh8FIpdx0QLqyofBgDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cfe4a168b0388778cee58e15f26032278908ed38b4c1210810f7d5bf941bac0a","last_reissued_at":"2026-07-05T09:27:25.584443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:27:25.584443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DreamClear: High-Capacity Real-World Image Restoration with Privacy-Safe Dataset Curation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Hongxia Yang, Huaibo Huang, Quanzeng You, Xiaoqiang Zhou, Xiaotian Han, Yuang Ai, Zhengyu Chen","submitted_at":"2024-10-24T11:57:20Z","abstract_excerpt":"Image restoration (IR) in real-world scenarios presents significant challenges due to the lack of high-capacity models and comprehensive datasets. To tackle these issues, we present a dual strategy: GenIR, an innovative data curation pipeline, and DreamClear, a cutting-edge Diffusion Transformer (DiT)-based image restoration model. GenIR, our pioneering contribution, is a dual-prompt learning pipeline that overcomes the limitations of existing datasets, which typically comprise only a few thousand images and thus offer limited generalizability for larger models. GenIR streamlines the process i"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.18666","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/2410.18666/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":"2410.18666","created_at":"2026-07-05T09:27:25.584500+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.18666v2","created_at":"2026-07-05T09:27:25.584500+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.18666","created_at":"2026-07-05T09:27:25.584500+00:00"},{"alias_kind":"pith_short_12","alias_value":"Z7SKC2FQHCDX","created_at":"2026-07-05T09:27:25.584500+00:00"},{"alias_kind":"pith_short_16","alias_value":"Z7SKC2FQHCDXRTXF","created_at":"2026-07-05T09:27:25.584500+00:00"},{"alias_kind":"pith_short_8","alias_value":"Z7SKC2FQ","created_at":"2026-07-05T09:27:25.584500+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.20291","citing_title":"Fine-structure Preserved Real-world Image Super-resolution via Transfer VAE Training","ref_index":2,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6","json":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6.json","graph_json":"https://pith.science/api/pith-number/Z7SKC2FQHCDXRTXFRYK7EYBSE6/graph.json","events_json":"https://pith.science/api/pith-number/Z7SKC2FQHCDXRTXFRYK7EYBSE6/events.json","paper":"https://pith.science/paper/Z7SKC2FQ"},"agent_actions":{"view_html":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6","download_json":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6.json","view_paper":"https://pith.science/paper/Z7SKC2FQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.18666&json=true","fetch_graph":"https://pith.science/api/pith-number/Z7SKC2FQHCDXRTXFRYK7EYBSE6/graph.json","fetch_events":"https://pith.science/api/pith-number/Z7SKC2FQHCDXRTXFRYK7EYBSE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6/action/storage_attestation","attest_author":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6/action/author_attestation","sign_citation":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6/action/citation_signature","submit_replication":"https://pith.science/pith/Z7SKC2FQHCDXRTXFRYK7EYBSE6/action/replication_record"}},"created_at":"2026-07-05T09:27:25.584500+00:00","updated_at":"2026-07-05T09:27:25.584500+00:00"}