{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:YESMGGRECZMLDUC7LSKBLHMJEV","short_pith_number":"pith:YESMGGRE","schema_version":"1.0","canonical_sha256":"c124c31a241658b1d05f5c94159d89254da7b7412cc86fdb31fb804c279d3973","source":{"kind":"arxiv","id":"2305.18107","version":2},"attestation_state":"computed","paper":{"title":"Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Haoyu Chen, Jinjin Gu, Ruofan Zhang, Wenming Yang, Yulun Zhang","submitted_at":"2023-05-29T14:22:48Z","abstract_excerpt":"Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range degradations to enhance generalization, a decline in accuracy is inevitable. However, since the degradation in a certain real-world applications typically exhibits a limited variation range, it becomes feasible to strike a trade-off between generalization performance and testing accuracy within this scope. In this work, we introduce a novel approach to craft t"},"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":"2305.18107","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2023-05-29T14:22:48Z","cross_cats_sorted":["eess.IV"],"title_canon_sha256":"3df090d212772c07ed3e34af85920dd4dde66d8c3a2d32eb0d98d39d71455698","abstract_canon_sha256":"2a49b19a5f61108c4743485726b17f81b12b32d233cfc9ffa8aef8d587e399f9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:16:19.203513Z","signature_b64":"EvJmsMIBXW7MYEKyQBdByeTqU83V1ESmWW9OzTs8Cgl4yRFlO7YGXnxC/K8z+ETULSKmw0xbPpUIgdpqZDAsAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c124c31a241658b1d05f5c94159d89254da7b7412cc86fdb31fb804c279d3973","last_reissued_at":"2026-07-05T06:16:19.203040Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:16:19.203040Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Crafting Training Degradation Distribution for the Accuracy-Generalization Trade-off in Real-World Super-Resolution","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["eess.IV"],"primary_cat":"cs.CV","authors_text":"Chao Dong, Haoyu Chen, Jinjin Gu, Ruofan Zhang, Wenming Yang, Yulun Zhang","submitted_at":"2023-05-29T14:22:48Z","abstract_excerpt":"Super-resolution (SR) techniques designed for real-world applications commonly encounter two primary challenges: generalization performance and restoration accuracy. We demonstrate that when methods are trained using complex, large-range degradations to enhance generalization, a decline in accuracy is inevitable. However, since the degradation in a certain real-world applications typically exhibits a limited variation range, it becomes feasible to strike a trade-off between generalization performance and testing accuracy within this scope. In this work, we introduce a novel approach to craft t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.18107","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/2305.18107/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":"2305.18107","created_at":"2026-07-05T06:16:19.203101+00:00"},{"alias_kind":"arxiv_version","alias_value":"2305.18107v2","created_at":"2026-07-05T06:16:19.203101+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.18107","created_at":"2026-07-05T06:16:19.203101+00:00"},{"alias_kind":"pith_short_12","alias_value":"YESMGGRECZML","created_at":"2026-07-05T06:16:19.203101+00:00"},{"alias_kind":"pith_short_16","alias_value":"YESMGGRECZMLDUC7","created_at":"2026-07-05T06:16:19.203101+00:00"},{"alias_kind":"pith_short_8","alias_value":"YESMGGRE","created_at":"2026-07-05T06:16:19.203101+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV","json":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV.json","graph_json":"https://pith.science/api/pith-number/YESMGGRECZMLDUC7LSKBLHMJEV/graph.json","events_json":"https://pith.science/api/pith-number/YESMGGRECZMLDUC7LSKBLHMJEV/events.json","paper":"https://pith.science/paper/YESMGGRE"},"agent_actions":{"view_html":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV","download_json":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV.json","view_paper":"https://pith.science/paper/YESMGGRE","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2305.18107&json=true","fetch_graph":"https://pith.science/api/pith-number/YESMGGRECZMLDUC7LSKBLHMJEV/graph.json","fetch_events":"https://pith.science/api/pith-number/YESMGGRECZMLDUC7LSKBLHMJEV/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV/action/storage_attestation","attest_author":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV/action/author_attestation","sign_citation":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV/action/citation_signature","submit_replication":"https://pith.science/pith/YESMGGRECZMLDUC7LSKBLHMJEV/action/replication_record"}},"created_at":"2026-07-05T06:16:19.203101+00:00","updated_at":"2026-07-05T06:16:19.203101+00:00"}