{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:7VUVNWRVVQS6W3FN26TIO3MJVT","short_pith_number":"pith:7VUVNWRV","schema_version":"1.0","canonical_sha256":"fd6956da35ac25eb6cadd7a6876d89acf22e5da09305520dde0407366e5a8861","source":{"kind":"arxiv","id":"2005.13983","version":6},"attestation_state":"computed","paper":{"title":"Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Guangtao Zhai, Kede Ma, Weixia Zhang, Xiaokang Yang","submitted_at":"2020-05-28T13:35:23Z","abstract_excerpt":"Performance of blind image quality assessment (BIQA) models has been significantly boosted by end-to-end optimization of feature engineering and quality regression. Nevertheless, due to the distributional shift between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa). To confront the cross-distortion-scenario challenge, we develop a \\textit{unified} BIQA model and an approach of training it for both synthetic and realistic distortions. We first sample p"},"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":"2005.13983","kind":"arxiv","version":6},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2020-05-28T13:35:23Z","cross_cats_sorted":["cs.LG","cs.MM","eess.IV"],"title_canon_sha256":"6c8aaaef3fed8630634c6df344c7b3c84fee84fd48d7c347d5179f5595615298","abstract_canon_sha256":"2d511d4f850ed19d6174e831a7cd7f9bcd42993901798aa5628700d1df9e6d03"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:29:27.047087Z","signature_b64":"5CKZ9DDKRN6G1JuctUTCwBdhhm6xA97mL5c6axacMY40L2AMkKFN552v+YXsQFxGKlyxgrPWl7U4/4a+L4UoAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd6956da35ac25eb6cadd7a6876d89acf22e5da09305520dde0407366e5a8861","last_reissued_at":"2026-07-05T02:29:27.046581Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:29:27.046581Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Uncertainty-Aware Blind Image Quality Assessment in the Laboratory and Wild","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","cs.MM","eess.IV"],"primary_cat":"cs.CV","authors_text":"Guangtao Zhai, Kede Ma, Weixia Zhang, Xiaokang Yang","submitted_at":"2020-05-28T13:35:23Z","abstract_excerpt":"Performance of blind image quality assessment (BIQA) models has been significantly boosted by end-to-end optimization of feature engineering and quality regression. Nevertheless, due to the distributional shift between images simulated in the laboratory and captured in the wild, models trained on databases with synthetic distortions remain particularly weak at handling realistic distortions (and vice versa). To confront the cross-distortion-scenario challenge, we develop a \\textit{unified} BIQA model and an approach of training it for both synthetic and realistic distortions. We first sample p"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2005.13983","kind":"arxiv","version":6},"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/2005.13983/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":"2005.13983","created_at":"2026-07-05T02:29:27.046636+00:00"},{"alias_kind":"arxiv_version","alias_value":"2005.13983v6","created_at":"2026-07-05T02:29:27.046636+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2005.13983","created_at":"2026-07-05T02:29:27.046636+00:00"},{"alias_kind":"pith_short_12","alias_value":"7VUVNWRVVQS6","created_at":"2026-07-05T02:29:27.046636+00:00"},{"alias_kind":"pith_short_16","alias_value":"7VUVNWRVVQS6W3FN","created_at":"2026-07-05T02:29:27.046636+00:00"},{"alias_kind":"pith_short_8","alias_value":"7VUVNWRV","created_at":"2026-07-05T02:29:27.046636+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.03494","citing_title":"Parameter-Efficient Adaptation of mPLUG-Owl2 via Pixel-Level Visual Prompts for NR-IQA","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT","json":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT.json","graph_json":"https://pith.science/api/pith-number/7VUVNWRVVQS6W3FN26TIO3MJVT/graph.json","events_json":"https://pith.science/api/pith-number/7VUVNWRVVQS6W3FN26TIO3MJVT/events.json","paper":"https://pith.science/paper/7VUVNWRV"},"agent_actions":{"view_html":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT","download_json":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT.json","view_paper":"https://pith.science/paper/7VUVNWRV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2005.13983&json=true","fetch_graph":"https://pith.science/api/pith-number/7VUVNWRVVQS6W3FN26TIO3MJVT/graph.json","fetch_events":"https://pith.science/api/pith-number/7VUVNWRVVQS6W3FN26TIO3MJVT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT/action/storage_attestation","attest_author":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT/action/author_attestation","sign_citation":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT/action/citation_signature","submit_replication":"https://pith.science/pith/7VUVNWRVVQS6W3FN26TIO3MJVT/action/replication_record"}},"created_at":"2026-07-05T02:29:27.046636+00:00","updated_at":"2026-07-05T02:29:27.046636+00:00"}