{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:W6VQMIW4OCRDL6QFKYZT74SPCZ","short_pith_number":"pith:W6VQMIW4","schema_version":"1.0","canonical_sha256":"b7ab0622dc70a235fa0556333ff24f1645bac40ebebae6d4c1dff54c1daaf11e","source":{"kind":"arxiv","id":"2108.07948","version":1},"attestation_state":"computed","paper":{"title":"Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Heliang Zheng, Huan Yang, Jianlong Fu, Jiebo Luo, Zheng-Jun Zha","submitted_at":"2021-08-18T02:35:08Z","abstract_excerpt":"An important scenario for image quality assessment (IQA) is to evaluate image restoration (IR) algorithms. The state-of-the-art approaches adopt a full-reference paradigm that compares restored images with their corresponding pristine-quality images. However, pristine-quality images are usually unavailable in blind image restoration tasks and real-world scenarios. In this paper, we propose a practical solution named degraded-reference IQA (DR-IQA), which exploits the inputs of IR models, degraded images, as references. Specifically, we extract reference information from degraded images by dist"},"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":"2108.07948","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"eess.IV","submitted_at":"2021-08-18T02:35:08Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"18c168cb6ca91737553c727d7e644227d6b39edfdba47d046cda2fa4ddcbb029","abstract_canon_sha256":"0cf0f861fe92e969f506e874e095501e10b7fedfef2fce7cad01d66ca24397e9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:07:52.604300Z","signature_b64":"GttWUUn8Eah/eog3hipPmou69738bGafZjx3zWZRVps5kK69hB9THOtvJoqgFZHrut9sgiChkrfAcW803A2ADQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b7ab0622dc70a235fa0556333ff24f1645bac40ebebae6d4c1dff54c1daaf11e","last_reissued_at":"2026-07-05T03:07:52.603836Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:07:52.603836Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Conditional Knowledge Distillation for Degraded-Reference Image Quality Assessment","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Heliang Zheng, Huan Yang, Jianlong Fu, Jiebo Luo, Zheng-Jun Zha","submitted_at":"2021-08-18T02:35:08Z","abstract_excerpt":"An important scenario for image quality assessment (IQA) is to evaluate image restoration (IR) algorithms. The state-of-the-art approaches adopt a full-reference paradigm that compares restored images with their corresponding pristine-quality images. However, pristine-quality images are usually unavailable in blind image restoration tasks and real-world scenarios. In this paper, we propose a practical solution named degraded-reference IQA (DR-IQA), which exploits the inputs of IR models, degraded images, as references. Specifically, we extract reference information from degraded images by dist"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.07948","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/2108.07948/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":"2108.07948","created_at":"2026-07-05T03:07:52.603905+00:00"},{"alias_kind":"arxiv_version","alias_value":"2108.07948v1","created_at":"2026-07-05T03:07:52.603905+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.07948","created_at":"2026-07-05T03:07:52.603905+00:00"},{"alias_kind":"pith_short_12","alias_value":"W6VQMIW4OCRD","created_at":"2026-07-05T03:07:52.603905+00:00"},{"alias_kind":"pith_short_16","alias_value":"W6VQMIW4OCRDL6QF","created_at":"2026-07-05T03:07:52.603905+00:00"},{"alias_kind":"pith_short_8","alias_value":"W6VQMIW4","created_at":"2026-07-05T03:07:52.603905+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.05394","citing_title":"Reverse Browser: Vector-Image-to-Code Generator","ref_index":34,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ","json":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ.json","graph_json":"https://pith.science/api/pith-number/W6VQMIW4OCRDL6QFKYZT74SPCZ/graph.json","events_json":"https://pith.science/api/pith-number/W6VQMIW4OCRDL6QFKYZT74SPCZ/events.json","paper":"https://pith.science/paper/W6VQMIW4"},"agent_actions":{"view_html":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ","download_json":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ.json","view_paper":"https://pith.science/paper/W6VQMIW4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2108.07948&json=true","fetch_graph":"https://pith.science/api/pith-number/W6VQMIW4OCRDL6QFKYZT74SPCZ/graph.json","fetch_events":"https://pith.science/api/pith-number/W6VQMIW4OCRDL6QFKYZT74SPCZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ/action/storage_attestation","attest_author":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ/action/author_attestation","sign_citation":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ/action/citation_signature","submit_replication":"https://pith.science/pith/W6VQMIW4OCRDL6QFKYZT74SPCZ/action/replication_record"}},"created_at":"2026-07-05T03:07:52.603905+00:00","updated_at":"2026-07-05T03:07:52.603905+00:00"}