{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:55IRTDERV543JKV4363OYQHTFA","short_pith_number":"pith:55IRTDER","schema_version":"1.0","canonical_sha256":"ef51198c91af79b4aabcdfb6ec40f3282aa3a197b9d4bff72a2fb3b0776a954e","source":{"kind":"arxiv","id":"2001.08113","version":1},"attestation_state":"computed","paper":{"title":"DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dietmar Saupe, Hanhe Lin, Vlad Hosu","submitted_at":"2020-01-20T15:13:26Z","abstract_excerpt":"Multi-level deep-features have been driving state-of-the-art methods for aesthetics and image quality assessment (IQA). However, most IQA benchmarks are comprised of artificially distorted images, for which features derived from ImageNet under-perform. We propose a new IQA dataset and a weakly supervised feature learning approach to train features more suitable for IQA of artificially distorted images. The dataset, KADIS-700k, is far more extensive than similar works, consisting of 140,000 pristine images, 25 distortions types, totaling 700k distorted versions. Our weakly supervised feature le"},"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":"2001.08113","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"eess.IV","submitted_at":"2020-01-20T15:13:26Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"1ada88e99e2d4907b24f4d0461a20c872a46551368cf9163a524537ebfde4eb4","abstract_canon_sha256":"464e9c2356c9da642505ab2d9cf2b3289faa66e775d6d60c9fc37f5afbd26d3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:35:07.922101Z","signature_b64":"J1XX9JJL7LmCmDPP1XQP17M1c2hxj4Tt5W8uUOpr4UFnMziyMCDTSypM4KIJ3AwC79o/wC6RRfLRtSLJFTqwCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef51198c91af79b4aabcdfb6ec40f3282aa3a197b9d4bff72a2fb3b0776a954e","last_reissued_at":"2026-07-05T00:35:07.921751Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:35:07.921751Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeepFL-IQA: Weak Supervision for Deep IQA Feature Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"eess.IV","authors_text":"Dietmar Saupe, Hanhe Lin, Vlad Hosu","submitted_at":"2020-01-20T15:13:26Z","abstract_excerpt":"Multi-level deep-features have been driving state-of-the-art methods for aesthetics and image quality assessment (IQA). However, most IQA benchmarks are comprised of artificially distorted images, for which features derived from ImageNet under-perform. We propose a new IQA dataset and a weakly supervised feature learning approach to train features more suitable for IQA of artificially distorted images. The dataset, KADIS-700k, is far more extensive than similar works, consisting of 140,000 pristine images, 25 distortions types, totaling 700k distorted versions. Our weakly supervised feature le"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2001.08113","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/2001.08113/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":"2001.08113","created_at":"2026-07-05T00:35:07.921813+00:00"},{"alias_kind":"arxiv_version","alias_value":"2001.08113v1","created_at":"2026-07-05T00:35:07.921813+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2001.08113","created_at":"2026-07-05T00:35:07.921813+00:00"},{"alias_kind":"pith_short_12","alias_value":"55IRTDERV543","created_at":"2026-07-05T00:35:07.921813+00:00"},{"alias_kind":"pith_short_16","alias_value":"55IRTDERV543JKV4","created_at":"2026-07-05T00:35:07.921813+00:00"},{"alias_kind":"pith_short_8","alias_value":"55IRTDER","created_at":"2026-07-05T00:35:07.921813+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08563","citing_title":"Partial-Reference IQA Based on Hermite-Gauss Structural Prediction and Texture Deviation","ref_index":60,"is_internal_anchor":true},{"citing_arxiv_id":"2606.29162","citing_title":"Spatially Localized Image Degradation Embeddings for Image Quality Assessment","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA","json":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA.json","graph_json":"https://pith.science/api/pith-number/55IRTDERV543JKV4363OYQHTFA/graph.json","events_json":"https://pith.science/api/pith-number/55IRTDERV543JKV4363OYQHTFA/events.json","paper":"https://pith.science/paper/55IRTDER"},"agent_actions":{"view_html":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA","download_json":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA.json","view_paper":"https://pith.science/paper/55IRTDER","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2001.08113&json=true","fetch_graph":"https://pith.science/api/pith-number/55IRTDERV543JKV4363OYQHTFA/graph.json","fetch_events":"https://pith.science/api/pith-number/55IRTDERV543JKV4363OYQHTFA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA/action/storage_attestation","attest_author":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA/action/author_attestation","sign_citation":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA/action/citation_signature","submit_replication":"https://pith.science/pith/55IRTDERV543JKV4363OYQHTFA/action/replication_record"}},"created_at":"2026-07-05T00:35:07.921813+00:00","updated_at":"2026-07-05T00:35:07.921813+00:00"}