{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:RTFKQRIPVELQSL5XSCTAJ5MA4E","short_pith_number":"pith:RTFKQRIP","schema_version":"1.0","canonical_sha256":"8ccaa8450fa917092fb790a604f580e1110b620bc6ffe508d1a35e73b5ab8896","source":{"kind":"arxiv","id":"2505.11034","version":2},"attestation_state":"computed","paper":{"title":"CleanPatrick: A Benchmark for Image Data Cleaning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander A. Navarini, Alvaro Gonzalez-Jimenez, Arash Koochek, Elisabeth Victoria Goessinger, Fabian Gr\\\"oger, Hanna Lindemann, Ludovic Amruthalingam, Marc Pouly, Marie Bargiela, Marie Hofbauer, Matthew Groh, Omar Badri, Philippe Gottfrois, Philipp Tschandl, Simone Lionetti","submitted_at":"2025-05-16T09:29:41Z","abstract_excerpt":"Robust machine learning depends on clean data, yet current image data cleaning benchmarks rely on synthetic noise or narrow human studies, limiting comparison and real-world relevance. We introduce CleanPatrick, the first large-scale benchmark for data cleaning in the image domain, built upon the publicly available Fitzpatrick17k dermatology dataset. We collect 496,377 binary annotations from 933 medical crowd workers, identify off-topic samples (4%), near-duplicates (21%), and label errors (32%), and employ an aggregation model inspired by item-response theory followed by expert review to der"},"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":"2505.11034","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T09:29:41Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"af2bad9ca3bbe47127609377c7ec6b9c99719a03b2a4f5774a565813d1debf65","abstract_canon_sha256":"c0e753d5b889372bb386356253755397b8869f61f20270648afb550230c71d94"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-10T01:09:17.331237Z","signature_b64":"a8VhbbK44dw5UbxKf4geiWROA5qe0t+YpZb2IvNdGLNMbgze0cf5jU9ZasNVI2bsgy+UW7S9Eq0slIV0k/LsBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8ccaa8450fa917092fb790a604f580e1110b620bc6ffe508d1a35e73b5ab8896","last_reissued_at":"2026-06-10T01:09:17.330117Z","signature_status":"signed_v1","first_computed_at":"2026-06-10T01:09:17.330117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CleanPatrick: A Benchmark for Image Data Cleaning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CV","authors_text":"Alexander A. Navarini, Alvaro Gonzalez-Jimenez, Arash Koochek, Elisabeth Victoria Goessinger, Fabian Gr\\\"oger, Hanna Lindemann, Ludovic Amruthalingam, Marc Pouly, Marie Bargiela, Marie Hofbauer, Matthew Groh, Omar Badri, Philippe Gottfrois, Philipp Tschandl, Simone Lionetti","submitted_at":"2025-05-16T09:29:41Z","abstract_excerpt":"Robust machine learning depends on clean data, yet current image data cleaning benchmarks rely on synthetic noise or narrow human studies, limiting comparison and real-world relevance. We introduce CleanPatrick, the first large-scale benchmark for data cleaning in the image domain, built upon the publicly available Fitzpatrick17k dermatology dataset. We collect 496,377 binary annotations from 933 medical crowd workers, identify off-topic samples (4%), near-duplicates (21%), and label errors (32%), and employ an aggregation model inspired by item-response theory followed by expert review to der"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11034","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/2505.11034/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":"2505.11034","created_at":"2026-06-10T01:09:17.330280+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11034v2","created_at":"2026-06-10T01:09:17.330280+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11034","created_at":"2026-06-10T01:09:17.330280+00:00"},{"alias_kind":"pith_short_12","alias_value":"RTFKQRIPVELQ","created_at":"2026-06-10T01:09:17.330280+00:00"},{"alias_kind":"pith_short_16","alias_value":"RTFKQRIPVELQSL5X","created_at":"2026-06-10T01:09:17.330280+00:00"},{"alias_kind":"pith_short_8","alias_value":"RTFKQRIP","created_at":"2026-06-10T01:09:17.330280+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/RTFKQRIPVELQSL5XSCTAJ5MA4E","json":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E.json","graph_json":"https://pith.science/api/pith-number/RTFKQRIPVELQSL5XSCTAJ5MA4E/graph.json","events_json":"https://pith.science/api/pith-number/RTFKQRIPVELQSL5XSCTAJ5MA4E/events.json","paper":"https://pith.science/paper/RTFKQRIP"},"agent_actions":{"view_html":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E","download_json":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E.json","view_paper":"https://pith.science/paper/RTFKQRIP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11034&json=true","fetch_graph":"https://pith.science/api/pith-number/RTFKQRIPVELQSL5XSCTAJ5MA4E/graph.json","fetch_events":"https://pith.science/api/pith-number/RTFKQRIPVELQSL5XSCTAJ5MA4E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E/action/storage_attestation","attest_author":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E/action/author_attestation","sign_citation":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E/action/citation_signature","submit_replication":"https://pith.science/pith/RTFKQRIPVELQSL5XSCTAJ5MA4E/action/replication_record"}},"created_at":"2026-06-10T01:09:17.330280+00:00","updated_at":"2026-06-10T01:09:17.330280+00:00"}