{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:RTFKQRIPVELQSL5XSCTAJ5MA4E","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"c0e753d5b889372bb386356253755397b8869f61f20270648afb550230c71d94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T09:29:41Z","title_canon_sha256":"af2bad9ca3bbe47127609377c7ec6b9c99719a03b2a4f5774a565813d1debf65"},"schema_version":"1.0","source":{"id":"2505.11034","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11034","created_at":"2026-06-10T01:09:17Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11034v2","created_at":"2026-06-10T01:09:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11034","created_at":"2026-06-10T01:09:17Z"},{"alias_kind":"pith_short_12","alias_value":"RTFKQRIPVELQ","created_at":"2026-06-10T01:09:17Z"},{"alias_kind":"pith_short_16","alias_value":"RTFKQRIPVELQSL5X","created_at":"2026-06-10T01:09:17Z"},{"alias_kind":"pith_short_8","alias_value":"RTFKQRIP","created_at":"2026-06-10T01:09:17Z"}],"graph_snapshots":[{"event_id":"sha256:15e21b2fd8adade4734ee0dc635642f285454a9bb11f12c86230779c52e0f62b","target":"graph","created_at":"2026-06-10T01:09:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.11034/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T09:29:41Z","title":"CleanPatrick: A Benchmark for Image Data Cleaning"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11034","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b168597ec1086194ff05bc5674dfe8d91088cb2cf3c9976d61e016b1a398cd7f","target":"record","created_at":"2026-06-10T01:09:17Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"c0e753d5b889372bb386356253755397b8869f61f20270648afb550230c71d94","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2025-05-16T09:29:41Z","title_canon_sha256":"af2bad9ca3bbe47127609377c7ec6b9c99719a03b2a4f5774a565813d1debf65"},"schema_version":"1.0","source":{"id":"2505.11034","kind":"arxiv","version":2}},"canonical_sha256":"8ccaa8450fa917092fb790a604f580e1110b620bc6ffe508d1a35e73b5ab8896","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8ccaa8450fa917092fb790a604f580e1110b620bc6ffe508d1a35e73b5ab8896","first_computed_at":"2026-06-10T01:09:17.330117Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-10T01:09:17.330117Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"a8VhbbK44dw5UbxKf4geiWROA5qe0t+YpZb2IvNdGLNMbgze0cf5jU9ZasNVI2bsgy+UW7S9Eq0slIV0k/LsBQ==","signature_status":"signed_v1","signed_at":"2026-06-10T01:09:17.331237Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11034","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b168597ec1086194ff05bc5674dfe8d91088cb2cf3c9976d61e016b1a398cd7f","sha256:15e21b2fd8adade4734ee0dc635642f285454a9bb11f12c86230779c52e0f62b"],"state_sha256":"6748ae9e079f1cb732c69bf7bf628030fa9d407aa50d92fec2a6e3f14338d490"}