{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:7HRYQCY3GPEANDA4FCVGNAYX5Y","short_pith_number":"pith:7HRYQCY3","schema_version":"1.0","canonical_sha256":"f9e3880b1b33c8068c1c28aa668317ee39ec99e13d1ceb7857538d9cd26fb07f","source":{"kind":"arxiv","id":"2508.04457","version":2},"attestation_state":"computed","paper":{"title":"Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jackie Ma, Simon Baur, Wojciech Samek","submitted_at":"2025-08-06T13:58:17Z","abstract_excerpt":"Reliable uncertainty quantification is crucial for trustworthy decision-making and the deployment of AI models in medical imaging. While prior work has explored the ability of neural networks to quantify predictive, epistemic, and aleatoric uncertainties using an information-theoretical approach in synthetic or well defined data settings like natural image classification, its applicability to real life medical diagnosis tasks remains underexplored. In this study, we provide an extensive uncertainty quantification benchmark for multi-label chest X-ray classification using the MIMIC-CXR-JPG data"},"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":"2508.04457","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"stat.ML","submitted_at":"2025-08-06T13:58:17Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"e9fb6d4ffb45f6aaf49be9c6890d8db2ef1ee0ac6eeaaa6b5d9c179bd0279630","abstract_canon_sha256":"b2b06ce6607d9c3c3468c48102f2cc6623e61dfdb7a19f82b24a90c6ad306777"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-01T01:02:18.257706Z","signature_b64":"VjunITUJXDYpxlwEXpefngDApEKH5LcXwV89lMX/R5C7pir2xpuBRXLoR8U42gK8/LkSGZJthFI+Q0VC8yhaDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f9e3880b1b33c8068c1c28aa668317ee39ec99e13d1ceb7857538d9cd26fb07f","last_reissued_at":"2026-06-01T01:02:18.256655Z","signature_status":"signed_v1","first_computed_at":"2026-06-01T01:02:18.256655Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Uncertainty and its Disentanglement in multi-label Chest X-Ray Classification","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Jackie Ma, Simon Baur, Wojciech Samek","submitted_at":"2025-08-06T13:58:17Z","abstract_excerpt":"Reliable uncertainty quantification is crucial for trustworthy decision-making and the deployment of AI models in medical imaging. While prior work has explored the ability of neural networks to quantify predictive, epistemic, and aleatoric uncertainties using an information-theoretical approach in synthetic or well defined data settings like natural image classification, its applicability to real life medical diagnosis tasks remains underexplored. In this study, we provide an extensive uncertainty quantification benchmark for multi-label chest X-ray classification using the MIMIC-CXR-JPG data"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.04457","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/2508.04457/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":"2508.04457","created_at":"2026-06-01T01:02:18.256791+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.04457v2","created_at":"2026-06-01T01:02:18.256791+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.04457","created_at":"2026-06-01T01:02:18.256791+00:00"},{"alias_kind":"pith_short_12","alias_value":"7HRYQCY3GPEA","created_at":"2026-06-01T01:02:18.256791+00:00"},{"alias_kind":"pith_short_16","alias_value":"7HRYQCY3GPEANDA4","created_at":"2026-06-01T01:02:18.256791+00:00"},{"alias_kind":"pith_short_8","alias_value":"7HRYQCY3","created_at":"2026-06-01T01:02:18.256791+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/7HRYQCY3GPEANDA4FCVGNAYX5Y","json":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y.json","graph_json":"https://pith.science/api/pith-number/7HRYQCY3GPEANDA4FCVGNAYX5Y/graph.json","events_json":"https://pith.science/api/pith-number/7HRYQCY3GPEANDA4FCVGNAYX5Y/events.json","paper":"https://pith.science/paper/7HRYQCY3"},"agent_actions":{"view_html":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y","download_json":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y.json","view_paper":"https://pith.science/paper/7HRYQCY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.04457&json=true","fetch_graph":"https://pith.science/api/pith-number/7HRYQCY3GPEANDA4FCVGNAYX5Y/graph.json","fetch_events":"https://pith.science/api/pith-number/7HRYQCY3GPEANDA4FCVGNAYX5Y/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y/action/storage_attestation","attest_author":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y/action/author_attestation","sign_citation":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y/action/citation_signature","submit_replication":"https://pith.science/pith/7HRYQCY3GPEANDA4FCVGNAYX5Y/action/replication_record"}},"created_at":"2026-06-01T01:02:18.256791+00:00","updated_at":"2026-06-01T01:02:18.256791+00:00"}