{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:CK275V4BBPJBAA4NT4DWXPURHB","short_pith_number":"pith:CK275V4B","schema_version":"1.0","canonical_sha256":"12b5fed7810bd210038d9f076bbe9138705aed2549cfaced8c49e186b433be55","source":{"kind":"arxiv","id":"2205.14094","version":2},"attestation_state":"computed","paper":{"title":"Failure Detection in Medical Image Classification: A Reality Check and Benchmarking Testbed","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Glocker, Fabio De Sousa Ribeiro, Melanie Bernhardt","submitted_at":"2022-05-27T16:50:48Z","abstract_excerpt":"Failure detection in automated image classification is a critical safeguard for clinical deployment. Detected failure cases can be referred to human assessment, ensuring patient safety in computer-aided clinical decision making. Despite its paramount importance, there is insufficient evidence about the ability of state-of-the-art confidence scoring methods to detect test-time failures of classification models in the context of medical imaging. This paper provides a reality check, establishing the performance of in-domain misclassification detection methods, benchmarking 9 widely used confidenc"},"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":"2205.14094","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2022-05-27T16:50:48Z","cross_cats_sorted":[],"title_canon_sha256":"1d87e2d836c62d5bdf76aff0fcdda50ced2dd44e36f37bf2f16c227c5af4cc3f","abstract_canon_sha256":"9963a6794642d03c72c377034c15241aac6a67ce26135ae426a918a12cc8aac1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:09:18.799488Z","signature_b64":"eFYTXhJVNw7+LfnpszckjoV9XTHFw8RCX5nUfB7Zh3ZydKVJAyED4/ArZFrVVa2pzCMfVDelhnY1XPsjMw7uBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"12b5fed7810bd210038d9f076bbe9138705aed2549cfaced8c49e186b433be55","last_reissued_at":"2026-07-05T05:09:18.799060Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:09:18.799060Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Failure Detection in Medical Image Classification: A Reality Check and Benchmarking Testbed","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Ben Glocker, Fabio De Sousa Ribeiro, Melanie Bernhardt","submitted_at":"2022-05-27T16:50:48Z","abstract_excerpt":"Failure detection in automated image classification is a critical safeguard for clinical deployment. Detected failure cases can be referred to human assessment, ensuring patient safety in computer-aided clinical decision making. Despite its paramount importance, there is insufficient evidence about the ability of state-of-the-art confidence scoring methods to detect test-time failures of classification models in the context of medical imaging. This paper provides a reality check, establishing the performance of in-domain misclassification detection methods, benchmarking 9 widely used confidenc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.14094","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/2205.14094/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":"2205.14094","created_at":"2026-07-05T05:09:18.799116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.14094v2","created_at":"2026-07-05T05:09:18.799116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.14094","created_at":"2026-07-05T05:09:18.799116+00:00"},{"alias_kind":"pith_short_12","alias_value":"CK275V4BBPJB","created_at":"2026-07-05T05:09:18.799116+00:00"},{"alias_kind":"pith_short_16","alias_value":"CK275V4BBPJBAA4N","created_at":"2026-07-05T05:09:18.799116+00:00"},{"alias_kind":"pith_short_8","alias_value":"CK275V4B","created_at":"2026-07-05T05:09:18.799116+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/CK275V4BBPJBAA4NT4DWXPURHB","json":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB.json","graph_json":"https://pith.science/api/pith-number/CK275V4BBPJBAA4NT4DWXPURHB/graph.json","events_json":"https://pith.science/api/pith-number/CK275V4BBPJBAA4NT4DWXPURHB/events.json","paper":"https://pith.science/paper/CK275V4B"},"agent_actions":{"view_html":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB","download_json":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB.json","view_paper":"https://pith.science/paper/CK275V4B","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.14094&json=true","fetch_graph":"https://pith.science/api/pith-number/CK275V4BBPJBAA4NT4DWXPURHB/graph.json","fetch_events":"https://pith.science/api/pith-number/CK275V4BBPJBAA4NT4DWXPURHB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB/action/storage_attestation","attest_author":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB/action/author_attestation","sign_citation":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB/action/citation_signature","submit_replication":"https://pith.science/pith/CK275V4BBPJBAA4NT4DWXPURHB/action/replication_record"}},"created_at":"2026-07-05T05:09:18.799116+00:00","updated_at":"2026-07-05T05:09:18.799116+00:00"}