{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7OPN66RJ3H4PFSIN57ZSFWQXOR","short_pith_number":"pith:7OPN66RJ","schema_version":"1.0","canonical_sha256":"fb9edf7a29d9f8f2c90deff322da17746d15a6bd5b9f9ec618db422c19d1792d","source":{"kind":"arxiv","id":"2407.01032","version":2},"attestation_state":"computed","paper":{"title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ME"],"primary_cat":"cs.LG","authors_text":"Carsten T. L\\\"uth, Jeremias Traub, Klaus H. Maier-Hein, Lena Maier-Hein, Michael Baumgartner, Paul F Jaeger, Till J. Bungert","submitted_at":"2024-07-01T07:32:58Z","abstract_excerpt":"Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the $\\mathrm{AUROC}$ in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, inte"},"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":"2407.01032","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-07-01T07:32:58Z","cross_cats_sorted":["cs.CV","stat.ME"],"title_canon_sha256":"c3fa591890bcc1c25f4c247ae5ff23df88a533a8b1826f47cddd429dbc62025a","abstract_canon_sha256":"0327b881e60349a996120a004f188cd1007d7bd15ec483a9f882064d9f385ede"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:22:40.987610Z","signature_b64":"znw4ZT5rOa8lxDzkFL3c74cox/G/ouqaRkOIwOVpCsZuhFBUqDIgfbaNyiJsJXqRR0o70M5y2+yl9BUdxBKJCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fb9edf7a29d9f8f2c90deff322da17746d15a6bd5b9f9ec618db422c19d1792d","last_reissued_at":"2026-07-05T09:22:40.987096Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:22:40.987096Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Overcoming Common Flaws in the Evaluation of Selective Classification Systems","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","stat.ME"],"primary_cat":"cs.LG","authors_text":"Carsten T. L\\\"uth, Jeremias Traub, Klaus H. Maier-Hein, Lena Maier-Hein, Michael Baumgartner, Paul F Jaeger, Till J. Bungert","submitted_at":"2024-07-01T07:32:58Z","abstract_excerpt":"Selective Classification, wherein models can reject low-confidence predictions, promises reliable translation of machine-learning based classification systems to real-world scenarios such as clinical diagnostics. While current evaluation of these systems typically assumes fixed working points based on pre-defined rejection thresholds, methodological progress requires benchmarking the general performance of systems akin to the $\\mathrm{AUROC}$ in standard classification. In this work, we define 5 requirements for multi-threshold metrics in selective classification regarding task alignment, inte"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.01032","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/2407.01032/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":"2407.01032","created_at":"2026-07-05T09:22:40.987157+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.01032v2","created_at":"2026-07-05T09:22:40.987157+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.01032","created_at":"2026-07-05T09:22:40.987157+00:00"},{"alias_kind":"pith_short_12","alias_value":"7OPN66RJ3H4P","created_at":"2026-07-05T09:22:40.987157+00:00"},{"alias_kind":"pith_short_16","alias_value":"7OPN66RJ3H4PFSIN","created_at":"2026-07-05T09:22:40.987157+00:00"},{"alias_kind":"pith_short_8","alias_value":"7OPN66RJ","created_at":"2026-07-05T09:22:40.987157+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.24756","citing_title":"Proper Scoring Rules for Agentic Uncertainty Quantification","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2511.11934","citing_title":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","ref_index":13,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR","json":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR.json","graph_json":"https://pith.science/api/pith-number/7OPN66RJ3H4PFSIN57ZSFWQXOR/graph.json","events_json":"https://pith.science/api/pith-number/7OPN66RJ3H4PFSIN57ZSFWQXOR/events.json","paper":"https://pith.science/paper/7OPN66RJ"},"agent_actions":{"view_html":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR","download_json":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR.json","view_paper":"https://pith.science/paper/7OPN66RJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.01032&json=true","fetch_graph":"https://pith.science/api/pith-number/7OPN66RJ3H4PFSIN57ZSFWQXOR/graph.json","fetch_events":"https://pith.science/api/pith-number/7OPN66RJ3H4PFSIN57ZSFWQXOR/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR/action/storage_attestation","attest_author":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR/action/author_attestation","sign_citation":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR/action/citation_signature","submit_replication":"https://pith.science/pith/7OPN66RJ3H4PFSIN57ZSFWQXOR/action/replication_record"}},"created_at":"2026-07-05T09:22:40.987157+00:00","updated_at":"2026-07-05T09:22:40.987157+00:00"}