{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:WHEKQM5KJYEI5RELMIQDY7IJ7N","short_pith_number":"pith:WHEKQM5K","schema_version":"1.0","canonical_sha256":"b1c8a833aa4e088ec48b62203c7d09fb41eed58363bbc5451a991afb68e7582a","source":{"kind":"arxiv","id":"2406.03323","version":2},"attestation_state":"computed","paper":{"title":"Comparative Benchmarking of Failure Detection Methods in Medical Image Segmentation: Unveiling the Role of Confidence Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Zimmerer, Fabian Isensee, Jeremias Traub, Klaus Maier-Hein, Maximilian Zenk, Paul F. J\\\"ager, Tobias Norajitra","submitted_at":"2024-06-05T14:36:33Z","abstract_excerpt":"Semantic segmentation is an essential component of medical image analysis research, with recent deep learning algorithms offering out-of-the-box applicability across diverse datasets. Despite these advancements, segmentation failures remain a significant concern for real-world clinical applications, necessitating reliable detection mechanisms. This paper introduces a comprehensive benchmarking framework aimed at evaluating failure detection methodologies within medical image segmentation. Through our analysis, we identify the strengths and limitations of current failure detection metrics, advo"},"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":"2406.03323","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2024-06-05T14:36:33Z","cross_cats_sorted":[],"title_canon_sha256":"89f0362975e04fd10be68230552c245c429ca5844708353d36621a69fbab6ee2","abstract_canon_sha256":"91261577041bf2ee91988a89f54b686b0318f1aac4edd16403b6264c2ac59568"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:51.308104Z","signature_b64":"TXcjclMILg8RCVVuwjq94h+nm28kpop2v7BXS5xUmjoffy4flstQQGGrLQGW5Tm+0zd4pJPDrzI5zjxXsZ68Cw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b1c8a833aa4e088ec48b62203c7d09fb41eed58363bbc5451a991afb68e7582a","last_reissued_at":"2026-07-05T09:23:51.307367Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:51.307367Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparative Benchmarking of Failure Detection Methods in Medical Image Segmentation: Unveiling the Role of Confidence Aggregation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"David Zimmerer, Fabian Isensee, Jeremias Traub, Klaus Maier-Hein, Maximilian Zenk, Paul F. J\\\"ager, Tobias Norajitra","submitted_at":"2024-06-05T14:36:33Z","abstract_excerpt":"Semantic segmentation is an essential component of medical image analysis research, with recent deep learning algorithms offering out-of-the-box applicability across diverse datasets. Despite these advancements, segmentation failures remain a significant concern for real-world clinical applications, necessitating reliable detection mechanisms. This paper introduces a comprehensive benchmarking framework aimed at evaluating failure detection methodologies within medical image segmentation. Through our analysis, we identify the strengths and limitations of current failure detection metrics, advo"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.03323","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/2406.03323/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":"2406.03323","created_at":"2026-07-05T09:23:51.307471+00:00"},{"alias_kind":"arxiv_version","alias_value":"2406.03323v2","created_at":"2026-07-05T09:23:51.307471+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.03323","created_at":"2026-07-05T09:23:51.307471+00:00"},{"alias_kind":"pith_short_12","alias_value":"WHEKQM5KJYEI","created_at":"2026-07-05T09:23:51.307471+00:00"},{"alias_kind":"pith_short_16","alias_value":"WHEKQM5KJYEI5REL","created_at":"2026-07-05T09:23:51.307471+00:00"},{"alias_kind":"pith_short_8","alias_value":"WHEKQM5K","created_at":"2026-07-05T09:23:51.307471+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/WHEKQM5KJYEI5RELMIQDY7IJ7N","json":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N.json","graph_json":"https://pith.science/api/pith-number/WHEKQM5KJYEI5RELMIQDY7IJ7N/graph.json","events_json":"https://pith.science/api/pith-number/WHEKQM5KJYEI5RELMIQDY7IJ7N/events.json","paper":"https://pith.science/paper/WHEKQM5K"},"agent_actions":{"view_html":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N","download_json":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N.json","view_paper":"https://pith.science/paper/WHEKQM5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2406.03323&json=true","fetch_graph":"https://pith.science/api/pith-number/WHEKQM5KJYEI5RELMIQDY7IJ7N/graph.json","fetch_events":"https://pith.science/api/pith-number/WHEKQM5KJYEI5RELMIQDY7IJ7N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N/action/storage_attestation","attest_author":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N/action/author_attestation","sign_citation":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N/action/citation_signature","submit_replication":"https://pith.science/pith/WHEKQM5KJYEI5RELMIQDY7IJ7N/action/replication_record"}},"created_at":"2026-07-05T09:23:51.307471+00:00","updated_at":"2026-07-05T09:23:51.307471+00:00"}