{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:FDC43UBBB7FURBEC6JJAWKIBGO","short_pith_number":"pith:FDC43UBB","schema_version":"1.0","canonical_sha256":"28c5cdd0210fcb488482f2520b2901338ca8619a12c972744da8e4c2d38f261d","source":{"kind":"arxiv","id":"2211.15259","version":2},"attestation_state":"computed","paper":{"title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Carsten T. L\\\"uth, Lukas Klein, Paul F. Jaeger, Till J. Bungert","submitted_at":"2022-11-28T12:25:27Z","abstract_excerpt":"Reliable application of machine learning-based decision systems in the wild is one of the major challenges currently investigated by the field. A large portion of established approaches aims to detect erroneous predictions by means of assigning confidence scores. This confidence may be obtained by either quantifying the model's predictive uncertainty, learning explicit scoring functions, or assessing whether the input is in line with the training distribution. Curiously, while these approaches all state to address the same eventual goal of detecting failures of a classifier upon real-life appl"},"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":"2211.15259","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CV","submitted_at":"2022-11-28T12:25:27Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a7ac9f532c78f5d04d2fcea08ecd42fd926e4206b382d7ee8175213846d4c9b8","abstract_canon_sha256":"81d8120dcd57791219811abfa3eaa17860b5480c4251cc1c4dbc0f916a072e3e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:18.278270Z","signature_b64":"iE0nYr3LfrAApFYYi6AaZVSJufGzZMdV4X24SZpdHjkkBxkGmwoaTzG1U079Gsjd4BRk+sSV4wDPhxUbfWvbBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"28c5cdd0210fcb488482f2520b2901338ca8619a12c972744da8e4c2d38f261d","last_reissued_at":"2026-07-05T05:58:18.277845Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:18.277845Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Call to Reflect on Evaluation Practices for Failure Detection in Image Classification","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CV","authors_text":"Carsten T. L\\\"uth, Lukas Klein, Paul F. Jaeger, Till J. Bungert","submitted_at":"2022-11-28T12:25:27Z","abstract_excerpt":"Reliable application of machine learning-based decision systems in the wild is one of the major challenges currently investigated by the field. A large portion of established approaches aims to detect erroneous predictions by means of assigning confidence scores. This confidence may be obtained by either quantifying the model's predictive uncertainty, learning explicit scoring functions, or assessing whether the input is in line with the training distribution. Curiously, while these approaches all state to address the same eventual goal of detecting failures of a classifier upon real-life appl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.15259","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/2211.15259/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":"2211.15259","created_at":"2026-07-05T05:58:18.277902+00:00"},{"alias_kind":"arxiv_version","alias_value":"2211.15259v2","created_at":"2026-07-05T05:58:18.277902+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.15259","created_at":"2026-07-05T05:58:18.277902+00:00"},{"alias_kind":"pith_short_12","alias_value":"FDC43UBBB7FU","created_at":"2026-07-05T05:58:18.277902+00:00"},{"alias_kind":"pith_short_16","alias_value":"FDC43UBBB7FURBEC","created_at":"2026-07-05T05:58:18.277902+00:00"},{"alias_kind":"pith_short_8","alias_value":"FDC43UBB","created_at":"2026-07-05T05:58:18.277902+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.11934","citing_title":"A Systematic Analysis of Out-of-Distribution Detection Under Representation and Training Paradigm Shifts","ref_index":8,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO","json":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO.json","graph_json":"https://pith.science/api/pith-number/FDC43UBBB7FURBEC6JJAWKIBGO/graph.json","events_json":"https://pith.science/api/pith-number/FDC43UBBB7FURBEC6JJAWKIBGO/events.json","paper":"https://pith.science/paper/FDC43UBB"},"agent_actions":{"view_html":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO","download_json":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO.json","view_paper":"https://pith.science/paper/FDC43UBB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2211.15259&json=true","fetch_graph":"https://pith.science/api/pith-number/FDC43UBBB7FURBEC6JJAWKIBGO/graph.json","fetch_events":"https://pith.science/api/pith-number/FDC43UBBB7FURBEC6JJAWKIBGO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO/action/storage_attestation","attest_author":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO/action/author_attestation","sign_citation":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO/action/citation_signature","submit_replication":"https://pith.science/pith/FDC43UBBB7FURBEC6JJAWKIBGO/action/replication_record"}},"created_at":"2026-07-05T05:58:18.277902+00:00","updated_at":"2026-07-05T05:58:18.277902+00:00"}