{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CSHNPZRF76XS7CMZFMRP4LPCEF","short_pith_number":"pith:CSHNPZRF","schema_version":"1.0","canonical_sha256":"148ed7e625ffaf2f89992b22fe2de2214265dbf458320137a52f3e1e1bbce563","source":{"kind":"arxiv","id":"2502.05275","version":2},"attestation_state":"computed","paper":{"title":"Interpretable Failure Detection with Human-Level Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kien X. Nguyen, Tang Li, Xi Peng","submitted_at":"2025-02-07T19:19:40Z","abstract_excerpt":"Reliable failure detection holds paramount importance in safety-critical applications. Yet, neural networks are known to produce overconfident predictions for misclassified samples. As a result, it remains a problematic matter as existing confidence score functions rely on category-level signals, the logits, to detect failures. This research introduces an innovative strategy, leveraging human-level concepts for a dual purpose: to reliably detect when a model fails and to transparently interpret why. By integrating a nuanced array of signals for each category, our method enables a finer-grained"},"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":"2502.05275","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CV","submitted_at":"2025-02-07T19:19:40Z","cross_cats_sorted":[],"title_canon_sha256":"808085eff8c5fc6a97f3be98a7ccd9d20fae14fd0c12cee4db49f6625d200734","abstract_canon_sha256":"9085ce11154307547b8a3e2a0bd0f586a1061a049ed3458d50eb73933c6f23bd"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:49:13.974105Z","signature_b64":"TlkMhl9Nonw4NMXAvEWTSsiNEd7a7t4lO6ohXBXX0d5OgNslSxQ+aJgXIekXXXXQ1sCeeC+Lm0UpJAxya2mMCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"148ed7e625ffaf2f89992b22fe2de2214265dbf458320137a52f3e1e1bbce563","last_reissued_at":"2026-07-05T10:49:13.973670Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:49:13.973670Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Interpretable Failure Detection with Human-Level Concepts","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CV","authors_text":"Kien X. Nguyen, Tang Li, Xi Peng","submitted_at":"2025-02-07T19:19:40Z","abstract_excerpt":"Reliable failure detection holds paramount importance in safety-critical applications. Yet, neural networks are known to produce overconfident predictions for misclassified samples. As a result, it remains a problematic matter as existing confidence score functions rely on category-level signals, the logits, to detect failures. This research introduces an innovative strategy, leveraging human-level concepts for a dual purpose: to reliably detect when a model fails and to transparently interpret why. By integrating a nuanced array of signals for each category, our method enables a finer-grained"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05275","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/2502.05275/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":"2502.05275","created_at":"2026-07-05T10:49:13.973726+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05275v2","created_at":"2026-07-05T10:49:13.973726+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05275","created_at":"2026-07-05T10:49:13.973726+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSHNPZRF76XS","created_at":"2026-07-05T10:49:13.973726+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSHNPZRF76XS7CMZ","created_at":"2026-07-05T10:49:13.973726+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSHNPZRF","created_at":"2026-07-05T10:49:13.973726+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/CSHNPZRF76XS7CMZFMRP4LPCEF","json":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF.json","graph_json":"https://pith.science/api/pith-number/CSHNPZRF76XS7CMZFMRP4LPCEF/graph.json","events_json":"https://pith.science/api/pith-number/CSHNPZRF76XS7CMZFMRP4LPCEF/events.json","paper":"https://pith.science/paper/CSHNPZRF"},"agent_actions":{"view_html":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF","download_json":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF.json","view_paper":"https://pith.science/paper/CSHNPZRF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05275&json=true","fetch_graph":"https://pith.science/api/pith-number/CSHNPZRF76XS7CMZFMRP4LPCEF/graph.json","fetch_events":"https://pith.science/api/pith-number/CSHNPZRF76XS7CMZFMRP4LPCEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF/action/storage_attestation","attest_author":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF/action/author_attestation","sign_citation":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF/action/citation_signature","submit_replication":"https://pith.science/pith/CSHNPZRF76XS7CMZFMRP4LPCEF/action/replication_record"}},"created_at":"2026-07-05T10:49:13.973726+00:00","updated_at":"2026-07-05T10:49:13.973726+00:00"}