{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:B2Q3X7WS376TYG5RN7JZHE4RAY","short_pith_number":"pith:B2Q3X7WS","schema_version":"1.0","canonical_sha256":"0ea1bbfed2dffd3c1bb16fd39393910638e6b42e6e0110ca4fbf668b9a230669","source":{"kind":"arxiv","id":"2205.11454","version":1},"attestation_state":"computed","paper":{"title":"What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Heim, Jacob Oaks, John Kirchenbauer","submitted_at":"2022-05-23T16:45:02Z","abstract_excerpt":"Classifier calibration has received recent attention from the machine learning community due both to its practical utility in facilitating decision making, as well as the observation that modern neural network classifiers are poorly calibrated. Much of this focus has been towards the goal of learning classifiers such that their output with largest magnitude (the \"predicted class\") is calibrated. However, this narrow interpretation of classifier outputs does not adequately capture the variety of practical use cases in which classifiers can aid in decision making. In this work, we argue that mor"},"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":"2205.11454","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2022-05-23T16:45:02Z","cross_cats_sorted":[],"title_canon_sha256":"312cee2d124004daefa738670db9fa4af633c010ba177f5f85a747a2619413c2","abstract_canon_sha256":"f8e08ec5d2ef29bbaffe543d95decd75f79dfe50a6a7602db6835019c9a45b6f"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:25:37.432797Z","signature_b64":"zk5cG9tBZZJatyEGB2gbx/yVZbcKIdQvhdVQPI9h/NK51G8mXljOCDsmRp72OpaZZmvOcGfEj8EvvjGWNRS3CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0ea1bbfed2dffd3c1bb16fd39393910638e6b42e6e0110ca4fbf668b9a230669","last_reissued_at":"2026-07-05T04:25:37.432462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:25:37.432462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What is Your Metric Telling You? Evaluating Classifier Calibration under Context-Specific Definitions of Reliability","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Eric Heim, Jacob Oaks, John Kirchenbauer","submitted_at":"2022-05-23T16:45:02Z","abstract_excerpt":"Classifier calibration has received recent attention from the machine learning community due both to its practical utility in facilitating decision making, as well as the observation that modern neural network classifiers are poorly calibrated. Much of this focus has been towards the goal of learning classifiers such that their output with largest magnitude (the \"predicted class\") is calibrated. However, this narrow interpretation of classifier outputs does not adequately capture the variety of practical use cases in which classifiers can aid in decision making. In this work, we argue that mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.11454","kind":"arxiv","version":1},"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/2205.11454/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":"2205.11454","created_at":"2026-07-05T04:25:37.432514+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.11454v1","created_at":"2026-07-05T04:25:37.432514+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.11454","created_at":"2026-07-05T04:25:37.432514+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2Q3X7WS376T","created_at":"2026-07-05T04:25:37.432514+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2Q3X7WS376TYG5R","created_at":"2026-07-05T04:25:37.432514+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2Q3X7WS","created_at":"2026-07-05T04:25:37.432514+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/B2Q3X7WS376TYG5RN7JZHE4RAY","json":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY.json","graph_json":"https://pith.science/api/pith-number/B2Q3X7WS376TYG5RN7JZHE4RAY/graph.json","events_json":"https://pith.science/api/pith-number/B2Q3X7WS376TYG5RN7JZHE4RAY/events.json","paper":"https://pith.science/paper/B2Q3X7WS"},"agent_actions":{"view_html":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY","download_json":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY.json","view_paper":"https://pith.science/paper/B2Q3X7WS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.11454&json=true","fetch_graph":"https://pith.science/api/pith-number/B2Q3X7WS376TYG5RN7JZHE4RAY/graph.json","fetch_events":"https://pith.science/api/pith-number/B2Q3X7WS376TYG5RN7JZHE4RAY/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY/action/storage_attestation","attest_author":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY/action/author_attestation","sign_citation":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY/action/citation_signature","submit_replication":"https://pith.science/pith/B2Q3X7WS376TYG5RN7JZHE4RAY/action/replication_record"}},"created_at":"2026-07-05T04:25:37.432514+00:00","updated_at":"2026-07-05T04:25:37.432514+00:00"}