{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:JADALDMDYIVQO6J6VHVOU3M2I3","short_pith_number":"pith:JADALDMD","schema_version":"1.0","canonical_sha256":"4806058d83c22b07793ea9eaea6d9a46da40bd96deeae965d78019f90811cb27","source":{"kind":"arxiv","id":"2607.11542","version":1},"attestation_state":"computed","paper":{"title":"Condition-Stratified Robustness Analysis of Post-Hoc Calibration Methods for Probabilistic Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gurdeep Singh Virdee","submitted_at":"2026-07-13T13:28:31Z","abstract_excerpt":"Post-hoc calibration is widely adopted to correct probability estimates from trained classifiers, yet most evaluations report aggregate performance without testing whether that performance holds across distinct operating conditions within a single dataset. We present a pre-registered, condition-stratified robustness analysis comparing temperature scaling (TEMP) and isotonic regression (ISO) across four controlled conditions (C1--C4). Four hypothesis groups are evaluated: discrimination deltas with Holm-corrected multiplicity control (H1), Brier score differences (H2), calibration slope outcome"},"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":"2607.11542","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-13T13:28:31Z","cross_cats_sorted":[],"title_canon_sha256":"5197f1a114ec49353cdbafd5451113e8b439b0fc1edd62a366bd2822c4b936b9","abstract_canon_sha256":"4fe6233ef5d6c01d914e5c65530492533e461c85f2cdc3bb933edcb2cebfa41d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-14T02:22:09.974834Z","signature_b64":"ruJriw0YkBwJ2CS5tS4W5mSoAXyPn79Xphwt6q5stuhVraUq2ozsDxcoTQ398GHabp9LFXO+PE5LM8hg3h19CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4806058d83c22b07793ea9eaea6d9a46da40bd96deeae965d78019f90811cb27","last_reissued_at":"2026-07-14T02:22:09.974033Z","signature_status":"signed_v1","first_computed_at":"2026-07-14T02:22:09.974033Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Condition-Stratified Robustness Analysis of Post-Hoc Calibration Methods for Probabilistic Classifiers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Gurdeep Singh Virdee","submitted_at":"2026-07-13T13:28:31Z","abstract_excerpt":"Post-hoc calibration is widely adopted to correct probability estimates from trained classifiers, yet most evaluations report aggregate performance without testing whether that performance holds across distinct operating conditions within a single dataset. We present a pre-registered, condition-stratified robustness analysis comparing temperature scaling (TEMP) and isotonic regression (ISO) across four controlled conditions (C1--C4). Four hypothesis groups are evaluated: discrimination deltas with Holm-corrected multiplicity control (H1), Brier score differences (H2), calibration slope outcome"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.11542","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/2607.11542/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":"2607.11542","created_at":"2026-07-14T02:22:09.974450+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.11542v1","created_at":"2026-07-14T02:22:09.974450+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.11542","created_at":"2026-07-14T02:22:09.974450+00:00"},{"alias_kind":"pith_short_12","alias_value":"JADALDMDYIVQ","created_at":"2026-07-14T02:22:09.974450+00:00"},{"alias_kind":"pith_short_16","alias_value":"JADALDMDYIVQO6J6","created_at":"2026-07-14T02:22:09.974450+00:00"},{"alias_kind":"pith_short_8","alias_value":"JADALDMD","created_at":"2026-07-14T02:22:09.974450+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/JADALDMDYIVQO6J6VHVOU3M2I3","json":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3.json","graph_json":"https://pith.science/api/pith-number/JADALDMDYIVQO6J6VHVOU3M2I3/graph.json","events_json":"https://pith.science/api/pith-number/JADALDMDYIVQO6J6VHVOU3M2I3/events.json","paper":"https://pith.science/paper/JADALDMD"},"agent_actions":{"view_html":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3","download_json":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3.json","view_paper":"https://pith.science/paper/JADALDMD","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.11542&json=true","fetch_graph":"https://pith.science/api/pith-number/JADALDMDYIVQO6J6VHVOU3M2I3/graph.json","fetch_events":"https://pith.science/api/pith-number/JADALDMDYIVQO6J6VHVOU3M2I3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3/action/storage_attestation","attest_author":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3/action/author_attestation","sign_citation":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3/action/citation_signature","submit_replication":"https://pith.science/pith/JADALDMDYIVQO6J6VHVOU3M2I3/action/replication_record"}},"created_at":"2026-07-14T02:22:09.974450+00:00","updated_at":"2026-07-14T02:22:09.974450+00:00"}