{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:CSKU2NYWFUI6CUL6GQYSZXIP3H","short_pith_number":"pith:CSKU2NYW","schema_version":"1.0","canonical_sha256":"14954d37162d11e1517e34312cdd0fd9e69398f375744a332dfefb1f9853d6b8","source":{"kind":"arxiv","id":"2607.16344","version":1},"attestation_state":"computed","paper":{"title":"Benchmarking Goodness-of-Fit and Calibration Algorithms for Logistic Regression Classifiers: A Large-Scale Simulation Study under Sparse Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ME","authors_text":"Ahmed El-Kotory, Ebrahim Khaled Ebrahim","submitted_at":"2026-07-16T20:55:37Z","abstract_excerpt":"Binary logistic regression is among the most widely used classification algorithms, yet a classifier is only trustworthy if its predicted probabilities are well calibrated. The classical checks -- the Pearson chi-square and deviance statistics -- break down precisely in the modern setting where predictors are continuous and the data are sparse (one covariate pattern per observation). Four decades of research have produced dozens of alternative goodness-of-fit and calibration algorithms, yet practitioners still default to the Hosmer-Lemeshow test because it ships with their software. This paper"},"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":"2607.16344","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ME","submitted_at":"2026-07-16T20:55:37Z","cross_cats_sorted":["stat.AP"],"title_canon_sha256":"5f8cfb83a5fbb3b1bdc976bff3f900d2772d42e8f1c564377913e388fb447979","abstract_canon_sha256":"284b1100d746ce50e6187a302aee022b8e26004f67ade3b751937a69ab69f025"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-21T00:20:13.369336Z","signature_b64":"3yyNJ8OJ7wmXs+y2DpABifiyz7TRyfy9p5rOv3JTcRe3iWd/2+ewftgu7mY7Lvrp76ZngDRUjQlXe4WWO0w4AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"14954d37162d11e1517e34312cdd0fd9e69398f375744a332dfefb1f9853d6b8","last_reissued_at":"2026-07-21T00:20:13.368400Z","signature_status":"signed_v1","first_computed_at":"2026-07-21T00:20:13.368400Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking Goodness-of-Fit and Calibration Algorithms for Logistic Regression Classifiers: A Large-Scale Simulation Study under Sparse Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.AP"],"primary_cat":"stat.ME","authors_text":"Ahmed El-Kotory, Ebrahim Khaled Ebrahim","submitted_at":"2026-07-16T20:55:37Z","abstract_excerpt":"Binary logistic regression is among the most widely used classification algorithms, yet a classifier is only trustworthy if its predicted probabilities are well calibrated. The classical checks -- the Pearson chi-square and deviance statistics -- break down precisely in the modern setting where predictors are continuous and the data are sparse (one covariate pattern per observation). Four decades of research have produced dozens of alternative goodness-of-fit and calibration algorithms, yet practitioners still default to the Hosmer-Lemeshow test because it ships with their software. This paper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.16344","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/2607.16344/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":"2607.16344","created_at":"2026-07-21T00:20:13.368874+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.16344v1","created_at":"2026-07-21T00:20:13.368874+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.16344","created_at":"2026-07-21T00:20:13.368874+00:00"},{"alias_kind":"pith_short_12","alias_value":"CSKU2NYWFUI6","created_at":"2026-07-21T00:20:13.368874+00:00"},{"alias_kind":"pith_short_16","alias_value":"CSKU2NYWFUI6CUL6","created_at":"2026-07-21T00:20:13.368874+00:00"},{"alias_kind":"pith_short_8","alias_value":"CSKU2NYW","created_at":"2026-07-21T00:20:13.368874+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/CSKU2NYWFUI6CUL6GQYSZXIP3H","json":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H.json","graph_json":"https://pith.science/api/pith-number/CSKU2NYWFUI6CUL6GQYSZXIP3H/graph.json","events_json":"https://pith.science/api/pith-number/CSKU2NYWFUI6CUL6GQYSZXIP3H/events.json","paper":"https://pith.science/paper/CSKU2NYW"},"agent_actions":{"view_html":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H","download_json":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H.json","view_paper":"https://pith.science/paper/CSKU2NYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.16344&json=true","fetch_graph":"https://pith.science/api/pith-number/CSKU2NYWFUI6CUL6GQYSZXIP3H/graph.json","fetch_events":"https://pith.science/api/pith-number/CSKU2NYWFUI6CUL6GQYSZXIP3H/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H/action/storage_attestation","attest_author":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H/action/author_attestation","sign_citation":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H/action/citation_signature","submit_replication":"https://pith.science/pith/CSKU2NYWFUI6CUL6GQYSZXIP3H/action/replication_record"}},"created_at":"2026-07-21T00:20:13.368874+00:00","updated_at":"2026-07-21T00:20:13.368874+00:00"}