{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:7U7RTRA6OP7TS2GR4AHQCL7LW7","short_pith_number":"pith:7U7RTRA6","schema_version":"1.0","canonical_sha256":"fd3f19c41e73ff3968d1e00f012febb7f2d89f2f7ef1208dc4e68eeeab25c481","source":{"kind":"arxiv","id":"2607.01842","version":1},"attestation_state":"computed","paper":{"title":"Understanding Software Defect Prediction: A Large-scale Empirical Study Across Uncertainty Quantification and Performance Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ranjun Peng, Rubing Huang, WenBin He, Xuan Xie, Zhijie Wang","submitted_at":"2026-07-02T08:05:27Z","abstract_excerpt":"Software defect prediction (SDP) classifiers produce probabilities used for inspection prioritization, threshold tuning, and risk communication. Probability-based uncertainty quantification (UQ) characterizes prediction confidence, but whether common UQ metrics reliably indicate performance and calibration remains unclear. We conducted a large-scale empirical study of probability-based UQ for SDP. We evaluated five UQ metrics, six performance metrics, and three calibration metrics for 16 representative classifiers. We analyzed these relationships under two prediction settings: within-project d"},"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":"2607.01842","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.SE","submitted_at":"2026-07-02T08:05:27Z","cross_cats_sorted":[],"title_canon_sha256":"9f65c9c3e159ea33ac714f64b26ca9777525a95d07c5f7448154df7e0dc386f7","abstract_canon_sha256":"c8ec44c245916860a89018f97d1dae328ee604977239bbcffd518e1888508c89"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T01:17:31.388766Z","signature_b64":"gDBH4DSIABwKiq/kK/7cpaee7116tysiZi4ysahj0Q7T8kBAiUbVunBpkVSVFLtmMAzLLtl7ydzH1drCoBe7DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fd3f19c41e73ff3968d1e00f012febb7f2d89f2f7ef1208dc4e68eeeab25c481","last_reissued_at":"2026-07-03T01:17:31.388395Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T01:17:31.388395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Understanding Software Defect Prediction: A Large-scale Empirical Study Across Uncertainty Quantification and Performance Evaluation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.SE","authors_text":"Ranjun Peng, Rubing Huang, WenBin He, Xuan Xie, Zhijie Wang","submitted_at":"2026-07-02T08:05:27Z","abstract_excerpt":"Software defect prediction (SDP) classifiers produce probabilities used for inspection prioritization, threshold tuning, and risk communication. Probability-based uncertainty quantification (UQ) characterizes prediction confidence, but whether common UQ metrics reliably indicate performance and calibration remains unclear. We conducted a large-scale empirical study of probability-based UQ for SDP. We evaluated five UQ metrics, six performance metrics, and three calibration metrics for 16 representative classifiers. We analyzed these relationships under two prediction settings: within-project d"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01842","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/2607.01842/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":"2607.01842","created_at":"2026-07-03T01:17:31.388444+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01842v1","created_at":"2026-07-03T01:17:31.388444+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01842","created_at":"2026-07-03T01:17:31.388444+00:00"},{"alias_kind":"pith_short_12","alias_value":"7U7RTRA6OP7T","created_at":"2026-07-03T01:17:31.388444+00:00"},{"alias_kind":"pith_short_16","alias_value":"7U7RTRA6OP7TS2GR","created_at":"2026-07-03T01:17:31.388444+00:00"},{"alias_kind":"pith_short_8","alias_value":"7U7RTRA6","created_at":"2026-07-03T01:17:31.388444+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/7U7RTRA6OP7TS2GR4AHQCL7LW7","json":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7.json","graph_json":"https://pith.science/api/pith-number/7U7RTRA6OP7TS2GR4AHQCL7LW7/graph.json","events_json":"https://pith.science/api/pith-number/7U7RTRA6OP7TS2GR4AHQCL7LW7/events.json","paper":"https://pith.science/paper/7U7RTRA6"},"agent_actions":{"view_html":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7","download_json":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7.json","view_paper":"https://pith.science/paper/7U7RTRA6","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01842&json=true","fetch_graph":"https://pith.science/api/pith-number/7U7RTRA6OP7TS2GR4AHQCL7LW7/graph.json","fetch_events":"https://pith.science/api/pith-number/7U7RTRA6OP7TS2GR4AHQCL7LW7/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7/action/storage_attestation","attest_author":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7/action/author_attestation","sign_citation":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7/action/citation_signature","submit_replication":"https://pith.science/pith/7U7RTRA6OP7TS2GR4AHQCL7LW7/action/replication_record"}},"created_at":"2026-07-03T01:17:31.388444+00:00","updated_at":"2026-07-03T01:17:31.388444+00:00"}