{"id":"W4399259577","doi":"10.1007/s10664-024-10464-6","title":"Towards graph-anonymization of software analytics data: empirical study on JIT defect prediction","year":2024,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"Queen's University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Analytics; Data mining; Empirical research; Software; Graph; Data science; Statistics; Theoretical computer science; Mathematics; Programming language","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001099028,0.0004526483,0.0005063902,0.0009186955,0.00009946365,0.0003233996,0.001861732,0.0002266685,0.00002380937],"category_scores_gemma":[0.006229357,0.0004240428,0.0002337683,0.003267763,0.00004527239,0.0008622362,0.0009741728,0.0008166108,0.00006087592],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002844596,"about_ca_system_score_gemma":0.0002517673,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000169892,"about_ca_topic_score_gemma":0.000002015661,"domain_scores_codex":[0.9958278,0.000108078,0.0006848006,0.001299192,0.001416858,0.0006632582],"domain_scores_gemma":[0.9949925,0.002480385,0.00006136293,0.00197608,0.0001840565,0.0003056106],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00002540039,0.0006886275,0.7455744,0.0005460212,0.0006158482,0.0002943575,0.001506175,0.2276895,0.00006553968,0.0001376036,0.01027621,0.01258031],"study_design_scores_gemma":[0.0006518567,0.001177516,0.6509946,0.0003906642,0.0001370474,0.00004722174,0.0000310984,0.3387888,0.0004210951,0.0002066943,0.006364909,0.0007884479],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1417712,0.000577612,0.8526489,0.0001667292,0.001246638,0.0004495954,0.00008178692,0.003047864,0.000009696723],"genre_scores_gemma":[0.9522227,0.00002132167,0.04702372,0.0000560525,0.0003574948,0.00006075718,0.00009486394,0.0001078649,0.00005519349],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8104516,"threshold_uncertainty_score":0.9998211,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06589437020513635,"score_gpt":0.3439454061040775,"score_spread":0.2780510358989411,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}