{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005294155,0.0004951023,0.0005464179,0.004556218,0.00105661,0.001970578,0.001228392,0.001283695,0.001244393],"category_scores_gemma":[0.05363838,0.0002690509,0.0006646611,0.00573226,0.001325302,0.004814116,0.002234711,0.001756209,0.0008564665],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008973043,"about_ca_system_score_gemma":0.002049502,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003681867,"about_ca_topic_score_gemma":0.003813458,"domain_scores_codex":[0.9906985,0.004835891,0.0004863542,0.001622997,0.001923641,0.0004326806],"domain_scores_gemma":[0.9258142,0.03109038,0.00780481,0.02946981,0.005066675,0.0007541713],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001275975,0.001737305,0.3138395,0.001216826,0.0005604559,0.0008581134,0.005413889,0.1106008,0.01682765,0.0606988,0.04751479,0.439456],"study_design_scores_gemma":[0.0001022603,0.0003318764,0.1006273,0.0003259674,0.0002464826,0.001342581,0.004372085,0.6858599,0.02126292,0.1423418,0.0430617,0.0001251309],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7043728,0.0008783921,0.2645387,0.002258876,0.0002628644,0.0004838177,0.01930041,0.003294321,0.004609839],"genre_scores_gemma":[0.9042875,0.0003869478,0.07068875,0.0001752918,0.000105506,0.0001785222,0.0226957,0.0001946536,0.001287286],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005294155,"threshold_uncertainty_score":0.02799851,"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."}}