{"id":"W1981621595","doi":"10.1007/s10664-010-9132-x","title":"Testing the theory of relative defect proneness for closed-source software","year":2010,"lang":"en","type":"article","venue":"Empirical Software Engineering","topic":"Software Engineering Research","field":"Computer Science","cited_by":26,"is_retracted":false,"has_abstract":false,"ca_institutions":"Children's Hospital of Eastern Ontario","funders":"","keywords":"Open source software; Software; Open source; Computer science; Software engineering; Data science; Programming language","routes":{"ca_aff":true,"ca_fund":false,"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":["metaresearch","metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.00155779,0.0003288211,0.000354074,0.0001855556,0.0002137111,0.0001113804,0.001604791,0.0002030184,0.000009388659],"category_scores_gemma":[0.04230084,0.0002521103,0.0002514038,0.001116678,0.0001105668,0.0004060057,0.0004977867,0.0009222929,0.00001376148],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007001199,"about_ca_system_score_gemma":0.0001513918,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000008553082,"about_ca_topic_score_gemma":0.000001197733,"domain_scores_codex":[0.9976843,0.00007339687,0.0004206872,0.0005749086,0.0005363118,0.0007104018],"domain_scores_gemma":[0.9759064,0.02246416,0.0001130857,0.001005699,0.0003239105,0.0001867845],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00007928372,0.0003172047,0.679453,0.001077197,0.0004909778,0.00003567817,0.004433122,0.09814982,0.01251414,0.01438901,0.001398062,0.1876626],"study_design_scores_gemma":[0.00170402,0.0006327985,0.8597234,0.0004027479,0.0001027321,0.0001636397,0.00004504341,0.08449407,0.0155782,0.009582237,0.0257443,0.00182678],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2070379,0.00016295,0.7904332,0.0001230547,0.000546767,0.0005202464,0.000007225141,0.001160842,0.000007897891],"genre_scores_gemma":[0.6399484,6.529411e-7,0.3594208,0.00005103916,0.000211924,0.0002088252,0.000003406383,0.00007197061,0.00008292928],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.4329106,"threshold_uncertainty_score":0.9999931,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0349592160170909,"score_gpt":0.2819665391038704,"score_spread":0.2470073230867795,"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."}}