{"id":"W4392359402","doi":"10.21203/rs.3.rs-3996923/v1","title":"Interpretation Conclusion Stability of Software Defect Prediction over Time","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Software Engineering Research","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Polytechnique Montréal","funders":"","keywords":"Interpretation (philosophy); Stability (learning theory); Software; Computer science; Machine learning; 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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00437957,0.000975607,0.0009242627,0.002607991,0.0003308904,0.001697714,0.001130984,0.0008478182,0.0004725347],"category_scores_gemma":[0.02757028,0.0002800144,0.0005997072,0.001527404,0.0004512282,0.001652807,0.0007341331,0.001493213,0.0002396092],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001041394,"about_ca_system_score_gemma":0.000772592,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007527227,"about_ca_topic_score_gemma":0.004462799,"domain_scores_codex":[0.9966213,0.0006323226,0.0003177593,0.001133636,0.001114209,0.0001808421],"domain_scores_gemma":[0.9797249,0.01003087,0.002959939,0.002961122,0.003953023,0.0003700042],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0009279153,0.0003142852,0.260971,0.000213878,0.0003949738,0.0005002359,0.000565386,0.4290671,0.009553797,0.001181994,0.003160367,0.293149],"study_design_scores_gemma":[0.000005816089,0.00008698633,0.02133549,0.00001827679,0.00002758506,0.0001087941,0.00008908575,0.9724177,0.004630775,0.000878153,0.0003840092,0.00001741923],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7658035,0.0008844391,0.2285926,0.0003823519,0.0001004217,0.00007832628,0.001034114,0.002080705,0.001043535],"genre_scores_gemma":[0.9742799,0.00006529325,0.02440751,0.00002980513,0.00001911204,0.00001980053,0.0008535379,0.00004498329,0.0002799363],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.007527227,"threshold_uncertainty_score":0.02316165,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03091608569368675,"score_gpt":0.3536234347108503,"score_spread":0.3227073490171635,"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."}}