{"id":"W2166700159","doi":"10.1145/1985793.1985844","title":"Identifying program, test, and environmental changes that affect behaviour","year":2011,"lang":"en","type":"article","venue":"","topic":"Software Engineering Research","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"National Science Foundation","keywords":"Computer science; Test suite; Context (archaeology); XML; Affect (linguistics); Test (biology); Source code; Path (computing); Suite; Code (set theory); Test case; Programming language; Operating system; Psychology; Machine learning","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":[],"consensus_categories":[],"category_scores_codex":[0.0001557664,0.00008692521,0.00006594951,0.00007958145,0.00005097064,0.0001089536,0.0003598418,0.00003244812,0.0000516992],"category_scores_gemma":[0.00003413524,0.00007608617,0.00001703948,0.00008538088,0.00003883319,0.0002337196,0.0003749392,0.00008708452,0.00003307177],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002141419,"about_ca_system_score_gemma":0.000004722994,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004123978,"about_ca_topic_score_gemma":0.000008823023,"domain_scores_codex":[0.9992345,0.00001313961,0.00004389687,0.0002532848,0.0002094783,0.0002456919],"domain_scores_gemma":[0.9994686,0.0001443109,0.00001292167,0.0002762986,0.000003391506,0.00009452478],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[6.691619e-7,0.0001119729,0.9164447,0.00001381121,0.000006524012,0.00004247634,0.0008790884,1.094126e-7,0.001148819,0.0001950167,0.0001453295,0.08101147],"study_design_scores_gemma":[0.0001234183,0.0001894431,0.9758104,0.000011003,0.000003019064,0.00004308975,0.00005603348,0.001206583,0.02224253,0.00006907437,0.0001042511,0.0001411434],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9324496,0.0002785861,0.06542391,0.00007067948,0.0001510613,0.0003925332,0.000001829016,0.0008436233,0.0003881101],"genre_scores_gemma":[0.9493297,0.00002130586,0.05019418,0.00001695057,0.00001493626,0.00005270892,9.644397e-7,0.00000894957,0.0003603619],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.08087032,"threshold_uncertainty_score":0.3102704,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.061317746701398,"score_gpt":0.2783450713997178,"score_spread":0.2170273246983198,"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."}}