{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002193665,0.0007417801,0.0004841695,0.00184621,0.0004346533,0.001359022,0.0006386586,0.0009442447,0.001416675],"category_scores_gemma":[0.02538785,0.0003450457,0.0004875403,0.001178613,0.0007129463,0.001427858,0.0007949417,0.0007398314,0.0005952677],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008557776,"about_ca_system_score_gemma":0.001279576,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005134372,"about_ca_topic_score_gemma":0.01039579,"domain_scores_codex":[0.9960646,0.001121353,0.0002551078,0.0008135345,0.001447558,0.0002978578],"domain_scores_gemma":[0.9786854,0.01144597,0.003611476,0.00220586,0.003391548,0.0006597223],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.000849898,0.0006535407,0.8180015,0.0004768014,0.0002165545,0.00166842,0.001999976,0.01677177,0.03518297,0.002027685,0.001710954,0.1204399],"study_design_scores_gemma":[0.00006283964,0.0008097538,0.7894753,0.0001235886,0.0003423742,0.001648449,0.002188195,0.1536548,0.03540228,0.00477956,0.01137568,0.0001372742],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9253641,0.0002496653,0.06456396,0.0002425421,0.00003678204,0.000348819,0.001429792,0.001877461,0.005886944],"genre_scores_gemma":[0.9720544,0.0001220688,0.02483709,0.00008150216,0.00001208924,0.0001682873,0.001257984,0.0002175305,0.001248993],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.005134372,"threshold_uncertainty_score":0.01160133,"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."}}