{"id":"W4396871671","doi":"10.1145/3664601","title":"Testing Updated Apps by Adapting Learned Models","year":2024,"lang":"en","type":"article","venue":"ACM Transactions on Software Engineering and Methodology","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Ottawa","funders":"Natural Sciences and Engineering Research Council of Canada; Centre National de la Recherche Scientifique","keywords":"Computer science; Correctness; Adaptation (eye); Software; Software inspection; Software performance testing; Machine learning; Software engineering; Human–computer interaction; Software development; Software quality; Operating system; Software construction; 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":[0.002897406,0.002508713,0.0009318402,0.001484956,0.0003499919,0.001724324,0.004376764,0.001499723,0.002371946],"category_scores_gemma":[0.03836945,0.00125799,0.001214625,0.0007159737,0.0008685481,0.004483138,0.003087291,0.002622931,0.001401534],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001108277,"about_ca_system_score_gemma":0.002342647,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007080216,"about_ca_topic_score_gemma":0.01132751,"domain_scores_codex":[0.9936081,0.001673045,0.0003616434,0.001625779,0.002364464,0.0003670272],"domain_scores_gemma":[0.9754047,0.0117328,0.001568644,0.007786157,0.003073535,0.000434097],"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":[0.001026814,0.001123839,0.0422955,0.0007685462,0.0003320799,0.00063785,0.0008145503,0.2526278,0.03093397,0.002528042,0.008327145,0.6585839],"study_design_scores_gemma":[0.00006108849,0.0003123198,0.003006128,0.00007535555,0.0001068337,0.0002688055,0.00009246977,0.9750768,0.01250501,0.003851343,0.004594381,0.00004948427],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3614489,0.001695807,0.5704099,0.0007734447,0.0002379842,0.0006603656,0.001506956,0.05716389,0.006102831],"genre_scores_gemma":[0.772447,0.0004720799,0.2185455,0.0004923003,0.00006006461,0.0004251816,0.002555338,0.00190624,0.003096318],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007080216,"threshold_uncertainty_score":0.01532316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1504107154579445,"score_gpt":0.3253355858346219,"score_spread":0.1749248703766774,"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."}}