{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001014509,0.0002375028,0.0002553242,0.0002970656,0.0001651662,0.0001482472,0.0004650967,0.0001677589,0.000004391011],"category_scores_gemma":[0.001732681,0.0002359464,0.00006323133,0.0006502048,0.00003525448,0.0003080885,0.00003586082,0.0005202289,0.000006924128],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003833137,"about_ca_system_score_gemma":0.00004407067,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006980098,"about_ca_topic_score_gemma":4.130914e-7,"domain_scores_codex":[0.9984988,0.000155735,0.0002443892,0.0005950379,0.0001373025,0.0003687389],"domain_scores_gemma":[0.9937888,0.005451973,0.00003051528,0.0005581787,0.00005436626,0.0001162124],"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":[0.000005658148,0.00002794928,0.00002060946,0.00008147678,0.00006339031,0.0000299532,0.0004494301,0.03542572,0.001805988,0.00155999,0.0009931903,0.9595367],"study_design_scores_gemma":[0.0001684916,0.0002382317,0.00004635299,0.0002748262,0.00004074526,0.0003653399,0.000009838456,0.9585621,0.003474042,0.033094,0.003241588,0.0004843929],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.001517384,0.001161237,0.9740168,0.0002777055,0.0004735666,0.00009113009,0.000007733946,0.02243738,0.00001702905],"genre_scores_gemma":[0.1220973,0.00003867004,0.8775322,0.0001189567,0.00002901192,0.00004188541,0.000003780938,0.00003730517,0.0001009244],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9590523,"threshold_uncertainty_score":0.9621617,"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."}}