{"id":"W4243891992","doi":"10.1109/icse.2013.6606688","title":"On extracting unit tests from interactive live programming sessions","year":2013,"lang":"en","type":"article","venue":"2013 35th International Conference on Software Engineering (ICSE)","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":23,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"","keywords":"Computer science; Leverage (statistics); Session (web analytics); Unit testing; Cluster analysis; Software testing; Software; Software engineering; Machine learning; Programming language; World Wide Web","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":[0.001296451,0.0009993312,0.0007113195,0.003691797,0.0005800851,0.001522921,0.001774456,0.00103395,0.002616461],"category_scores_gemma":[0.02073801,0.0004133157,0.0004666643,0.003227851,0.0008118447,0.002169131,0.001241392,0.001185323,0.001495724],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003824886,"about_ca_system_score_gemma":0.0005596395,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001568562,"about_ca_topic_score_gemma":0.003126169,"domain_scores_codex":[0.9978797,0.000578217,0.0001690033,0.0004532664,0.0007806425,0.0001391963],"domain_scores_gemma":[0.9773187,0.0128087,0.002251208,0.004087348,0.003076507,0.0004574459],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0003676311,0.0002713019,0.01534836,0.0006122275,0.00006748667,0.001119861,0.00343245,0.01157147,0.07253344,0.0051244,0.003293751,0.8862577],"study_design_scores_gemma":[0.0001316206,0.0012507,0.1070989,0.0007557246,0.0002031014,0.006366993,0.004949175,0.4609155,0.2996387,0.05331427,0.06492903,0.0004463349],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09250413,0.0003378472,0.8962646,0.0001665641,0.00004536575,0.000374013,0.001194256,0.006712435,0.002400721],"genre_scores_gemma":[0.3354273,0.0004212474,0.6539699,0.00009482267,0.00006245427,0.0005257118,0.004680514,0.001329235,0.003488704],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.003691797,"threshold_uncertainty_score":0.008752942,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04223610172680727,"score_gpt":0.2958842169984304,"score_spread":0.2536481152716231,"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."}}