{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001900791,0.0003810175,0.0002566722,0.0003452325,0.000148071,0.0007022059,0.001341357,0.0001498937,0.0004033691],"category_scores_gemma":[0.002640151,0.0003605385,0.00009796749,0.0002325032,0.0000353884,0.0009055167,0.0003370986,0.0007618796,0.0007536424],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001675819,"about_ca_system_score_gemma":0.00009552713,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008704609,"about_ca_topic_score_gemma":0.000008935282,"domain_scores_codex":[0.9978811,0.00005015267,0.0003895471,0.0006671281,0.0005843462,0.0004277862],"domain_scores_gemma":[0.9964764,0.001882374,0.0002359492,0.0006198268,0.0005778651,0.0002075834],"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":[0.00009496175,0.001667734,0.04026071,0.0001106003,0.0007665096,0.0003131361,0.008225133,0.01412296,0.002647977,0.2082957,0.0630193,0.6604753],"study_design_scores_gemma":[0.0007622468,0.0005883548,0.03890965,0.003254939,0.00002251712,0.00005587935,0.0001256139,0.9060483,0.00159714,0.04281116,0.00419548,0.001628741],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07279126,0.00002878576,0.9129789,0.0009526746,0.001941386,0.0004400617,0.00002925638,0.009968048,0.0008696158],"genre_scores_gemma":[0.6816604,0.00000909034,0.3174731,0.0002455657,0.0001535225,0.0001520153,0.00003286829,0.00003410285,0.0002393993],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8919253,"threshold_uncertainty_score":0.9998847,"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."}}