{"id":"W2143742229","doi":"10.5555/2486788.2486974","title":"On extracting unit tests from interactive live programming sessions","year":2013,"lang":"en","type":"article","venue":"International Conference on Software Engineering","topic":"Software Testing and Debugging Techniques","field":"Computer Science","cited_by":6,"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; Programming language; Machine learning; 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":[0.0001142358,0.0002575468,0.0001710442,0.0002586302,0.00009961083,0.0005374033,0.0009886523,0.00008924042,0.0002195071],"category_scores_gemma":[0.00280811,0.0002456674,0.00006839561,0.0001817968,0.00001951745,0.0007361813,0.0002394069,0.0005154423,0.0003601088],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001189211,"about_ca_system_score_gemma":0.00005740444,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003430884,"about_ca_topic_score_gemma":0.000003481207,"domain_scores_codex":[0.9985043,0.00003014018,0.0002637749,0.0004861616,0.0004228502,0.0002927899],"domain_scores_gemma":[0.997146,0.001807397,0.0001407939,0.0004158416,0.0003606527,0.0001292848],"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":[0.00004895519,0.0008757769,0.03042191,0.00004482415,0.0004009719,0.000269469,0.006648133,0.008295684,0.003445168,0.1302185,0.00807016,0.8112605],"study_design_scores_gemma":[0.0007551729,0.0005558832,0.04579778,0.003988251,0.00001708185,0.00006486694,0.0002046097,0.8785866,0.003903423,0.06259087,0.001923795,0.001611694],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1002345,0.00001237916,0.8877579,0.0004567443,0.00113001,0.0002582977,0.00001124959,0.009152884,0.0009860247],"genre_scores_gemma":[0.7185225,0.000002318186,0.2809724,0.0001732113,0.00009695776,0.0001113763,0.0000148936,0.00002011537,0.00008620846],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8702909,"threshold_uncertainty_score":0.9999996,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03945455755763936,"score_gpt":0.2990520090276418,"score_spread":0.2595974514700024,"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."}}