{"id":"W2047859318","doi":"10.1145/1538234.1538239","title":"Adding Test Generation to the Teaching Machine","year":2009,"lang":"en","type":"article","venue":"ACM Transactions on Computing Education","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Memorial University of Newfoundland","funders":"","keywords":"Plug-in; Computer science; Scripting language; Generator (circuit theory); Visualization; Extension (predicate logic); Field (mathematics); Programming language; Software engineering; Artificial intelligence; Theoretical computer science","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.0008385223,0.0001457114,0.00009421322,0.0001916683,0.001405611,0.0004306221,0.0008729193,0.00004467383,0.000004248056],"category_scores_gemma":[0.0003491571,0.0001210174,0.00006277279,0.0004020527,0.000008304887,0.0002332242,0.00001290188,0.0005826405,0.00006660409],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001069372,"about_ca_system_score_gemma":0.00009952326,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009637611,"about_ca_topic_score_gemma":0.00001556906,"domain_scores_codex":[0.9987411,0.0001837427,0.000216731,0.0003821728,0.0002271813,0.0002490343],"domain_scores_gemma":[0.9986167,0.0003577092,0.00008293363,0.0007977928,0.00005560954,0.00008922994],"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":[9.228067e-7,0.00020313,0.00003882857,0.000001574518,0.000003731344,1.751728e-7,0.003364394,0.02027659,0.0003263912,0.001410035,0.0006722064,0.973702],"study_design_scores_gemma":[0.0004898443,0.00120124,0.01665954,0.0003364865,0.00005604533,0.0001405739,0.0007794368,0.5781558,0.001817171,0.0008561349,0.3984501,0.001057655],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01371913,0.00004806881,0.959333,0.02474352,0.001227234,0.0002002732,6.489106e-7,0.0004515926,0.0002765407],"genre_scores_gemma":[0.7135693,0.000001079178,0.2838874,0.001934833,0.0003212152,0.000007773271,0.000005295252,0.000007602391,0.0002655236],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9726444,"threshold_uncertainty_score":0.9998944,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02250825520392931,"score_gpt":0.3034278843088667,"score_spread":0.2809196291049374,"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."}}