{"id":"W4384834957","doi":"10.1145/3593342.3593352","title":"spy3: A Python Subset for CS1","year":2023,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Python (programming language); Computer science; Programming language","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":[],"consensus_categories":[],"category_scores_codex":[0.0004933283,0.00005256458,0.00005951358,0.00007158934,0.0001301035,0.0001414644,0.0003498706,0.00002585273,0.000005090597],"category_scores_gemma":[0.0000875934,0.00004460265,0.00004733396,0.0003119681,0.000008205368,0.0001109185,0.0000897034,0.00007622738,0.0002583974],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007572718,"about_ca_system_score_gemma":0.00001564582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002522133,"about_ca_topic_score_gemma":0.000008217476,"domain_scores_codex":[0.9993794,0.00002635044,0.00007234179,0.0001981043,0.00009282145,0.0002310126],"domain_scores_gemma":[0.9995574,0.000124879,0.00001958062,0.0002381845,0.00001656171,0.0000433349],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000002038574,0.00001506467,0.0009570786,0.00001440592,0.000006891495,0.000005725331,0.001644837,0.0001592462,0.0001080842,0.08136546,0.02490893,0.8908122],"study_design_scores_gemma":[0.0001920737,0.00007819077,0.00283414,0.000008120053,0.00000175316,0.000004641653,0.00007186416,0.05996487,0.0001770301,0.001205029,0.9353399,0.0001223688],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01486425,0.00001501266,0.9785603,0.002939178,0.0003641704,0.0001056245,4.817875e-7,0.002174452,0.0009765618],"genre_scores_gemma":[0.6268636,0.00000195445,0.3576175,0.0003196872,0.0001253691,0.000044424,0.000008550146,0.00001434114,0.0150046],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.910431,"threshold_uncertainty_score":0.3321262,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03760042061524928,"score_gpt":0.3032821673837298,"score_spread":0.2656817467684805,"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."}}