{"id":"W4401413989","doi":"10.1109/cec60901.2024.10611881","title":"Emergent Discovery of Reinforced Programs using Q-Learning and Planning: A Proof of Concept","year":2024,"lang":"en","type":"article","venue":"","topic":"Teaching and Learning Programming","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Dalhousie University","funders":"","keywords":"Proof of concept; Computer science; Programming language; Artificial intelligence; Theoretical computer science; Operating system","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":[0.003128378,0.0008117635,0.0008944052,0.0003608247,0.0005961458,0.001180501,0.002037321,0.001405141,0.00460335],"category_scores_gemma":[0.01190244,0.0004795342,0.0009710875,0.0003211058,0.002169504,0.001656885,0.003046824,0.003139588,0.0004610399],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008715916,"about_ca_system_score_gemma":0.002960562,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002117393,"about_ca_topic_score_gemma":0.001967218,"domain_scores_codex":[0.9987464,0.0003807242,0.00004689751,0.0002731984,0.0004149316,0.0001378622],"domain_scores_gemma":[0.9943088,0.004329511,0.0003031552,0.0004152897,0.0003789922,0.0002642616],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001638873,0.0005200636,0.001437955,0.0002774523,0.00006993057,0.0002621528,0.0002541984,0.7113229,0.007481545,0.1454392,0.002634298,0.1301365],"study_design_scores_gemma":[0.00006145299,0.00006818373,0.00006835333,0.00001779268,0.000007521975,0.00003668955,0.0000108308,0.9740648,0.001634129,0.02306952,0.0009521662,0.000008538712],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009227085,0.00005131497,0.9870424,0.0003336391,0.00002754974,0.0001632157,0.00002048042,0.000512138,0.002622202],"genre_scores_gemma":[0.2682448,0.0001246427,0.7287062,0.0002297183,0.00003530186,0.0005566056,0.00005212512,0.0002190441,0.001831685],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00460335,"threshold_uncertainty_score":0.01654464,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03268827297966532,"score_gpt":0.3007368586964658,"score_spread":0.2680485857168005,"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."}}