{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0003662567,0.0001032388,0.0001735,0.0001086391,0.00006363776,0.0001682725,0.0001890327,0.00004218934,0.000003126886],"category_scores_gemma":[0.0000694906,0.00008306822,0.00006238379,0.0003124477,0.00007412228,0.0004019962,0.0001737481,0.0002210924,2.508244e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000119384,"about_ca_system_score_gemma":0.00005722624,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009712468,"about_ca_topic_score_gemma":4.463871e-7,"domain_scores_codex":[0.9990206,0.00006655804,0.0002707134,0.0002509973,0.0002023729,0.0001887369],"domain_scores_gemma":[0.9996062,0.00006802266,0.00009969628,0.0001467013,0.00003675266,0.00004265104],"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":[0.0000134197,0.00004692777,0.005418556,0.0005775758,0.0001221565,0.00002593682,0.03130617,0.0250036,0.004305756,0.04637785,0.00004140933,0.8867607],"study_design_scores_gemma":[0.0002708694,0.0006346197,0.0001665216,0.001126629,0.00003271656,0.00004218029,0.001974682,0.964274,0.01740157,0.00009955972,0.01366678,0.000309833],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2280099,0.001121551,0.7700866,0.00004892323,0.0001783978,0.0001293144,1.745474e-7,0.0001927248,0.0002324127],"genre_scores_gemma":[0.9405894,0.000002010613,0.05838069,0.000004270546,0.00002707928,0.00000345314,0.000001627939,0.000009032317,0.0009823912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9392704,"threshold_uncertainty_score":0.3387423,"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."}}