{"id":"W4414359334","doi":"10.24963/ijcai.2025/851","title":"InnateCoder: Learning Programmatic Options with Foundation Models","year":2025,"lang":"en","type":"article","venue":"","topic":"Intelligent Tutoring Systems and Adaptive Learning","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"HORIZON EUROPE Framework Programme; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Alliance de recherche numérique du Canada; Natural Sciences and Engineering Research Council of Canada; European Commission; Nederlandse Organisatie voor Wetenschappelijk Onderzoek; Canadian Institute for Advanced Research","keywords":"Reinforcement learning; Process (computing); Foundation (evidence); ENCODE; Encoding (memory); Knowledge transfer; Empirical evidence; Action (physics)","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0002365403,0.00008680938,0.00009310856,0.000235308,0.0002465534,0.0003289055,0.0002543941,0.00002838381,0.00001013753],"category_scores_gemma":[0.00001715569,0.00006615659,0.00002630369,0.0006587273,0.0000145257,0.0005623462,0.00007686989,0.0001517101,0.00005357191],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003426569,"about_ca_system_score_gemma":0.00005194712,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007017026,"about_ca_topic_score_gemma":0.00001175198,"domain_scores_codex":[0.999247,0.00005754917,0.0001542957,0.0002224979,0.0001424386,0.0001762286],"domain_scores_gemma":[0.9995571,0.00004176985,0.00005499843,0.000193936,0.0001264649,0.00002574112],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000113978,0.00001389472,0.0002463488,0.00001570357,0.00001535566,0.0000012734,0.000205152,0.07410841,0.00003814514,0.9012154,0.00002614242,0.02411301],"study_design_scores_gemma":[0.0001377199,0.00008335069,0.0001616275,0.0001401787,0.00000518479,0.000005502176,0.0001995911,0.9377306,0.0003165586,0.01063714,0.05044572,0.0001367914],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.001949908,0.00003275838,0.9565035,0.0003769323,0.0001198013,0.000162104,1.739909e-8,0.000382381,0.04047257],"genre_scores_gemma":[0.8225109,0.00001099689,0.1086809,0.00006766466,0.00002271695,0.00005074396,0.000001764047,0.000006161927,0.06864822],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8905783,"threshold_uncertainty_score":0.3171643,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01671768766656682,"score_gpt":0.2477664878578028,"score_spread":0.2310488001912359,"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."}}