{"id":"W4382240209","doi":"10.1609/aaai.v37i4.25626","title":"Show Me the Way! Bilevel Search for Synthesizing Programmatic Strategies","year":2023,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Natural Sciences and Engineering Research Council of Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Institute for Advanced Research","keywords":"Computer science; Space (punctuation); Function (biology); Search algorithm; Set (abstract data type); Differentiable function; Bilevel optimization; Feature (linguistics); Evaluation function; Theoretical computer science; Algorithm; Artificial intelligence; Mathematics; Optimization problem; Programming language","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001984971,0.0003737918,0.0003920371,0.0002598641,0.0007471006,0.001256845,0.005078511,0.000141649,0.00003621141],"category_scores_gemma":[0.001044643,0.000230947,0.0002824272,0.001957324,0.0008201862,0.0008481346,0.0007947315,0.000444128,0.0003049958],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006752847,"about_ca_system_score_gemma":0.000233955,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006576004,"about_ca_topic_score_gemma":0.00002900583,"domain_scores_codex":[0.9964231,0.00005365077,0.0008977958,0.0007632514,0.000964882,0.0008973098],"domain_scores_gemma":[0.9965922,0.001069879,0.0004067876,0.0006930505,0.00111843,0.000119674],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00003283553,0.00007003419,0.00005909691,0.00008806907,0.00002522197,5.174504e-7,0.003940901,0.0004962875,0.03089694,0.7988943,0.0002146246,0.1652812],"study_design_scores_gemma":[0.000009166371,0.0001517225,0.00006661949,0.0001806372,0.00001279418,0.000003067562,0.006428318,0.2426309,0.4465272,0.3036409,0.0001454485,0.0002032184],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4389658,0.00009419926,0.486911,0.0499764,0.002524413,0.006653444,0.00003517498,0.001685624,0.01315402],"genre_scores_gemma":[0.9940658,0.00004662677,0.004792976,0.0001496557,0.0001514344,0.0003496355,8.216324e-7,0.00003309318,0.0004100135],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.5551,"threshold_uncertainty_score":0.9997799,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1857926898496378,"score_gpt":0.3534989015197543,"score_spread":0.1677062116701165,"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."}}