{"id":"W4283791892","doi":"10.1609/aaai.v36i7.20744","title":"What Can We Learn Even from the Weakest? Learning Sketches for Programmatic Strategies","year":2022,"lang":"en","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Fundação de Amparo à Pesquisa do Estado de Minas Gerais; Compute Canada; Coordenação de Aperfeiçoamento de Pessoal de Nível Superior; Canadian Institute for Advanced Research","keywords":"Sketch; Computer science; Cloning (programming); Action (physics); Artificial intelligence; Human–computer interaction; Programming language; Algorithm","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":["metaepi_narrow","sts","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001189568,0.0003784516,0.0003987098,0.0001123526,0.001396502,0.001871957,0.005161511,0.00008930951,0.0001438024],"category_scores_gemma":[0.0008094402,0.000264559,0.0002771505,0.0009537711,0.0005619599,0.001160813,0.001216576,0.0008947909,0.0000436375],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001372188,"about_ca_system_score_gemma":0.0003387771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003042309,"about_ca_topic_score_gemma":0.0001634133,"domain_scores_codex":[0.9965463,0.0001199183,0.0008717768,0.0008078082,0.0009924226,0.0006617327],"domain_scores_gemma":[0.9969771,0.0009433899,0.0007730788,0.000570014,0.0006333154,0.0001031125],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007244576,0.0001438669,0.0001796689,0.00003210983,0.00004013781,5.822567e-7,0.01957501,0.002377165,0.007610888,0.6695335,0.0001549518,0.3002797],"study_design_scores_gemma":[0.00002447584,0.0005131539,0.00005647215,0.0002342382,0.00003155351,0.000004686488,0.08097816,0.1174348,0.1316503,0.6660032,0.002705924,0.0003630833],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6851063,0.001197559,0.1489438,0.1460444,0.007015679,0.006644043,0.00006176534,0.001044655,0.003941856],"genre_scores_gemma":[0.9952189,0.0001615881,0.002970534,0.0003334644,0.0001757213,0.000533738,0.000002791562,0.00003314059,0.0005701202],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3101126,"threshold_uncertainty_score":0.9999807,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.09476838440004962,"score_gpt":0.3105838047822173,"score_spread":0.2158154203821676,"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."}}