{"id":"W2022522100","doi":"10.1016/j.tcs.2005.09.047","title":"Tuning evaluation functions by maximizing concordance","year":2005,"lang":"en","type":"article","venue":"Theoretical Computer Science","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":19,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Concordance; Computer science; Mathematics; Algorithm; Biology; Bioinformatics","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":[0.002834624,0.0001807188,0.0001639532,0.0001608137,0.0006940014,0.0006248413,0.002350423,0.00004899793,0.0001674202],"category_scores_gemma":[0.0002521129,0.0001649694,0.00005715793,0.001245613,0.002196867,0.001698877,0.0007350985,0.0002288579,0.0005303748],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002072909,"about_ca_system_score_gemma":0.0002012788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00000583724,"about_ca_topic_score_gemma":0.000002052451,"domain_scores_codex":[0.9968756,0.0001520519,0.0003635247,0.0008045519,0.001184067,0.0006201981],"domain_scores_gemma":[0.9980667,0.0002926773,0.00009608804,0.0008524155,0.0004399863,0.0002521786],"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":[0.00000200242,0.00003166335,0.00003281179,9.237017e-7,0.000001758011,8.124791e-7,0.0003688858,0.001447199,0.002226189,0.5682763,0.0005157365,0.4270957],"study_design_scores_gemma":[0.00007235563,0.0000815917,0.00007626149,0.00001814404,0.000004950715,0.00001893004,0.00001965754,0.9291681,0.01909545,0.04916176,0.00207223,0.0002105918],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02024375,0.0001462227,0.9680267,0.002955655,0.0008009585,0.0001984607,0.000001145873,0.0002979108,0.007329193],"genre_scores_gemma":[0.8186278,0.000003344369,0.1802586,0.0008447313,0.0002071818,0.00001585444,9.224904e-7,0.000006895632,0.00003459112],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.9277209,"threshold_uncertainty_score":0.8094446,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02927408007419969,"score_gpt":0.3047333935201485,"score_spread":0.2754593134459488,"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."}}