{"id":"W1548895693","doi":"10.1007/978-0-387-35706-5_1","title":"Evaluation Function Tuning via Ordinal Correlation","year":2004,"lang":"en","type":"book-chapter","venue":"Advances in Computer Games","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Heuristic; Metric (unit); Correlation; Computer science; Function (biology); Feature (linguistics); Quality (philosophy); Evaluation function; Space (punctuation); Artificial intelligence; Ordinal optimization; Mathematics; Data mining; Machine learning; Ordinal data; Engineering","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"],"consensus_categories":[],"category_scores_codex":[0.0008735927,0.0004420711,0.0004128705,0.0004779389,0.0001196279,0.0001736402,0.0008395324,0.0003047749,0.0001817141],"category_scores_gemma":[0.00003551813,0.0004739328,0.0001418733,0.0001452826,0.0001346674,0.001913821,0.0003223785,0.0005681234,0.0003350195],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006533225,"about_ca_system_score_gemma":0.0002438622,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001966938,"about_ca_topic_score_gemma":0.0001015515,"domain_scores_codex":[0.9967765,0.0000891816,0.0007258445,0.0009474411,0.001109283,0.0003517698],"domain_scores_gemma":[0.9980603,0.0002441299,0.0004952745,0.0007373139,0.0003868407,0.00007607588],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00000786303,0.00001550316,0.00003623757,0.00001533738,0.00001658114,0.0000117791,0.0001992348,0.1249355,0.000003107771,0.12338,0.00005880475,0.7513199],"study_design_scores_gemma":[0.0001251312,0.000167497,0.00007476049,0.0003794128,0.00003162818,0.00001474416,0.000003241104,0.4780514,0.00004276869,0.4947024,0.02603973,0.0003673001],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.00002378574,0.004444508,0.9334579,0.0001228044,0.005667622,0.000479534,0.000001462334,0.0002292054,0.05557321],"genre_scores_gemma":[0.4339418,0.004430498,0.5097229,0.00184584,0.006033081,0.0002934863,0.000242095,0.0003604845,0.04312985],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.7509527,"threshold_uncertainty_score":0.9997712,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03255499166891886,"score_gpt":0.2965026661006124,"score_spread":0.2639476744316935,"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."}}