{"id":"W4405452958","doi":"10.1145/3705013","title":"A Comprehensive Model of Automated Evaluation of Difficulty in Platformer Games","year":2024,"lang":"en","type":"article","venue":"Games Research and Practice","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Chicoutimi","funders":"","keywords":"Computer science","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001331219,0.001098733,0.0007635971,0.001890732,0.0004865617,0.003078898,0.001861814,0.00118136,0.003655155],"category_scores_gemma":[0.007622895,0.0007947243,0.001427734,0.0008050769,0.001542495,0.002841545,0.001096249,0.001157156,0.0007586173],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001855463,"about_ca_system_score_gemma":0.001820813,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01054643,"about_ca_topic_score_gemma":0.008597605,"domain_scores_codex":[0.9984862,0.0003676269,0.0001241943,0.0003750534,0.0005030559,0.0001439599],"domain_scores_gemma":[0.9969814,0.001711197,0.0004075181,0.000333877,0.000442742,0.0001232007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00008259688,0.0001263919,0.003721392,0.0001843129,0.00005686711,0.0001400038,0.0003997857,0.8977385,0.004282137,0.06007196,0.0007120388,0.03248407],"study_design_scores_gemma":[0.000014012,0.00005232904,0.000883969,0.00002975185,0.00001947963,0.00005841101,0.0000261847,0.9789463,0.0008975291,0.01762268,0.001428854,0.00002050183],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.02912989,0.0001219693,0.9646332,0.0001082471,0.00001438663,0.0001876167,0.0002803477,0.0009275029,0.004596772],"genre_scores_gemma":[0.5219134,0.000307544,0.4723907,0.00006392494,0.0000202955,0.0006154018,0.00059374,0.0002546606,0.003840291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01054643,"threshold_uncertainty_score":0.02097005,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3253714657586089,"score_gpt":0.4986562545373149,"score_spread":0.173284788778706,"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."}}