{"id":"W4416014029","doi":"10.1609/aiide.v21i1.36821","title":"Signals of Struggle: Detecting Player Difficulties Using Machine Learning","year":2025,"lang":"","type":"article","venue":"Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Carleton University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Random forest; Set (abstract data type); Feature (linguistics); Window (computing); Feature extraction; Cognition","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","scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.0006112334,0.0007568703,0.0009576083,0.0005477089,0.000529889,0.001253764,0.001928506,0.0002240504,0.0001159064],"category_scores_gemma":[0.001689793,0.0006055541,0.0004411324,0.001025479,0.00119884,0.00189571,0.001885754,0.001015809,0.000016356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002683524,"about_ca_system_score_gemma":0.0002124336,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002522472,"about_ca_topic_score_gemma":0.0000222121,"domain_scores_codex":[0.9950384,0.00008277575,0.002083939,0.001138324,0.0009060768,0.0007504352],"domain_scores_gemma":[0.9954221,0.0006736821,0.001790834,0.0003932017,0.001560211,0.0001599951],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.001854228,0.00193954,0.01015244,0.0007148223,0.0008088709,0.000004028633,0.02258892,0.005090022,0.2972499,0.162263,0.00004267688,0.4972916],"study_design_scores_gemma":[0.00004907449,0.0006818298,0.00009516448,0.00265739,0.00006668135,0.000006125973,0.01163262,0.3443101,0.6277329,0.01236723,0.00005404199,0.0003468267],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9357463,0.0003079356,0.05426709,0.001067883,0.001185462,0.001126747,0.0000623095,0.00005675434,0.006179482],"genre_scores_gemma":[0.9982834,0.0001976875,0.0004542798,0.0001314866,0.00006013446,0.00002588349,0.00000163816,0.00003018481,0.0008153239],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4969447,"threshold_uncertainty_score":0.999783,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05538629029033634,"score_gpt":0.308263734996322,"score_spread":0.2528774447059857,"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."}}