{"id":"W2810374059","doi":"10.1109/tg.2018.2844121","title":"Recommender System for Items in <i>Dota 2</i>","year":2018,"lang":"en","type":"article","venue":"IEEE Transactions on Games","topic":"Artificial Intelligence in Games","field":"Computer Science","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"","keywords":"Recommender system; Purchasing; Computer science; HERO; Cluster analysis; Logistic regression; Affect (linguistics); Feature (linguistics); Artificial intelligence; Psychology; Machine learning; Marketing; Business; Communication","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":[0.001294507,0.001140163,0.001476257,0.001647419,0.00072676,0.001432098,0.001805002,0.001475569,0.008736827],"category_scores_gemma":[0.006083228,0.0005117938,0.001201431,0.001212751,0.0001488205,0.001401879,0.0006206077,0.001616198,0.009971987],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005209632,"about_ca_system_score_gemma":0.0007025774,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03396852,"about_ca_topic_score_gemma":0.06183945,"domain_scores_codex":[0.9989466,0.0001447325,0.00009510584,0.0003648367,0.0003460746,0.0001026636],"domain_scores_gemma":[0.997092,0.0006744618,0.0001945233,0.0004701415,0.001386549,0.0001822561],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001674,0.001231147,0.08625923,0.0009638684,0.0009403433,0.00155984,0.0006009216,0.03668747,0.03520313,0.00414085,0.1978566,0.6328826],"study_design_scores_gemma":[0.0001705283,0.0007640654,0.06478293,0.0001976888,0.0004680648,0.001685411,0.0004035833,0.8388566,0.01804313,0.002602848,0.07172944,0.0002957539],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.2917535,0.004292873,0.5905629,0.003933627,0.002084774,0.002072958,0.02580128,0.0378957,0.04160235],"genre_scores_gemma":[0.5547139,0.001475584,0.3764586,0.001049615,0.0004103951,0.0005828642,0.02198213,0.0005007554,0.04282605],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.03396852,"threshold_uncertainty_score":0.0675416,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04347225596915313,"score_gpt":0.2961998781675012,"score_spread":0.252727622198348,"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."}}