{"id":"W2809133880","doi":"10.1145/3208788.3208800","title":"Outcome prediction of DOTA2 using machine learning methods","year":2018,"lang":"en","type":"article","venue":"","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":26,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Outcome (game theory); Machine learning; Normalization (sociology); Artificial intelligence; Table (database); Task (project management); Data mining; Engineering","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":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007954553,0.00007215828,0.0002364779,0.0001547983,0.00007834942,0.00001694696,0.00008006722,0.00004797245,0.002312177],"category_scores_gemma":[0.00004808273,0.00007133575,0.00006807876,0.0001784023,0.00005055696,0.0001156305,0.00003368123,0.00008633899,0.0000678818],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000260577,"about_ca_system_score_gemma":0.000005334475,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008420095,"about_ca_topic_score_gemma":0.00001911398,"domain_scores_codex":[0.9991545,0.000006351417,0.0005230375,0.0001654609,0.00002050964,0.000130138],"domain_scores_gemma":[0.999522,0.00001521484,0.0002316813,0.0001591239,0.00003802838,0.00003390118],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00000408959,0.00001526517,0.9698024,0.00001073318,0.00002087294,1.776586e-7,0.00009594517,0.0003903156,0.0001599596,0.02877215,0.00002640527,0.000701614],"study_design_scores_gemma":[0.0002078637,0.00009507039,0.07615221,0.000005764796,0.000007803904,0.000002914398,0.0000229336,0.8585241,0.001016116,0.002165904,0.06169008,0.0001092742],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6940138,0.0005228419,0.2509839,0.00005659504,0.0007150628,0.00007906096,0.00004858994,0.00004341334,0.05353672],"genre_scores_gemma":[0.9701505,0.00005557253,0.02685481,0.00006294189,0.0001425405,7.70575e-7,0.000004972571,0.00001176526,0.002716147],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8936503,"threshold_uncertainty_score":0.9985998,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1404159682735247,"score_gpt":0.3333290935459258,"score_spread":0.1929131252724011,"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."}}