{"id":"W4402916376","doi":"10.1109/cvprw63382.2024.00332","title":"X-VARS: Introducing Explainability in Football Refereeing with Multi-Modal Large Language Models","year":2024,"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":"Kootenay Association for Science & Technology","funders":"King Abdullah University of Science and Technology; Fonds De La Recherche Scientifique - FNRS","keywords":"Football; Modal; Computer science; Natural language processing; Speech recognition; Linguistics; History; Materials science; Archaeology","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":[],"consensus_categories":[],"category_scores_codex":[0.0008280129,0.0001480057,0.0002897364,0.0002755585,0.0000504764,0.0001313961,0.0001396544,0.00006948059,0.0005911994],"category_scores_gemma":[0.00002094503,0.0001323306,0.00006039118,0.0003392529,0.00002153415,0.0004547081,0.00005569097,0.0002270778,0.0001050808],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001488952,"about_ca_system_score_gemma":0.00002581028,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001567482,"about_ca_topic_score_gemma":0.001977324,"domain_scores_codex":[0.9986256,0.000005064685,0.0004382232,0.0005362706,0.00003835708,0.0003564538],"domain_scores_gemma":[0.9994802,0.000023212,0.00005993193,0.0003618866,0.00001786787,0.00005683305],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004389936,0.0002731528,0.1632192,0.0002999814,0.00008244959,0.0001387913,0.008616907,0.02953851,0.00002074393,0.7950746,0.0003667317,0.002324956],"study_design_scores_gemma":[0.0004728832,0.00004546066,0.01348232,0.00006542687,0.000003895401,0.000004888647,0.0006828513,0.9725556,0.00003517753,0.004597763,0.00776343,0.0002902415],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.915222,0.002596987,0.06180018,0.0004090426,0.000203389,0.0001835695,0.00005452522,0.00009853506,0.01943176],"genre_scores_gemma":[0.9952416,0.0001055923,0.002071596,0.0001299431,0.00009859463,0.00001844101,0.00001700118,0.00002685838,0.002290331],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9430171,"threshold_uncertainty_score":0.6473218,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03053137800724538,"score_gpt":0.2421394657411799,"score_spread":0.2116080877339345,"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."}}