{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00373782,0.00133926,0.0004696923,0.001621763,0.0006710665,0.002609717,0.002030317,0.001595351,0.00701491],"category_scores_gemma":[0.02084254,0.0005469561,0.002187606,0.0008160174,0.000827635,0.003473768,0.003206672,0.002734053,0.00167799],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001490799,"about_ca_system_score_gemma":0.001684835,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01596497,"about_ca_topic_score_gemma":0.02388084,"domain_scores_codex":[0.9973757,0.001447939,0.000161048,0.000601577,0.0003049895,0.0001086634],"domain_scores_gemma":[0.99011,0.007874805,0.0005383356,0.0007387546,0.0005028791,0.0002352304],"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":[0.001060305,0.0005237975,0.02311702,0.001571793,0.0009220229,0.001799394,0.007504942,0.2990632,0.01418812,0.2283432,0.05462248,0.3672838],"study_design_scores_gemma":[0.00005718383,0.00008778139,0.001332346,0.00009123643,0.00006877711,0.0001580266,0.0003325479,0.8688574,0.001961266,0.1062235,0.02076199,0.00006785717],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01602116,0.0005078051,0.9662488,0.001266609,0.0001214249,0.0002312201,0.00386521,0.009796951,0.001940836],"genre_scores_gemma":[0.3586959,0.0005706061,0.6217779,0.001379286,0.0002838377,0.0007474038,0.01098695,0.001399264,0.004158912],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.01596497,"threshold_uncertainty_score":0.03174412,"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."}}