{"id":"W4405827159","doi":"10.21203/rs.3.rs-5712957/v1","title":"Empirical Evaluation for Cricket CommentaryDecoder","year":2024,"lang":"en","type":"preprint","venue":"Research Square","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Cricket; Empirical research; Computer science; Mathematics; Statistics; Biology; Zoology","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":[0.03328618,0.0009161212,0.001036466,0.006557515,0.003838304,0.005559386,0.0024217,0.003615833,0.1431772],"category_scores_gemma":[0.2925772,0.0003675097,0.0008395051,0.006274804,0.001798734,0.002463301,0.002902836,0.003488452,0.0256528],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004272514,"about_ca_system_score_gemma":0.007670609,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01879686,"about_ca_topic_score_gemma":0.02293407,"domain_scores_codex":[0.964324,0.01849748,0.001767928,0.00250566,0.01151415,0.001390779],"domain_scores_gemma":[0.5574722,0.3123354,0.01181003,0.02142115,0.08980928,0.007152113],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.003418977,0.0005738093,0.007540873,0.001883419,0.0001859799,0.0003626879,0.001789156,0.001752376,0.0007446288,0.03358942,0.8218966,0.1262621],"study_design_scores_gemma":[0.001250876,0.001031204,0.03104832,0.00339557,0.0005766166,0.0003515563,0.005706994,0.01195553,0.004448819,0.02248224,0.9175664,0.0001857945],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1264443,0.006210825,0.03195672,0.08962311,0.03690426,0.004881273,0.06881595,0.002887112,0.6322765],"genre_scores_gemma":[0.5879731,0.002633674,0.0331681,0.03228467,0.0141497,0.00797277,0.05055607,0.003810067,0.2674518],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.1431772,"threshold_uncertainty_score":0.4789754,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3988626679700391,"score_gpt":0.4923184601591041,"score_spread":0.09345579218906502,"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."}}