{"id":"W4412881956","doi":"10.1002/ejsc.70018","title":"Decoding the Tackle: Using a Machine Learning Approach to Understand Direct Head Contact Events in Elite Women's Rugby","year":2025,"lang":"en","type":"article","venue":"European Journal of Sport Science","topic":"Sports injuries and prevention","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"ADAPT - Centre for Digital Content Technology; Irish Research Council; Science Foundation Ireland; Irish Research eLibrary","keywords":"Elite; Decoding methods; Head (geology); Computer science; Psychology; Human–computer interaction; Physical medicine and rehabilitation; Applied psychology; Cognitive psychology; Artificial intelligence; Medicine; Telecommunications; Political science; Biology","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":[0.006325492,0.0001053889,0.0002551669,0.0003944221,0.0002456652,0.00004240979,0.0002729687,0.00001076465,0.00002674956],"category_scores_gemma":[0.0001389517,0.00007003325,0.00006813605,0.001084101,0.00009205053,0.0002134995,0.00008943256,0.0003572644,0.000002104578],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003067908,"about_ca_system_score_gemma":0.0002435152,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002053515,"about_ca_topic_score_gemma":0.000002634618,"domain_scores_codex":[0.9985278,0.00005317922,0.0004961914,0.0001908681,0.0004428972,0.0002890395],"domain_scores_gemma":[0.999295,0.00001741586,0.0002687407,0.0001613193,0.0001095696,0.0001479752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00101126,0.0002814505,0.9572836,0.00008350019,0.00006496411,0.000432196,0.00782872,0.003603881,0.009614757,0.0007057342,0.00008741947,0.01900257],"study_design_scores_gemma":[0.001386718,0.0003348252,0.9748417,0.001319146,0.0000510878,0.0002948582,0.003567711,0.002543636,0.0002336907,0.00005866499,0.01521968,0.000148347],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.977161,0.000320943,0.001996703,0.0002337811,0.0002640268,0.0001582604,4.703147e-7,0.000008167038,0.0198566],"genre_scores_gemma":[0.9970191,0.00007450904,0.001661976,0.0003980261,0.00006679902,3.237765e-7,6.27164e-7,0.00001033327,0.0007683008],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01985806,"threshold_uncertainty_score":0.2855873,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02890812360245419,"score_gpt":0.3088526952769906,"score_spread":0.2799445716745364,"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."}}