{"id":"W4414425779","doi":"10.21203/rs.3.rs-7408657/v1","title":"Automated Detection of Physical Contact Events in Youth Ice Hockey: A Player-Focused Deep Learning Approach","year":2025,"lang":"en","type":"preprint","venue":"Research Square","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Ottawa","funders":"","keywords":"Precision and recall; Classifier (UML); Deep learning; Recall; Discriminative model; Pattern recognition (psychology); F1 score","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.001982005,0.0002570297,0.0008466208,0.001411546,0.0001371253,0.00006007997,0.0004702561,0.0003618725,0.00004264846],"category_scores_gemma":[0.0002911713,0.0002888403,0.0002563135,0.0009512691,0.00005384012,0.0001096092,0.0005140319,0.001894465,0.00004752356],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004172976,"about_ca_system_score_gemma":0.0001338843,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004756128,"about_ca_topic_score_gemma":0.0002154916,"domain_scores_codex":[0.9975569,0.0001148678,0.0007689881,0.0007548481,0.0002362457,0.0005680965],"domain_scores_gemma":[0.9985787,0.0001367296,0.0004312672,0.0005520844,0.0002021947,0.00009901522],"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":[0.0007163726,0.002420698,0.6477521,0.006771641,0.00068208,0.00002359891,0.02399275,0.2927279,0.0001645084,0.01462735,0.00006817505,0.01005281],"study_design_scores_gemma":[0.0007316478,0.000193809,0.1269475,0.0004652075,0.00000984224,3.65101e-7,0.0005681096,0.8688932,0.0001822909,0.001299779,0.000417291,0.0002909667],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9877887,0.001038226,0.00152005,0.00002794973,0.0001630457,0.0007798398,0.0003198833,0.00009674015,0.00826556],"genre_scores_gemma":[0.9985983,0.0004111987,0.00005741831,0.000004877495,0.0001138739,0.00009480013,0.0002251855,0.00003053232,0.0004637923],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5761653,"threshold_uncertainty_score":0.9999564,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07010471534689511,"score_gpt":0.3260762349793021,"score_spread":0.255971519632407,"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."}}