{"id":"W4385793603","doi":"10.1101/2023.08.08.552425","title":"Comparing the advantages and disadvantages of physics-based and neural network-based modelling for predicting cycling power","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Sports Performance and Training","field":"Medicine","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Simon Fraser University","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Cadence; Interpretability; Artificial neural network; Computer science; Metronome; Power (physics); Cycling; Machine learning; Artificial intelligence; Engineering; Electronic engineering; Physics","routes":{"ca_aff":true,"ca_fund":true,"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":[0.001303894,0.0006459515,0.0004259309,0.0007622706,0.0002205853,0.0007507176,0.0007331144,0.0009467008,0.001290626],"category_scores_gemma":[0.005651981,0.0003797131,0.0004801741,0.0004106796,0.0003188933,0.001180868,0.00043815,0.0005602051,0.0002512829],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0008066476,"about_ca_system_score_gemma":0.0006708867,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01832945,"about_ca_topic_score_gemma":0.01439832,"domain_scores_codex":[0.9996691,0.0001529538,0.00002465427,0.00006319799,0.00006811255,0.00002195527],"domain_scores_gemma":[0.9977959,0.00175327,0.0001074979,0.00009891418,0.0001997213,0.00004469791],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001971393,0.0001110532,0.006149026,0.00007099209,0.00009286164,0.00002391599,0.00004609351,0.9718816,0.002606545,0.0006081081,0.0001295418,0.01808318],"study_design_scores_gemma":[0.000005777404,0.00002855952,0.0013479,0.000005412291,0.000007386016,0.000004146547,0.000006474409,0.997824,0.0003625909,0.0003588083,0.00004322916,0.000005892224],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8002203,0.0007287717,0.19118,0.0008363572,0.00007916149,0.0001026999,0.0002720528,0.0005844085,0.005996165],"genre_scores_gemma":[0.9840761,0.0001468407,0.01486616,0.00004082576,0.00001359308,0.00006306686,0.0001134772,0.00002652158,0.0006533935],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01832945,"threshold_uncertainty_score":0.0364455,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03879213230416417,"score_gpt":0.269374683444871,"score_spread":0.2305825511407068,"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."}}