{"id":"W2096435762","doi":"10.4271/2013-01-1249","title":"Statistical Considerations for Evaluating Biofidelity, Repeatability, and Reproducibility of ATDs","year":2013,"lang":"en","type":"article","venue":"SAE International Journal of Transportation Safety","topic":"Mechanics and Biomechanics Studies","field":"Engineering","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"Chrysler (Canada)","funders":"","keywords":"Computer science; Repeatability; Set (abstract data type); Statistical hypothesis testing; Statistical model; Statistics; Statistical analysis; Simulation; Mathematics; Artificial intelligence","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":[0.001432194,0.00008886114,0.0002186179,0.00008945839,0.00004012446,0.00002298758,0.0000899195,0.00004148545,0.0001566256],"category_scores_gemma":[0.0007544064,0.00007889826,0.00008013625,0.0000501188,0.00003943756,0.0001807265,0.000007650501,0.00008648746,7.456111e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004287887,"about_ca_system_score_gemma":0.00004338196,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002945041,"about_ca_topic_score_gemma":0.00007711365,"domain_scores_codex":[0.9984058,0.00002782737,0.0009580778,0.000193995,0.0003274296,0.00008692349],"domain_scores_gemma":[0.997717,0.0004024742,0.0002148124,0.00017582,0.001438065,0.00005183511],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0009451107,0.0006069841,0.03711393,0.001390857,0.003367061,0.00002490023,0.006411563,0.01528899,0.4529831,0.2982001,0.005074742,0.1785926],"study_design_scores_gemma":[0.003271611,0.000741504,0.4010555,0.0002178151,0.0002920824,0.00005247104,0.0009312818,0.03582387,0.02706194,0.5290394,0.001085964,0.0004265445],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7812012,0.0002711909,0.2142645,0.001437048,0.001302631,0.0004600457,0.0009400357,0.00002587922,0.00009756271],"genre_scores_gemma":[0.9557918,0.0001494185,0.04389525,0.00003087092,0.00006625675,0.000009941204,0.00004176853,0.000008715926,0.000005938747],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4259212,"threshold_uncertainty_score":0.3217377,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04420741627930622,"score_gpt":0.3192062487199813,"score_spread":0.274998832440675,"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."}}