{"id":"W2935069460","doi":"10.31234/osf.io/qkwst","title":"Many analysts, one dataset: Making transparent how variations in analytical choices affect results","year":2017,"lang":"en","type":"article","venue":"","topic":"Sports Analytics and Performance","field":"Economics, Econometrics and Finance","cited_by":84,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; University of Alberta","funders":"Institute of Education Sciences; Leverhulme Trust; U.S. Department of Education","keywords":"Affect (linguistics); Variation (astronomy); Crowdsourcing; Odds; Psychology; Covariate; Quality (philosophy); Data science; Social psychology; Computer science; Econometrics; Logistic regression; Economics; Machine learning","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":[0.0008313261,0.0001496546,0.0004298642,0.0003138607,0.0002719449,0.0004655434,0.0004856589,0.00008616663,0.0006623054],"category_scores_gemma":[0.0001286263,0.0001567391,0.00009701916,0.0001575216,0.0000581457,0.0005129293,0.00006295019,0.0001639113,0.0001437491],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000662349,"about_ca_system_score_gemma":0.00001494788,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001582286,"about_ca_topic_score_gemma":0.004650235,"domain_scores_codex":[0.998584,0.000006538271,0.0005565066,0.0004769143,0.00006116989,0.0003149179],"domain_scores_gemma":[0.9984736,0.00003916717,0.0004385283,0.0009561171,0.0000173392,0.00007527405],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00005619921,0.0002712154,0.6564851,0.00004565825,0.0001779905,0.00002515512,0.0001610068,0.001197943,0.000002934806,0.3341008,0.006369808,0.001106163],"study_design_scores_gemma":[0.0006663831,0.00002827825,0.7180868,0.00002882213,0.00001966606,8.166027e-7,0.00001233147,0.2266024,0.000005815754,0.001074423,0.05325282,0.0002215164],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.3985341,0.002215113,0.07708187,0.03999799,0.002088416,0.001595995,0.0275034,0.0001785932,0.4508045],"genre_scores_gemma":[0.9966681,0.0002482345,0.0004348094,0.0001497282,0.0001340621,0.000008988178,0.000413046,0.00001319038,0.001929823],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.598134,"threshold_uncertainty_score":0.7251779,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1454736522912063,"score_gpt":0.3159732682378469,"score_spread":0.1704996159466405,"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."}}