{"id":"W2901602856","doi":"10.1016/j.infbeh.2018.09.010","title":"Should I test more babies? Solutions for transparent data peeking","year":2018,"lang":"en","type":"review","venue":"Infant Behavior and Development","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":29,"is_retracted":false,"has_abstract":false,"ca_institutions":"Concordia University","funders":"Concordia University; Natural Sciences and Engineering Research Council of Canada; Fonds de Recherche du Québec-Société et Culture; Canada Research Chairs","keywords":"False positive paradox; Sample (material); Test (biology); Data collection; Computer science; Statistics; Artificial intelligence; Mathematics; Biology","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.0183641,0.0009171251,0.001744426,0.003021077,0.001026732,0.004840317,0.003148674,0.004785147,0.01134732],"category_scores_gemma":[0.05424986,0.0005583695,0.001994852,0.002709345,0.004043011,0.009628467,0.004054636,0.007288905,0.003505816],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00175181,"about_ca_system_score_gemma":0.007556233,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002727913,"about_ca_topic_score_gemma":0.005100987,"domain_scores_codex":[0.9930502,0.002800825,0.0008702272,0.0006155609,0.002334268,0.000328898],"domain_scores_gemma":[0.9553732,0.03512307,0.002171944,0.002298221,0.004288806,0.0007446632],"domain_codex":null,"domain_gemma":"reproducibility","domain_candidate":"reproducibility","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00007438107,0.00004978085,0.0005050284,0.01177649,0.0001510058,0.0002042189,0.0006073458,0.0002778947,0.0005381348,0.03476992,0.072671,0.8783748],"study_design_scores_gemma":[0.00002512758,0.00003406161,0.0004394477,0.01442394,0.0001527532,0.0008898401,0.0004267936,0.0001348461,0.000525488,0.02080383,0.9621095,0.00003423832],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.0004213772,0.9508194,0.006418606,0.03252194,0.002351535,0.00005931786,0.0001805474,0.0001714721,0.007055842],"genre_scores_gemma":[0.00700157,0.9528609,0.01574561,0.01779118,0.002129748,0.0001243335,0.000281113,0.0001144705,0.003951067],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.9816359,"threshold_uncertainty_score":0.09711981,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3214620153321917,"score_gpt":0.4081116767200691,"score_spread":0.08664966138787744,"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."}}