{"id":"W3175201286","doi":"10.31234/osf.io/qhxkm","title":"Infants’ Social Evaluation of Helpers and Hinderers: A Large-Scale, Multi-Lab, Coordinated Replication Study","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Child and Animal Learning Development","field":"Psychology","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of British Columbia","funders":"Social Sciences and Humanities Research Council of Canada; Natural Sciences and Engineering Research Council of Canada; Pennington Biomedical Research Foundation","keywords":"Preference; Replication (statistics); Psychology; Replicate; Social psychology; Character (mathematics); Developmental psychology; Statistics; Mathematics","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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.002449123,0.000240873,0.0004465114,0.0001430329,0.000127476,0.00005840443,0.0001634871,0.000326142,0.001458685],"category_scores_gemma":[0.0002125553,0.0002381105,0.00008811205,0.0001736367,0.0000471167,0.00003846392,0.0004356727,0.000499514,0.00001475913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001051882,"about_ca_system_score_gemma":0.0002058499,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004012639,"about_ca_topic_score_gemma":0.0003451593,"domain_scores_codex":[0.9971182,0.0006647569,0.0005111991,0.001034357,0.0004537291,0.0002178022],"domain_scores_gemma":[0.9983944,0.000045623,0.0003639411,0.0005782309,0.0005655196,0.00005227715],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003813061,0.006973888,0.5835834,0.0002447926,0.002247659,0.00001442228,0.3134015,0.00008053906,0.001367137,0.0005312084,0.003548539,0.08762566],"study_design_scores_gemma":[0.002937689,0.00008687052,0.9574379,0.00006118484,0.00023476,0.000002773828,0.03697359,0.001758857,0.00004366907,0.00002657843,0.0001778831,0.0002582261],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9920742,0.000381329,0.0004991055,0.0003814364,0.0003682952,0.001331337,0.00001943035,0.00008385488,0.004861],"genre_scores_gemma":[0.9975104,0.00001079875,0.000935428,0.00009488756,0.00007121721,0.0001768096,0.0002559829,0.00002743424,0.000917027],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3738545,"threshold_uncertainty_score":0.9994541,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0828703529378064,"score_gpt":0.3942012474699639,"score_spread":0.3113308945321576,"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."}}