{"id":"W2782851571","doi":"10.1017/s0140525x18000882","title":"Conceptualizing and evaluating replication across domains of behavioral research","year":2018,"lang":"en","type":"preprint","venue":"Behavioral and Brain Sciences","topic":"Mental Health Research Topics","field":"Psychology","cited_by":121,"is_retracted":false,"has_abstract":true,"ca_institutions":"Kellogg's (Canada)","funders":"","keywords":"Conceptualization; Replication (statistics); Psychology; Cognitive science; Cognitive psychology; Epistemology; Computer science; Artificial intelligence; Mathematics; Statistics; Philosophy","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":["sts"],"consensus_categories":[],"category_scores_codex":[0.01233858,0.0001953047,0.0003426751,0.0001932293,0.0008853724,0.0001975558,0.0006021796,0.0003163266,0.0002653883],"category_scores_gemma":[0.0001876832,0.0001672623,0.00004687952,0.0004105485,0.005442549,0.0001335559,0.001612794,0.0007213295,0.00001204422],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00007849905,"about_ca_system_score_gemma":0.0002533321,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005529006,"about_ca_topic_score_gemma":0.0003670278,"domain_scores_codex":[0.9952738,0.0009830018,0.0005662963,0.00125021,0.001135205,0.0007914435],"domain_scores_gemma":[0.9979992,0.0004057071,0.0002867483,0.0007119227,0.0003577313,0.000238682],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0002127616,0.0009571759,0.3197664,0.0005728882,0.00001822116,0.00002727586,0.08754882,0.000001485271,0.01532567,0.007542683,0.003951379,0.5640752],"study_design_scores_gemma":[0.002991521,0.01502869,0.8212311,0.001719403,0.00009714896,0.0001500968,0.121173,0.0008483064,0.005149664,0.0259813,0.004143272,0.0014865],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9957052,0.001163208,0.00001350893,0.00071839,0.0004281081,0.0009907931,0.0001162985,0.00002905209,0.0008354275],"genre_scores_gemma":[0.9964219,0.0000497226,0.002105364,0.0000634825,0.0001841359,0.0002054909,0.00002474351,0.00001402645,0.0009310966],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5625887,"threshold_uncertainty_score":0.9972641,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7128275322034786,"score_gpt":0.6878642254028715,"score_spread":0.0249633068006071,"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."}}