{"id":"W2562775190","doi":"10.1037/xge0000079","title":"Generalization versus contextualization in automatic evaluation revisited: A meta-analysis of successful and failed replications.","year":2015,"lang":"en","type":"review","venue":"Journal of Experimental Psychology General","topic":"Social and Intergroup Psychology","field":"Social Sciences","cited_by":25,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Social Sciences and Humanities Research Council of Canada; Universiteit Gent","keywords":"Contextualization; Generalization; Psychology; Meta-analysis; Cognitive psychology; Social psychology; Epistemology; Linguistics","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.004380559,0.0002674786,0.002924643,0.001230254,0.0001052923,0.00004098392,0.0003908082,0.0004629485,0.0008233223],"category_scores_gemma":[0.0004331837,0.0002211765,0.001047827,0.001703324,0.0003056776,0.0002613659,0.0000382123,0.0002574776,0.000004100043],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003775486,"about_ca_system_score_gemma":0.0003017056,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000198099,"about_ca_topic_score_gemma":0.0002398466,"domain_scores_codex":[0.993335,0.003555849,0.001879162,0.0003874802,0.0006271705,0.0002153574],"domain_scores_gemma":[0.9962094,0.0001932106,0.002542692,0.0003179742,0.0006124051,0.0001243291],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.000777484,0.003337007,0.001714051,0.0009769857,0.253427,0.0000410003,0.05979441,0.0001563832,0.000331239,0.0224966,0.03047733,0.6264705],"study_design_scores_gemma":[0.005038451,0.001264335,0.0005400001,0.0004392962,0.3340498,0.00003844036,0.005598224,0.001086402,0.00001360531,0.000853261,0.650148,0.000930166],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"review","genre_gemma":"review","genre_scores_codex":[0.005049301,0.9910655,0.0001079582,0.0001718677,0.0007862754,0.0006729775,0.00002066117,0.000009608018,0.002115852],"genre_scores_gemma":[0.01800375,0.9803292,0.0006563854,0.0002033422,0.0003740336,0.0001315426,0.000162726,0.00002981602,0.0001092179],"genre_candidate":"review","genre_consensus":"review","teacher_disagreement_score":0.6255404,"threshold_uncertainty_score":0.9019316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3501963841645199,"score_gpt":0.5638342725341257,"score_spread":0.2136378883696057,"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."}}