{"id":"W4310641393","doi":"10.1177/17456916221134575","title":"Improving the Generalizability of Behavioral Science by Using Reality Checks: A Tool for Assessing Heterogeneity in Participants’ Consumership of Study Stimuli","year":2022,"lang":"en","type":"article","venue":"Perspectives on Psychological Science","topic":"Decision-Making and Behavioral Economics","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"The Scarborough Hospital; University of Toronto","funders":"","keywords":"Generalizability theory; Realism; Psychology; Relevance (law); External validity; Writ; Cognitive psychology; Ecological validity; Behavioural sciences; Social psychology; Nomothetic; Experimental psychology; Epistemology; Cognition; Developmental psychology; Psychotherapist","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.2444506,0.00169009,0.001541153,0.00458468,0.002651837,0.005405365,0.002196855,0.002467876,0.007281967],"category_scores_gemma":[0.5179405,0.001284643,0.002407847,0.003026641,0.006366411,0.005982329,0.006889654,0.004234876,0.00114121],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001380415,"about_ca_system_score_gemma":0.001519627,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001033165,"about_ca_topic_score_gemma":0.0009536957,"domain_scores_codex":[0.7813038,0.1608153,0.01888867,0.01687258,0.02026852,0.001851032],"domain_scores_gemma":[0.2573583,0.5401947,0.05468269,0.1185952,0.02706525,0.002103698],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.008795229,0.005884644,0.4433029,0.005505435,0.00511166,0.0007273384,0.1139126,0.004133523,0.04761694,0.03131529,0.01180883,0.3218855],"study_design_scores_gemma":[0.001804815,0.009375139,0.7537187,0.001640522,0.002044433,0.001020096,0.01621897,0.02207791,0.05076256,0.08273564,0.05738948,0.001211702],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"methods","genre_scores_codex":[0.5979782,0.0009962253,0.355739,0.002266312,0.0008579755,0.01155988,0.001410805,0.001633911,0.02755769],"genre_scores_gemma":[0.8632465,0.0001937964,0.1186693,0.001264459,0.0002087968,0.01444306,0.0005927918,0.0003944155,0.0009869019],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7555494,"threshold_uncertainty_score":0.931727,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4827743902377341,"score_gpt":0.5657951970758375,"score_spread":0.08302080683810342,"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."}}