{"id":"W4392022385","doi":"10.1177/25152459231217932","title":"Tempered Expectations: A Tutorial for Calculating and Interpreting Prediction Intervals in the Context of Replications","year":2024,"lang":"en","type":"article","venue":"Advances in Methods and Practices in Psychological Science","topic":"Mental Health Research Topics","field":"Psychology","cited_by":9,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Guelph","funders":"Social Sciences and Humanities Research Council","keywords":"Replication (statistics); Consistency (knowledge bases); Computer science; Context (archaeology); Statistic; Confidence interval; Interpretation (philosophy); Interval (graph theory); Prediction interval; Statistics; Artificial intelligence; Data science; Machine learning; 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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.01134122,0.00006885824,0.000140076,0.0001853111,0.00009292705,0.00007035914,0.0002470229,0.00006059335,0.00001919936],"category_scores_gemma":[0.009129154,0.00004557863,0.00001608434,0.0008426831,0.0005143504,0.0006573872,0.00005820963,0.0003375105,4.377244e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0000450994,"about_ca_system_score_gemma":0.00002002368,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009499301,"about_ca_topic_score_gemma":0.00008854224,"domain_scores_codex":[0.9975117,0.001136716,0.0004646079,0.0005022264,0.0001578734,0.000226902],"domain_scores_gemma":[0.9911419,0.008406157,0.0001863514,0.0001962003,0.00003350631,0.00003592431],"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":[0.0001799409,0.0001245449,0.01560449,0.00009136415,0.000002087444,0.000004433694,0.01845074,0.000003407343,0.001704686,0.05314009,0.00001194476,0.9106823],"study_design_scores_gemma":[0.003841352,0.004428419,0.3039859,0.002121687,0.00003313487,0.0002847958,0.2721059,0.05541474,0.0007422819,0.2853406,0.07107238,0.0006288795],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9224237,0.02296859,0.03374558,0.004118521,0.002154589,0.001868526,0.00001711874,0.0000287517,0.01267465],"genre_scores_gemma":[0.9086719,0.0006871497,0.0899985,0.0001603066,0.00005526569,0.0004128985,8.957321e-7,0.000002906417,0.0000102439],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9100534,"threshold_uncertainty_score":0.9992174,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1850727433818254,"score_gpt":0.6805398545476518,"score_spread":0.4954671111658264,"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."}}