{"id":"W6962764716","doi":"10.17605/osf.io/xmnzb","title":"Detecting Item and Test Functioning of LSAS-SR Scale Across Seven Countries: An analysis of the SMARVUS dataset","year":2023,"lang":"en","type":"other","venue":"Open Science Framework","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Scale (ratio); Differential item functioning; Test (biology); Item response theory; Differential (mechanical device)","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","sts"],"consensus_categories":[],"category_scores_codex":[0.005395204,0.0003728441,0.000951996,0.0006989142,0.0009118174,0.0009707335,0.004954612,0.0003852932,0.0006925326],"category_scores_gemma":[0.007396383,0.0002878316,0.0001143047,0.01347954,0.003236162,0.0008255452,0.003142552,0.0005994585,0.0001409577],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001816961,"about_ca_system_score_gemma":0.0004466191,"about_ca_topic_candidate":true,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.006386193,"about_ca_topic_score_gemma":0.02621911,"domain_scores_codex":[0.9958039,0.0001463755,0.0006131147,0.001263543,0.001476229,0.0006968713],"domain_scores_gemma":[0.9934264,0.001679732,0.001514014,0.002939182,0.0002432038,0.0001974419],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001031669,0.0002681628,0.9284147,0.0002491501,0.001143417,0.000009814364,0.01179382,0.001630141,0.002647635,0.0002956527,0.04549911,0.007945256],"study_design_scores_gemma":[0.001530358,0.0006222345,0.519345,0.01202152,0.006535195,0.00003970652,0.0519368,0.01758691,0.006690216,0.0006564928,0.3790633,0.00397224],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6798292,0.001057637,0.001549127,0.0003050796,0.00407709,0.006847891,0.2591973,0.001121202,0.04601541],"genre_scores_gemma":[0.9309478,0.0001358288,0.01531521,0.0003459233,0.0004663991,0.0001729448,0.0009553914,0.002304444,0.0493561],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4090697,"threshold_uncertainty_score":0.9999574,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02873789530748104,"score_gpt":0.3613532860714376,"score_spread":0.3326153907639566,"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."}}