{"id":"W7001644685","doi":"","title":"Latent variable models for harmonization of test scores:a case study on memory","year":2020,"lang":"en","type":"other","venue":"TU/e Research Portal (Eindhoven University of Technology)","topic":"Psychometric Methodologies and Testing","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Test (biology); Harmonization; Variable (mathematics); Reliability (semiconductor); Latent variable; Observational study","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":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.004861542,0.0002411952,0.0008746739,0.004603336,0.0002186948,0.00002849259,0.001968961,0.0005778578,0.000769935],"category_scores_gemma":[0.02766716,0.0002233554,0.0001621245,0.005561203,0.0005238866,0.0001022851,0.0009019031,0.0007124122,0.00002504902],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00006330353,"about_ca_system_score_gemma":0.0003077052,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001858403,"about_ca_topic_score_gemma":0.0001741332,"domain_scores_codex":[0.9960856,0.0003061706,0.0005388139,0.0009335181,0.001663519,0.0004723179],"domain_scores_gemma":[0.9909405,0.006012754,0.0008694867,0.001193124,0.0008418316,0.0001423228],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"qualitative","study_design_scores_codex":[0.000559571,0.003824692,0.03541635,0.000499052,0.0009936477,0.009474341,0.00131413,0.001227755,0.001379532,0.008980764,0.8482674,0.08806276],"study_design_scores_gemma":[0.02644895,0.04833263,0.004549034,0.004216794,0.001272488,0.001275187,0.3859752,0.04876805,0.006120899,0.2101524,0.2578534,0.00503497],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"other","genre_gemma":"empirical","genre_scores_codex":[0.1188373,0.00166048,0.09412377,0.002700918,0.000874391,0.0121319,0.00230675,0.001360949,0.7660036],"genre_scores_gemma":[0.7368361,0.0002057465,0.06625568,0.00001789545,0.0001142844,0.00001202657,0.0000325629,0.0002533114,0.1962724],"genre_candidate":"other","genre_consensus":null,"teacher_disagreement_score":0.6179988,"threshold_uncertainty_score":0.9805232,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.4986817858837838,"score_gpt":0.4564420118672449,"score_spread":0.04223977401653889,"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."}}