{"id":"W4317794535","doi":"10.5038/1936-4660.16.1.1420","title":"Establishing the Validity and Reliability of the LOCUS Assessments","year":2023,"lang":"en","type":"article","venue":"Numeracy","topic":"Statistics Education and Methodologies","field":"Mathematics","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Mount Saint Vincent University","funders":"National Science Foundation","keywords":"Psychology; Validity; Reliability (semiconductor); External validity; Test validity; Scale (ratio); Applied psychology; Psychometrics; Social psychology; Clinical psychology","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":[],"consensus_categories":[],"category_scores_codex":[0.1389491,0.0006182489,0.001062501,0.005458164,0.002068992,0.003626374,0.001608831,0.001064923,0.002196084],"category_scores_gemma":[0.3130435,0.000824274,0.001522516,0.002401103,0.003416794,0.003319757,0.00525623,0.002365879,0.001202389],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002555247,"about_ca_system_score_gemma":0.007018907,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002104907,"about_ca_topic_score_gemma":0.003468351,"domain_scores_codex":[0.8989066,0.04692171,0.01140744,0.005021466,0.03563397,0.002108805],"domain_scores_gemma":[0.6483608,0.1607719,0.02064312,0.03276066,0.1324855,0.004978019],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0009703419,0.001731029,0.5973676,0.000817967,0.0005572529,0.0002908968,0.02793684,0.00410029,0.006402437,0.02377221,0.005799696,0.3302535],"study_design_scores_gemma":[0.000434755,0.00545312,0.8603731,0.001397421,0.0004145979,0.0005910294,0.01311622,0.0222202,0.01554807,0.02674884,0.05332204,0.0003805424],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8347145,0.0006036591,0.1118682,0.001017874,0.0004281886,0.007958944,0.0009942714,0.000432946,0.0419814],"genre_scores_gemma":[0.8861294,0.0003109614,0.1011702,0.0001861731,0.00007551319,0.008639062,0.0008031745,0.0001307349,0.002554798],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1389491,"threshold_uncertainty_score":0.734842,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2793615220572844,"score_gpt":0.4826761901861915,"score_spread":0.203314668128907,"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."}}