{"id":"W1999929076","doi":"10.1080/10627197.2011.584042","title":"Voices From Test-Takers: Further Evidence for Language Assessment Validation and Use","year":2011,"lang":"en","type":"article","venue":"Educational Assessment","topic":"Student Assessment and Feedback","field":"Social Sciences","cited_by":56,"is_retracted":false,"has_abstract":true,"ca_institutions":"Queen's University","funders":"Guangdong University of Foreign Studies; Ministry of Education, India; Ministry of Earth Sciences","keywords":"Test (biology); Language assessment; Psychology; Test validity; Scale (ratio); Coding (social sciences); Test score; Computer science; Psychometrics; Mathematics education; Standardized test; Developmental 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":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0007981853,0.0001567756,0.0001553686,0.00007561059,0.0004112134,0.0003189947,0.0002558788,0.00007516475,0.001931211],"category_scores_gemma":[0.0004854253,0.0001514935,0.0000648942,0.0001531375,0.0001318884,0.001056247,0.0000540769,0.0001031332,0.00002413667],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002746262,"about_ca_system_score_gemma":0.0007396631,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004590329,"about_ca_topic_score_gemma":0.0007340058,"domain_scores_codex":[0.9983507,0.000155092,0.0002588482,0.0003936194,0.0005638489,0.0002778464],"domain_scores_gemma":[0.996206,0.00306067,0.0001915675,0.0001979789,0.0002047774,0.0001390319],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001592754,0.0005150101,0.9355121,0.00001300655,0.00007642732,4.885773e-7,0.03221306,8.068428e-7,0.000948586,0.02444211,0.003796168,0.002466294],"study_design_scores_gemma":[0.0003171286,0.00007924424,0.9670038,0.00006335666,0.00007493111,2.041324e-7,0.02250137,0.0000601529,0.0001087253,0.005017477,0.004552266,0.0002213025],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9740303,0.0003001885,0.001592885,0.01055068,0.001103314,0.001072566,0.00007065481,0.00007311721,0.01120635],"genre_scores_gemma":[0.9415594,0.0001537736,0.05300405,0.0002679187,0.000772633,0.0003314223,0.0001056562,0.00001693733,0.003788183],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.05141116,"threshold_uncertainty_score":0.9989812,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1441623853519503,"score_gpt":0.4552257976525222,"score_spread":0.3110634123005719,"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."}}