{"id":"W2992174637","doi":"10.5539/elt.v13n1p31","title":"A Comparability Study of Text Difficulty and Task Characteristics of Parallel Academic IELTS Reading Tests","year":2019,"lang":"en","type":"article","venue":"English Language Teaching","topic":"Educational Technology and Assessment","field":"Computer Science","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Comparability; Scope (computer science); Task (project management); Psychology; Test (biology); Reading (process); Construct (python library); Reading comprehension; Natural language processing; Cognitive psychology; Computer science; Linguistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.0006409936,0.0001050386,0.0002602488,0.00008094572,0.00005440011,0.00001591249,0.0004610969,0.00007542034,0.000005311668],"category_scores_gemma":[0.0003854698,0.00009294734,0.00002439309,0.000110508,0.00004020733,0.0002150593,0.0002343545,0.0005180768,0.000001472494],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002527858,"about_ca_system_score_gemma":0.00002697708,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005384906,"about_ca_topic_score_gemma":0.000004387412,"domain_scores_codex":[0.998948,0.0001393193,0.0003151154,0.0002788634,0.0001779461,0.0001407749],"domain_scores_gemma":[0.99892,0.0003450096,0.0002190976,0.0004376912,0.00004150916,0.00003669169],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000009349077,0.0007936644,0.7243423,0.00008374903,0.0000400572,0.000003907771,0.2353788,0.00002465335,0.01038174,0.01513713,0.00003541939,0.01376931],"study_design_scores_gemma":[0.0007889308,0.0002863456,0.9492634,0.0001248641,0.00001862831,0.000005568365,0.04649046,0.001736153,0.0006352651,0.0003692109,0.00006610372,0.0002150888],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9976268,0.00006552528,0.001336056,0.00005795269,0.0001828825,0.0002608865,0.000005248035,0.00008915106,0.0003755162],"genre_scores_gemma":[0.9955729,0.000002608127,0.004300363,0.00001785473,0.00003966458,0.000008703848,0.000005165168,0.000004874315,0.00004785449],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2249211,"threshold_uncertainty_score":0.3790283,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01083677456860607,"score_gpt":0.2972518000888276,"score_spread":0.2864150255202215,"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."}}