{"id":"W4389005017","doi":"10.5430/jct.v12n6p347","title":"Content Words and Readability in Students’ Thesis Findings","year":2023,"lang":"en","type":"article","venue":"Journal of Curriculum and Teaching","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Readability; Bachelor; Computer science; Reading (process); Content (measure theory); Content analysis; Natural language processing; Linguistics; Lexical density; Mathematics education; Psychology; Lexical item; Mathematics","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":[0.002649822,0.00007237132,0.0001753916,0.0001639147,0.0001005732,0.0001707103,0.0002934233,0.00003728139,0.00000100003],"category_scores_gemma":[0.0003396537,0.00005283334,0.00003969051,0.0001387523,0.00003137868,0.0005238857,0.0001384864,0.0002837504,0.000001132881],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003728285,"about_ca_system_score_gemma":0.00001754292,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00008603215,"about_ca_topic_score_gemma":0.00001810604,"domain_scores_codex":[0.9989638,0.0001534913,0.0003338292,0.0001506586,0.000262905,0.0001353],"domain_scores_gemma":[0.999431,0.0002005495,0.0001217754,0.0001346542,0.00003715082,0.00007487667],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000004411194,0.0001131034,0.89139,0.00002050573,0.000009855169,0.00001525885,0.004813182,0.000006368746,0.0004943187,0.007374649,0.00005041566,0.09570792],"study_design_scores_gemma":[0.0002456791,0.000081853,0.9913656,0.00007744615,0.000006529865,0.00006426854,0.0015517,0.002006332,0.00008049524,0.004087649,0.0003512583,0.00008124157],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9931951,0.000124153,0.005005322,0.001406258,0.0001057329,0.00006266069,3.805755e-7,0.00002073311,0.00007973138],"genre_scores_gemma":[0.9983832,0.00006609342,0.001448162,0.00004256356,0.0000296486,0.000001430198,1.761521e-7,0.000002361744,0.00002632375],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.09997553,"threshold_uncertainty_score":0.2154481,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03112994362675947,"score_gpt":0.2941948043226865,"score_spread":0.263064860695927,"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."}}