{"id":"W4413888947","doi":"10.1007/978-3-032-03870-8_20","title":"Improving Text Readability to Support Student Comprehension and Learning: An LLM-Powered Approach","year":2025,"lang":"en","type":"book-chapter","venue":"Lecture notes in computer science","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Alberta","funders":"","keywords":"Readability; Computer science; Comprehension; Multimedia; Human–computer interaction; Artificial intelligence; Natural language processing; Programming language","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":[0.001331326,0.000786025,0.0007239404,0.001709775,0.0004081499,0.001995052,0.001753461,0.0009406709,0.01446728],"category_scores_gemma":[0.008136329,0.0002912476,0.0005833922,0.001423859,0.0004311364,0.002165054,0.002181148,0.001211357,0.004991943],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005804902,"about_ca_system_score_gemma":0.0009219531,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0004189177,"about_ca_topic_score_gemma":0.0006354426,"domain_scores_codex":[0.9987294,0.000356369,0.00006505552,0.0001841371,0.0005965391,0.00006855425],"domain_scores_gemma":[0.9951535,0.002339128,0.0004424399,0.0008656838,0.001004505,0.0001946649],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0001627783,0.0004872347,0.001502692,0.0006521789,0.00002407968,0.00009883181,0.0006395543,0.002113194,0.06668314,0.006560099,0.01079446,0.9102818],"study_design_scores_gemma":[0.0003357973,0.00326878,0.03325946,0.001172556,0.0005482908,0.001497273,0.001904453,0.1706856,0.4286535,0.08545104,0.2729908,0.0002324951],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1127075,0.00212698,0.7702523,0.003926734,0.000363667,0.0007707723,0.0008080137,0.01837125,0.09067284],"genre_scores_gemma":[0.5000405,0.001178172,0.4273949,0.0008111307,0.0003012097,0.0006958212,0.001151542,0.001558095,0.06686859],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01446728,"threshold_uncertainty_score":0.04839784,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0208712578425082,"score_gpt":0.2735095957058067,"score_spread":0.2526383378632985,"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."}}