{"id":"W4313589266","doi":"10.21203/rs.3.rs-2410184/v1","title":"Biomedical Text Readability and Cognitive Burden after Hypernym Substitution with Fine-Tuned Large Language Models","year":2023,"lang":"en","type":"preprint","venue":"Research Square","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Readability; Substitution (logic); Computer science; Cognition; Natural language processing; Linguistics; Artificial intelligence; Psychology; Programming language; Philosophy","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":[],"consensus_categories":[],"category_scores_codex":[0.003072406,0.0002933561,0.0003788497,0.0004348015,0.0002893751,0.0004474969,0.0008410093,0.0004428913,0.00003360157],"category_scores_gemma":[0.0007815672,0.0002343786,0.0000894602,0.000826004,0.0006444464,0.0004296797,0.002175309,0.001408821,0.0001230877],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002135295,"about_ca_system_score_gemma":0.0006505768,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001174046,"about_ca_topic_score_gemma":0.000655825,"domain_scores_codex":[0.9950432,0.0007512632,0.0003614512,0.001458508,0.001620821,0.0007647921],"domain_scores_gemma":[0.9965333,0.000896086,0.00008564238,0.001366671,0.0007796981,0.0003385757],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.004967109,0.005938077,0.06989794,0.02272882,0.001346374,0.00414578,0.1564073,0.001616103,0.00393288,0.1300613,0.002595357,0.5963629],"study_design_scores_gemma":[0.003652783,0.001985939,0.3574925,0.006725347,0.0001655152,0.0001236348,0.01143369,0.4724052,0.002554248,0.1373071,0.003074584,0.0030795],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7620103,0.0007667225,0.231353,0.002973399,0.0001147634,0.001635913,0.0004922415,0.0004053444,0.0002482803],"genre_scores_gemma":[0.9966163,0.00007514616,0.001765562,0.00001994305,0.0001729739,0.0006084368,0.0003607573,0.00002679593,0.0003540886],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5932834,"threshold_uncertainty_score":0.9557681,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0669732686738143,"score_gpt":0.3703418086020396,"score_spread":0.3033685399282253,"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."}}