{"id":"W2252260887","doi":"","title":"Building Readability Lexicons with Unannotated Corpora","year":2012,"lang":"en","type":"article","venue":"","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":6,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"","keywords":"Readability; Computer science; Lexicon; Natural language processing; Annotation; Artificial intelligence; Word (group theory); Information retrieval; Resource (disambiguation); Simple (philosophy); Term (time); Linguistics","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":[0.0004715824,0.00009821649,0.0001053169,0.00004115046,0.000105582,0.0000759341,0.0003869662,0.00004423054,0.00004605813],"category_scores_gemma":[0.00004372825,0.00006974542,0.00002650637,0.0003890908,0.00007985742,0.0009466049,0.00008288055,0.00008955772,0.00008067633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005236237,"about_ca_system_score_gemma":0.00005369163,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001152105,"about_ca_topic_score_gemma":0.00001565506,"domain_scores_codex":[0.9990389,0.00006301342,0.0001612646,0.0002603107,0.0001807324,0.0002957162],"domain_scores_gemma":[0.9988893,0.0001079362,0.00006253838,0.0007163463,0.00008278238,0.0001410852],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.00001011337,0.0002281861,0.07764527,0.00001217009,0.00001090498,9.192836e-7,0.0005277505,0.00002061303,0.003281732,0.8686439,0.0004404468,0.04917794],"study_design_scores_gemma":[0.0006386472,0.0003545196,0.7829315,0.00003683088,0.00002906482,0.0001814757,0.000153502,0.01991736,0.1014304,0.04525874,0.04787725,0.001190648],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.3109152,0.00001940943,0.6823294,0.0008368721,0.00008390439,0.0001296085,8.47507e-7,0.0003062856,0.005378496],"genre_scores_gemma":[0.8535013,5.558789e-7,0.146099,0.0001397707,0.0000237351,0.000009906563,0.00000162016,0.000003841665,0.000220304],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8233852,"threshold_uncertainty_score":0.2844136,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02464466633386138,"score_gpt":0.2583301695586538,"score_spread":0.2336855032247924,"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."}}