{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002105325,0.00136675,0.001245776,0.01152246,0.001060597,0.003040637,0.001887921,0.001077022,0.01008995],"category_scores_gemma":[0.03117999,0.0009590969,0.001344307,0.007805217,0.0009825793,0.006448323,0.002789845,0.001862411,0.00625854],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001356895,"about_ca_system_score_gemma":0.001770335,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005063447,"about_ca_topic_score_gemma":0.01055495,"domain_scores_codex":[0.9967313,0.0008432277,0.0005074182,0.001065802,0.0007306574,0.0001217474],"domain_scores_gemma":[0.9767091,0.01387829,0.001887723,0.002722724,0.004350091,0.0004520678],"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":[0.0005608991,0.000705705,0.0353276,0.003933414,0.0004565199,0.001509172,0.006336263,0.0186347,0.06177227,0.0204428,0.08272776,0.767593],"study_design_scores_gemma":[0.0004198583,0.0006847423,0.1184158,0.001382623,0.0008748229,0.00288847,0.006567983,0.4277213,0.06539912,0.07608061,0.2988726,0.0006920241],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1350091,0.001014264,0.734512,0.0007266129,0.0004154913,0.001709531,0.07056368,0.02033189,0.03571742],"genre_scores_gemma":[0.3448904,0.0005992517,0.5090697,0.0002762569,0.0002378744,0.00355975,0.1318974,0.002647946,0.006821433],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.01152246,"threshold_uncertainty_score":0.03375429,"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."}}