{"id":"W3205584125","doi":"10.64152/10125/67407","title":"Research Investigating Lexical Coverage and Lexical Profiling: What We Know, What We Don’t Know, and What Needs to be Examined","year":2021,"lang":"en","type":"article","venue":"Reading in a Foreign Language","topic":"Text Readability and Simplification","field":"Computer Science","cited_by":37,"is_retracted":false,"has_abstract":true,"ca_institutions":"Western University","funders":"","keywords":"Need to know; Profiling (computer programming); Psychology; Linguistics; Natural language processing; Computer science","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":["scholarly_communication"],"consensus_categories":[],"category_scores_codex":[0.001877123,0.000254859,0.0003751153,0.0004207992,0.0002705154,0.004154182,0.0004937812,0.0002335673,0.00001798469],"category_scores_gemma":[0.0007546196,0.0002437473,0.00005320631,0.00146953,0.0002552679,0.00507138,0.0007473055,0.0006147734,0.0000117882],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001772853,"about_ca_system_score_gemma":0.0001835763,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0000776403,"about_ca_topic_score_gemma":0.0001241201,"domain_scores_codex":[0.996866,0.0005156418,0.0004509295,0.000887383,0.0005901802,0.0006898949],"domain_scores_gemma":[0.9974606,0.001139394,0.00007036085,0.000786179,0.0001379348,0.0004055516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"qualitative","study_design_scores_codex":[0.00002995849,0.0001416478,0.001411745,0.0003287179,0.00001847162,0.0001941385,0.0463328,0.000045499,0.03833522,0.1812133,0.0001255222,0.731823],"study_design_scores_gemma":[0.003315166,0.001255086,0.007512805,0.01347549,0.00004836284,0.0009105065,0.4996475,0.09490281,0.2604057,0.09547354,0.02049449,0.002558478],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9512384,0.02546729,0.01000504,0.01167262,0.0001946932,0.0006213459,0.000003097764,0.0001480169,0.000649484],"genre_scores_gemma":[0.9743111,0.01077138,0.01330828,0.0007914037,0.0001339911,0.00008003152,0.00002915841,0.00002876217,0.0005459188],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7292645,"threshold_uncertainty_score":0.9968796,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06034828346412041,"score_gpt":0.3346003613303287,"score_spread":0.2742520778662083,"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."}}