{"id":"W2860074735","doi":"10.1371/journal.pone.0197775","title":"Words by the tail: Assessing lexical diversity in scholarly titles using frequency-rank distribution tail fits","year":2018,"lang":"en","type":"article","venue":"PLoS ONE","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":21,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Université de Montréal","funders":"","keywords":"Zipf's law; Word lists by frequency; Discipline; Scientometrics; Microdata (statistics); Rank (graph theory); Diversity (politics); Computer science; Statistics; Social science; Natural language processing; Mathematics; Sociology; Library science; Population; Demography","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":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.006739102,0.0005225171,0.0008253263,0.01874417,0.0008841117,0.003969681,0.0008425367,0.001160356,0.004019091],"category_scores_gemma":[0.06224837,0.0002239585,0.0007656227,0.01620511,0.001476986,0.005185857,0.002441998,0.0008195596,0.001958749],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007808967,"about_ca_system_score_gemma":0.0006721917,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.002552217,"about_ca_topic_score_gemma":0.002130032,"domain_scores_codex":[0.9955936,0.001246037,0.0004733576,0.0006883205,0.00171375,0.0002849531],"domain_scores_gemma":[0.9424825,0.03691295,0.009159059,0.004139706,0.005724087,0.001581662],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007431463,0.000142728,0.8196965,0.000423535,0.0004912815,0.0003481821,0.003463836,0.009320214,0.00655535,0.008451019,0.002817101,0.1475472],"study_design_scores_gemma":[0.00003182888,0.0004465874,0.9067233,0.0001413238,0.0001652914,0.0008208621,0.003933519,0.05342269,0.005065349,0.02133726,0.007711999,0.0001999647],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9283182,0.001016736,0.05520467,0.0002048895,0.00003701126,0.0001120876,0.003294047,0.0008489289,0.01096351],"genre_scores_gemma":[0.9910927,0.0001274986,0.005622351,0.00002883452,0.0000368638,0.00006158389,0.002220304,0.00007665365,0.0007331722],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9812558,"threshold_uncertainty_score":0.03564018,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.686871493058404,"score_gpt":0.5087649493474646,"score_spread":0.1781065437109394,"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."}}