{"id":"W2967837635","doi":"10.1016/j.joi.2019.07.004","title":"Analyzing linguistic complexity and scientific impact","year":2019,"lang":"en","type":"article","venue":"Journal of Informetrics","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":74,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal","funders":"Qinglan Project of Jiangsu Province of China; Major Program of National Fund of Philosophy and Social Science of China","keywords":"Computer science; Linguistics; Linguistic sequence complexity; Natural language processing; Data science; 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":[0.001134585,0.00008780943,0.0001969932,0.001228811,0.00008514188,0.0006589502,0.0006823311,0.00004483468,0.000008700011],"category_scores_gemma":[0.001240697,0.00006068455,0.00008380615,0.002072843,0.00005991041,0.0009375507,0.0001900956,0.0002787869,0.000007115701],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009304599,"about_ca_system_score_gemma":0.0001770119,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007411035,"about_ca_topic_score_gemma":7.124311e-7,"domain_scores_codex":[0.9989768,0.0000143843,0.0003574893,0.00009936048,0.0003773911,0.0001745937],"domain_scores_gemma":[0.9984486,0.000155974,0.0004678817,0.0002230102,0.0005958303,0.0001086883],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00008800341,0.0002067353,0.241246,0.0004746381,0.0002213845,0.0002161552,0.004858661,0.0001926563,0.006588845,0.1996656,0.004434083,0.5418073],"study_design_scores_gemma":[0.004951824,0.005495757,0.1454226,0.001572761,0.0001835895,0.006089255,0.0003182428,0.216072,0.02823632,0.5646284,0.02433107,0.002698166],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5171636,0.00822198,0.4724397,0.000119735,0.001038274,0.0001047901,0.000002125259,0.0000858498,0.0008239539],"genre_scores_gemma":[0.7005275,0.00001681925,0.299332,0.00002725949,0.00003783292,6.629558e-8,2.774665e-7,0.000002600428,0.00005557611],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5391091,"threshold_uncertainty_score":0.6354272,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02438825478114541,"score_gpt":0.3143265421653923,"score_spread":0.2899382873842469,"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."}}