{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.008062338,0.0003974176,0.0007093158,0.0190471,0.001760548,0.007188539,0.0008551857,0.0009950238,0.005903327],"category_scores_gemma":[0.1176973,0.0004126641,0.0007490084,0.01245527,0.003630242,0.008554831,0.004021529,0.001945665,0.0005009656],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002354996,"about_ca_system_score_gemma":0.002025949,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004475081,"about_ca_topic_score_gemma":0.004596584,"domain_scores_codex":[0.9923825,0.002645095,0.0005596299,0.0005521025,0.003431752,0.0004288009],"domain_scores_gemma":[0.7888609,0.1719094,0.01567568,0.006105574,0.01380342,0.00364516],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.001654333,0.0008975413,0.6350241,0.0008065751,0.001038794,0.001053878,0.005890341,0.02886854,0.006414833,0.1197326,0.005208951,0.1934095],"study_design_scores_gemma":[0.0001505417,0.0004020917,0.4101758,0.0002544411,0.0007799708,0.0006374432,0.01131309,0.140659,0.004838499,0.41904,0.01151425,0.0002347041],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9539765,0.001635235,0.0147743,0.003132779,0.00009560063,0.00008867105,0.0009902067,0.0001432069,0.02516345],"genre_scores_gemma":[0.9947211,0.0003065239,0.003753889,0.00006731485,0.0001385776,0.00002867105,0.0003596662,0.0000345308,0.0005896469],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9809529,"threshold_uncertainty_score":0.04263818,"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."}}