{"id":"W2524791359","doi":"10.1007/s11192-016-2134-8","title":"The linguistic patterns and rhetorical structure of citation context: an approach using n-grams","year":2016,"lang":"en","type":"article","venue":"Scientometrics","topic":"Topic Modeling","field":"Computer Science","cited_by":50,"is_retracted":false,"has_abstract":false,"ca_institutions":"Université de Montréal; Université du Québec à Montréal","funders":"","keywords":"Rhetorical question; Citation; Linguistics; Context (archaeology); Computer science; Linguistic context; Function (biology); Natural (archaeology); Natural language processing; Information retrieval; Linguistic analysis; History; Library science; Philosophy; Biology","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":[0.0007221449,0.00007224044,0.00009236571,0.000492243,0.0001561838,0.000180824,0.000571169,0.00004254263,8.407481e-7],"category_scores_gemma":[0.001240445,0.00003958286,0.00002012096,0.002405575,0.0000808344,0.0002217495,0.000165448,0.00005785301,3.614922e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00005509664,"about_ca_system_score_gemma":0.00004327997,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00004154988,"about_ca_topic_score_gemma":0.000007373903,"domain_scores_codex":[0.9986974,0.0000668227,0.0001863581,0.0002959526,0.0005499657,0.0002034971],"domain_scores_gemma":[0.9988305,0.0003087219,0.0001082421,0.0004034295,0.0002509523,0.00009814324],"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":[0.000004558396,0.0000559617,0.06857125,0.00003529806,0.00001242354,0.000001826654,0.003293814,0.0002860831,0.006552438,0.1421149,0.000008265692,0.7790632],"study_design_scores_gemma":[0.0005367494,0.0001068045,0.03740083,0.00003714938,0.00001176787,0.00001884729,0.0001949255,0.946605,0.001767439,0.01270424,0.0003728088,0.0002434231],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.4092207,0.00008304675,0.5901917,0.00003396341,0.000377021,0.00005003508,0.000003036854,0.00001535317,0.00002511231],"genre_scores_gemma":[0.9626554,0.000008811357,0.03722548,0.00002188315,0.00006384227,5.666193e-7,4.369285e-7,0.000003729841,0.00001984146],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9463189,"threshold_uncertainty_score":0.174369,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08286568018633636,"score_gpt":0.3170019493522849,"score_spread":0.2341362691659486,"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."}}