{"id":"W2751763719","doi":"","title":"K-means and Hierarchical Clustering Method to Improve our Understanding of Citation Contexts","year":2017,"lang":"en","type":"preprint","venue":"HAL (Le Centre pour la Communication Scientifique Directe)","topic":"Computational and Text Analysis Methods","field":"Social Sciences","cited_by":4,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal","funders":"","keywords":"Cluster analysis; Citation; Computer science; Hierarchical clustering; Focus (optics); Set (abstract data type); Information retrieval; Data science; Phenomenon; Section (typography); World Wide Web; Artificial intelligence; Epistemology; Physics","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":[0.01380993,0.0001949741,0.0004136406,0.0002854507,0.0008549035,0.0004628832,0.0007562326,0.0002109903,0.00002364698],"category_scores_gemma":[0.004090704,0.0002133051,0.0001775396,0.0002360955,0.0002184143,0.0001300996,0.0009856208,0.0003816205,0.000003563377],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001479666,"about_ca_system_score_gemma":0.0003417022,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005622615,"about_ca_topic_score_gemma":0.0124411,"domain_scores_codex":[0.9906673,0.00752106,0.0004458506,0.0005757643,0.0005318643,0.0002581936],"domain_scores_gemma":[0.9946856,0.002485099,0.0005735356,0.0007385708,0.001284202,0.0002329159],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.0000258752,0.000151344,0.001236174,0.0001703404,0.0001649694,0.000002319216,0.07353912,0.00060024,0.001884209,0.5612603,0.0001584957,0.3608066],"study_design_scores_gemma":[0.001812965,0.000004046923,0.01997971,0.005183448,0.0004731499,0.000005961489,0.01441341,0.2826002,0.008309806,0.6459037,0.01953105,0.001782574],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.007277538,0.0001836308,0.9374531,0.01963641,0.0002189472,0.0003586447,0.00003055859,0.00005992042,0.03478124],"genre_scores_gemma":[0.7158939,0.00009721689,0.2806897,0.00004474157,0.00004368011,0.00002110302,0.00003987407,0.0000158599,0.003153865],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.7086164,"threshold_uncertainty_score":0.8698332,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06243913043965525,"score_gpt":0.3615403434242099,"score_spread":0.2991012129845546,"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."}}