{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.002474024,0.0007937466,0.001227764,0.01024184,0.002901715,0.003422946,0.001701448,0.001749863,0.008523],"category_scores_gemma":[0.02243494,0.0004385386,0.001746056,0.01294093,0.0008486539,0.003870296,0.001763872,0.001904339,0.003602329],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001572044,"about_ca_system_score_gemma":0.003427473,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01533975,"about_ca_topic_score_gemma":0.02432972,"domain_scores_codex":[0.9974993,0.0008970902,0.0002302785,0.0006075648,0.0006031849,0.0001624663],"domain_scores_gemma":[0.9900209,0.004738547,0.0005738399,0.001532653,0.002794204,0.0003399088],"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":[0.000290253,0.0003355835,0.01452566,0.001128317,0.0006642174,0.0004123535,0.003510625,0.04520421,0.01330238,0.1536846,0.05447727,0.7124645],"study_design_scores_gemma":[0.00006130895,0.0000734639,0.01446929,0.0002440179,0.0003973148,0.0004554112,0.001555555,0.5920305,0.009169857,0.3268188,0.05449386,0.0002307072],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.04547242,0.003168993,0.9336958,0.001475312,0.0006238002,0.0002603363,0.003019059,0.003350071,0.008934154],"genre_scores_gemma":[0.3370814,0.001444183,0.6454869,0.0003219685,0.00056014,0.0004720586,0.003370218,0.001038047,0.01022504],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9897581,"threshold_uncertainty_score":0.03050095,"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."}}