{"id":"W3114226199","doi":"10.22452/mjlis.vol25no3.3","title":"Similarity indexes for scientometric research: A comparative analysis","year":2020,"lang":"en","type":"article","venue":"Malaysian Journal of Library & Information Science","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Agence Universitaire de la Francophonie","keywords":"Jaccard index; Similarity (geometry); Scientometrics; Computer science; Index (typography); Citation analysis; Information retrieval; Statistics; Citation; Mathematics; Artificial intelligence; Library science; Pattern recognition (psychology); World Wide Web","routes":{"ca_aff":false,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics","scholarly_communication"],"category_scores_codex":[0.05478487,0.0001608212,0.0006267215,0.2056576,0.0009204723,0.01116513,0.007216415,0.00007999659,0.0005996611],"category_scores_gemma":[0.05567328,0.0001091926,0.0004543319,0.659561,0.001336129,0.03547196,0.001127492,0.000619681,0.0001791365],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001064241,"about_ca_system_score_gemma":0.002040251,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000002613381,"about_ca_topic_score_gemma":2.772848e-7,"domain_scores_codex":[0.9769451,0.0003588125,0.002020997,0.0004359313,0.0193837,0.0008554413],"domain_scores_gemma":[0.9780642,0.005168298,0.001526762,0.0005782815,0.01298374,0.001678743],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0007713684,0.0003427733,0.7058786,0.00005788037,0.0003169615,0.00002425124,0.02038783,0.02107625,0.001403196,0.03077973,0.1265406,0.09242055],"study_design_scores_gemma":[0.00171174,0.002212238,0.4436045,0.00002151821,0.00008205752,0.00003135551,0.01143276,0.2898059,0.009432349,0.009939705,0.2312214,0.0005045522],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8592663,0.0002948005,0.09964037,0.01737266,0.0005471149,0.0006597885,0.0001672484,0.00003340958,0.02201829],"genre_scores_gemma":[0.9886415,0.00004299577,0.01017948,0.0008907131,0.0001309803,0.000004967143,0.000004787924,0.000003523092,0.0001010317],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4539033,"threshold_uncertainty_score":0.998155,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7831704493547128,"score_gpt":0.6110607620420506,"score_spread":0.1721096873126622,"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."}}