{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.07453757,0.001195136,0.00257772,0.06205319,0.001970927,0.009139173,0.001430015,0.001287357,0.005583625],"category_scores_gemma":[0.1975997,0.0006570002,0.002272544,0.10189,0.002231253,0.01038875,0.004331314,0.001755626,0.001350858],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00434037,"about_ca_system_score_gemma":0.00438753,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001336755,"about_ca_topic_score_gemma":0.001213258,"domain_scores_codex":[0.8949797,0.05995177,0.009533884,0.003317943,0.0313492,0.0008674485],"domain_scores_gemma":[0.8203894,0.1431303,0.00566536,0.008638631,0.02097485,0.001201445],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0004566347,0.0002905865,0.02976431,0.006576991,0.001726144,0.0002724839,0.005457509,0.007467634,0.002564692,0.1589283,0.01392203,0.7725727],"study_design_scores_gemma":[0.0003811998,0.003124586,0.1903282,0.008366444,0.002812829,0.002000576,0.01922322,0.1489948,0.008709783,0.3304421,0.2846316,0.0009847285],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.1378478,0.04519512,0.7170455,0.003387167,0.001795654,0.002866707,0.004814495,0.002852191,0.08419535],"genre_scores_gemma":[0.3344848,0.01343008,0.6439296,0.0001510838,0.0006106707,0.002514393,0.002917352,0.0006741604,0.001287898],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9379468,"threshold_uncertainty_score":0.394197,"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."}}