{"id":"W4313400493","doi":"10.1007/s11192-022-04627-9","title":"An artificial intelligence-based framework for data-driven categorization of computer scientists: a case study of world’s Top 10 computing departments","year":2022,"lang":"en","type":"article","venue":"Scientometrics","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":11,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Regina","funders":"","keywords":"Computer science; Ranking (information retrieval); Context (archaeology); Cluster analysis; Metric (unit); Rank (graph theory); Artificial intelligence; Categorization; Rand index; Data mining; Index (typography); Artificial neural network; Machine learning; Information retrieval; Mathematics","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":[0.008770975,0.0005176658,0.0006014428,0.008321675,0.001952985,0.006515566,0.002726101,0.001665545,0.003206265],"category_scores_gemma":[0.01569603,0.0003109133,0.001385045,0.007675598,0.001689882,0.004214345,0.002334902,0.001318996,0.0008601992],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003805647,"about_ca_system_score_gemma":0.006000447,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02600744,"about_ca_topic_score_gemma":0.03497092,"domain_scores_codex":[0.9945046,0.00248333,0.0004650264,0.0008365056,0.001458824,0.0002516805],"domain_scores_gemma":[0.9910013,0.005356305,0.0005854733,0.000747511,0.001897326,0.0004120973],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"observational","study_design_scores_codex":[0.0003542264,0.001218932,0.04319157,0.0009659029,0.0003345136,0.001716009,0.007455666,0.08782403,0.0111055,0.4380489,0.01662454,0.3911603],"study_design_scores_gemma":[0.00004858895,0.000124636,0.009254722,0.0002162108,0.00009000459,0.0005829915,0.002648916,0.7392063,0.004834577,0.1988699,0.04402702,0.00009605027],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04363288,0.0003382438,0.9362899,0.004702513,0.00008523365,0.0009625572,0.002060441,0.001172155,0.01075608],"genre_scores_gemma":[0.2231421,0.0001184048,0.7724699,0.0002527901,0.00002901235,0.0003231892,0.001949544,0.00006259733,0.001652489],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9916783,"threshold_uncertainty_score":0.05171216,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.6906770264083343,"score_gpt":0.6059824450165449,"score_spread":0.08469458139178943,"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."}}