{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","bibliometrics","scholarly_communication","open_science"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.04189893,0.0002325196,0.0006119534,0.152086,0.001194154,0.001628224,0.006528906,0.00007221501,0.00050893],"category_scores_gemma":[0.02086886,0.0002034104,0.0001477622,0.5139614,0.0003366939,0.0007391094,0.003036876,0.0003307525,0.00001211593],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003049129,"about_ca_system_score_gemma":0.0006097962,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003263329,"about_ca_topic_score_gemma":0.0001433762,"domain_scores_codex":[0.9798456,0.0007449447,0.001946404,0.001730446,0.01491634,0.0008161958],"domain_scores_gemma":[0.981778,0.008041147,0.001335089,0.002569471,0.005776648,0.0004995993],"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":[0.0002135182,0.01216143,0.1920584,0.0000556993,0.00008048384,0.0002312322,0.003410785,0.2095086,0.0002421397,0.006705624,0.002706028,0.5726261],"study_design_scores_gemma":[0.0004656335,0.002522631,0.002782987,0.000005662008,0.00003077428,0.00002222244,0.006041101,0.9828791,0.0006416523,0.003427812,0.0009292706,0.0002511447],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5279557,0.00004851952,0.4693736,0.00003158338,0.001350325,0.0008449333,0.0003486045,0.0000185628,0.00002815842],"genre_scores_gemma":[0.9356912,0.000001331177,0.06394059,0.00003928757,0.0001000234,0.00002629401,0.0001179751,0.00001888987,0.00006437374],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7733706,"threshold_uncertainty_score":0.9994082,"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."}}