{"id":"W4381490040","doi":"10.3138/jsp-2022-0025","title":"Exploring Author, Article, and Venue Feature Sets for Rising Star Prediction in Academic Network","year":2023,"lang":"en","type":"article","venue":"Journal of Scholarly Publishing","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Machine learning; Computer science; Classifier (UML); Artificial intelligence; Empirical research; Set (abstract data type); Feature (linguistics); Ensemble learning; Supervised learning; Data science; Artificial neural network; Mathematics; Statistics","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["scholarly_communication"],"consensus_categories":["scholarly_communication"],"category_scores_codex":[0.006810761,0.00010501,0.0002125237,0.000485538,0.0002585237,0.008530272,0.0006318938,0.0001895869,2.558907e-7],"category_scores_gemma":[0.001982845,0.00009765343,0.00006120351,0.001160163,0.00001067416,0.05991183,0.0001705344,0.001749057,0.000001863269],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001277748,"about_ca_system_score_gemma":0.00008212973,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001114624,"about_ca_topic_score_gemma":0.000003108958,"domain_scores_codex":[0.9982397,0.0001424982,0.0004751348,0.0002200519,0.0005332188,0.0003894166],"domain_scores_gemma":[0.9987372,0.000288945,0.0003614864,0.0001661875,0.000274802,0.0001714121],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0001852405,0.0000765745,0.4635732,0.0002994692,0.0001679693,0.0003824638,0.05748057,0.01404459,0.02061615,0.01326115,0.220542,0.2093706],"study_design_scores_gemma":[0.003424614,0.0005034534,0.7262983,0.004126828,0.00003762868,0.0006322758,0.003562742,0.1564942,0.0006968169,0.01791793,0.08570658,0.0005986719],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9759656,0.001539802,0.009635731,0.01006191,0.002547374,0.0001219872,0.000003877042,0.00008506911,0.0000387137],"genre_scores_gemma":[0.9847383,0.0001469264,0.01339107,0.0001543372,0.001449882,0.00001247194,0.000001804665,0.00001745765,0.00008772261],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.262725,"threshold_uncertainty_score":0.992499,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1522723496817844,"score_gpt":0.317295330723369,"score_spread":0.1650229810415846,"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."}}