{"id":"W4280604520","doi":"10.21203/rs.3.rs-1639305/v1","title":"Graph Neural Networks: a bibliometrics overview","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":16,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Bibliometrics; Computer science; Field (mathematics); Data science; Scopus; Artificial intelligence; Subject (documents); Graph; Convolutional neural network; Science and engineering; Library science; Engineering ethics; Political science; Engineering","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"review","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"high","status":"direct model label, unvalidated"}],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","bibliometrics","scholarly_communication","open_science","research_integrity"],"consensus_categories":["bibliometrics","open_science"],"category_scores_codex":[0.003532927,0.0005741825,0.0007035683,0.01629044,0.0009212719,0.001274074,0.007523279,0.0004240471,0.0002651737],"category_scores_gemma":[0.0005325528,0.0005713935,0.0006088307,0.06885967,0.0002592175,0.0006683217,0.02371606,0.007495738,0.00003241044],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003761904,"about_ca_system_score_gemma":0.0002840921,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001188242,"about_ca_topic_score_gemma":0.00002172162,"domain_scores_codex":[0.9891484,0.002015166,0.0006744371,0.002087487,0.004023124,0.002051382],"domain_scores_gemma":[0.9926801,0.001831603,0.0002848986,0.003811478,0.0008049129,0.0005869601],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.00004979417,0.0003813443,0.004906148,0.001138525,0.0001354243,0.001237105,0.0002589651,0.7167008,0.000006059687,0.04975287,0.04718751,0.1782455],"study_design_scores_gemma":[0.0004233108,0.000514815,0.007636329,0.0003570369,0.00001195665,0.00004100198,0.00005935304,0.8745436,0.000007026704,0.07758165,0.03780043,0.001023498],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.009598502,0.1992773,0.764763,0.005449646,0.00850571,0.005824002,0.0001743318,0.00256075,0.003846801],"genre_scores_gemma":[0.8806549,0.08128332,0.02935285,0.001449951,0.002108765,0.003004806,0.0004302954,0.0003563202,0.001358795],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8710564,"threshold_uncertainty_score":0.9997627,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1496516874135247,"score_gpt":0.4316644671126066,"score_spread":0.2820127796990819,"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."}}