{"id":"W4385572774","doi":"10.18653/v1/2022.emnlp-main.89","title":"Geographic Citation Gaps in NLP Research","year":2022,"lang":"en","type":"article","venue":"","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Research Council Canada","funders":"","keywords":"Citation; Publication; Field (mathematics); Computer science; Diversity (politics); China; Data science; Artificial intelligence; World Wide Web; Geography; Political science","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":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.01109955,0.0005634304,0.001198782,0.03218288,0.002477964,0.006701279,0.001611307,0.001748809,0.006818156],"category_scores_gemma":[0.1197081,0.0005403414,0.000729689,0.1011399,0.001820462,0.007411618,0.005555188,0.001344554,0.00298492],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00266557,"about_ca_system_score_gemma":0.002824471,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01005241,"about_ca_topic_score_gemma":0.01525818,"domain_scores_codex":[0.9800723,0.006547528,0.003348262,0.003647671,0.00567643,0.000707887],"domain_scores_gemma":[0.8458251,0.1078021,0.02449778,0.0111949,0.009023428,0.001656643],"domain_codex":null,"domain_gemma":"evaluation","domain_candidate":"evaluation","domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000645687,0.0001990059,0.3664932,0.01279852,0.0009527117,0.001345414,0.01738548,0.01205,0.002098189,0.1078344,0.2149619,0.2632355],"study_design_scores_gemma":[0.0001614121,0.00006132176,0.2469643,0.001897196,0.0002994923,0.001202985,0.007888689,0.007848232,0.002009899,0.0984778,0.63306,0.0001287361],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5359053,0.09654161,0.0268747,0.02430075,0.001349636,0.000315997,0.2431037,0.003112498,0.06849578],"genre_scores_gemma":[0.7398317,0.02027342,0.02106706,0.001498237,0.001475289,0.0008097453,0.2079794,0.0007685049,0.006296675],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.9889004,"threshold_uncertainty_score":0.05870074,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04003137957396832,"score_gpt":0.3559137284766063,"score_spread":0.315882348902638,"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."}}