{"id":"W4413024604","doi":"10.1002/asi.70013","title":"Understanding discrepancies in the coverage of <scp>OpenAlex</scp> : The case of China","year":2025,"lang":"en","type":"article","venue":"Journal of the Association for Information Science and Technology","topic":"scientometrics and bibliometrics research","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université de Montréal; Bureau de Coopération Interuniversitaire; Université du Québec à Montréal","funders":"Fonds de recherche du Québec; China Scholarship Council; Social Sciences and Humanities Research Council of Canada; National Natural Science Foundation of China","keywords":"China; Computer science; Data science; Information retrieval; Geography","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[{"model":"gemma","categories":["bibliometrics","metaresearch"],"domain":"evaluation","study_design":"observational","genre":"empirical","about_ca_system":false,"about_ca_topic":false,"confidence":"low","status":"direct model label, unvalidated"},{"model":"gpt","categories":["bibliometrics"],"domain":null,"study_design":"design_other","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":["metaresearch","bibliometrics"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.04441822,0.00004749222,0.0001728993,0.01591107,0.000460774,0.0005297453,0.001941639,0.00007252412,0.000001019791],"category_scores_gemma":[0.1144452,0.00001957084,0.00007553293,0.08355657,0.0004544321,0.00161975,0.0003203875,0.000219868,5.167143e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002586191,"about_ca_system_score_gemma":0.0004015732,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003027513,"about_ca_topic_score_gemma":0.00004051379,"domain_scores_codex":[0.9961826,0.00009019184,0.000839073,0.00007276501,0.002625128,0.0001902358],"domain_scores_gemma":[0.9898437,0.004641227,0.001816756,0.0002778678,0.003399009,0.00002144136],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00001365187,0.00006677442,0.1927679,0.00002031708,0.00003291799,0.000001805518,0.004090281,0.0003316217,0.0006047405,0.7562651,0.008748167,0.03705675],"study_design_scores_gemma":[0.001608102,0.0003570908,0.2638918,0.00006737998,0.00003873861,0.0002048389,0.06739923,0.009288346,0.00680065,0.5997475,0.05053057,0.00006569522],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9605867,0.0001330103,0.007014241,0.02428059,0.0003700803,0.0003364198,0.00002058268,0.000002671698,0.007255763],"genre_scores_gemma":[0.9995866,0.00009821795,0.00006469374,0.0001146007,0.000005227492,0.000002557463,1.015226e-7,6.014827e-7,0.0001274143],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1565176,"threshold_uncertainty_score":0.9952427,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2534551526371789,"score_gpt":0.4762531204382082,"score_spread":0.2227979678010293,"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."}}