{"id":"W4406367101","doi":"10.1002/asi.24979","title":"Evaluating the linguistic coverage of <scp>OpenAlex</scp>: An assessment of metadata accuracy and completeness","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":44,"is_retracted":false,"has_abstract":true,"ca_institutions":"Université du Québec à Montréal; Lakehead University; Université de Montréal","funders":"Social Sciences and Humanities Research Council of Canada; Fonds de Recherche du Québec-Société et Culture; Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung","keywords":"Metadata; Computer science; Scopus; Publishing; English language; Completeness (order theory); World Wide Web; Quality (philosophy); Information retrieval; Library science; Linguistics; MEDLINE; Mathematics; Political science","routes":{"ca_aff":true,"ca_fund":true,"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"],"consensus_categories":["metaresearch","bibliometrics"],"category_scores_codex":[0.05486309,0.00005783109,0.0002520432,0.0124613,0.0004840068,0.0009241219,0.002057218,0.00007111753,0.000001370999],"category_scores_gemma":[0.2872457,0.00002908775,0.00005369115,0.04410224,0.0003871084,0.002722835,0.0006095876,0.0001935649,2.730366e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000136585,"about_ca_system_score_gemma":0.0008538084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000009754604,"about_ca_topic_score_gemma":0.000003343535,"domain_scores_codex":[0.9942976,0.0001192588,0.001058855,0.0001134705,0.004224605,0.0001862736],"domain_scores_gemma":[0.9719273,0.008112122,0.003310392,0.0004006712,0.01619774,0.00005171039],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.00001827494,0.0001079542,0.4237889,0.00004782922,0.00009236397,1.355773e-7,0.0009161767,0.0006864754,0.01038457,0.2058496,0.001286563,0.3568211],"study_design_scores_gemma":[0.001536363,0.0007928904,0.7469926,0.00005904626,0.00008134722,0.00001477655,0.003945458,0.09231553,0.009448286,0.1151413,0.02960697,0.00006539631],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9841245,0.000131612,0.01100402,0.002453394,0.0004067246,0.0003096046,0.00003722922,0.000003293124,0.001529565],"genre_scores_gemma":[0.9981253,0.0001097416,0.001526878,0.0001118562,0.000009286389,0.000003175426,6.190571e-7,9.387446e-7,0.0001122448],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.3567558,"threshold_uncertainty_score":0.9987316,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3736602032162077,"score_gpt":0.602059430984761,"score_spread":0.2283992277685533,"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."}}