{"id":"W4310153872","doi":"10.1007/s13042-022-01686-5","title":"MORE: Toward Improving Author Name Disambiguation in Academic Knowledge Graphs","year":2022,"lang":"en","type":"article","venue":"International Journal of Machine Learning and Cybernetics","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Calgary","funders":"International Science and Technology Cooperation Programme; National Key Research and Development Program of China","keywords":"Computer science; Embedding; Cluster analysis; Artificial intelligence; Graph; Graph embedding; Representation (politics); Similarity (geometry); Hierarchical clustering; Feature learning; Machine learning; Task (project management); Data mining; Theoretical computer science; Image (mathematics)","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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.005398422,0.00009388833,0.0001829441,0.0005647379,0.0001061737,0.0001590943,0.0008307124,0.00003535646,0.0002681745],"category_scores_gemma":[0.002423246,0.0000799195,0.00008013385,0.0002731723,0.0000557252,0.000239898,0.0006139562,0.0009578096,0.0000100217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009579493,"about_ca_system_score_gemma":0.00005333594,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001124695,"about_ca_topic_score_gemma":0.00002321444,"domain_scores_codex":[0.9969273,0.0004854287,0.0008010737,0.0001928739,0.001462443,0.0001308579],"domain_scores_gemma":[0.9984496,0.0005375717,0.000628783,0.00008567733,0.0002274735,0.00007085946],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0002835909,0.0002496536,0.1126421,0.00001127353,0.00009466945,0.0001071799,0.01378333,0.0145704,0.0004428453,0.02250196,0.003305903,0.8320071],"study_design_scores_gemma":[0.003201894,0.0007535304,0.1210058,0.0001060355,0.00006424116,0.0003961024,0.01568528,0.1826668,0.0000934226,0.08445354,0.5911038,0.0004695521],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9707275,0.005309106,0.007464955,0.01342208,0.001939907,0.0001056123,0.0000371495,0.00001847701,0.0009752258],"genre_scores_gemma":[0.9965796,0.0003165625,0.0005287974,0.0002162445,0.0001149414,0.000002994857,0.00001355398,0.000007921338,0.002219354],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8315376,"threshold_uncertainty_score":0.4161259,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08535776253208069,"score_gpt":0.4255861532448205,"score_spread":0.3402283907127398,"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."}}