{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.004565291,0.002060834,0.002506277,0.01745324,0.002948885,0.005398626,0.002963531,0.003074193,0.01019375],"category_scores_gemma":[0.02525377,0.0008934878,0.002022544,0.01131342,0.001228931,0.01379952,0.005689151,0.002594918,0.007814558],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001113232,"about_ca_system_score_gemma":0.003283272,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007516256,"about_ca_topic_score_gemma":0.02134928,"domain_scores_codex":[0.9944277,0.001872721,0.0003957071,0.001431453,0.001497453,0.0003750107],"domain_scores_gemma":[0.9828817,0.005874726,0.0008644009,0.005950887,0.003783747,0.0006446954],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0006589007,0.0009430228,0.01570772,0.001543312,0.0007453674,0.0002986625,0.0009398741,0.02647489,0.01177604,0.02602471,0.1944886,0.7203988],"study_design_scores_gemma":[0.0003415573,0.0003743551,0.00975294,0.0005962322,0.001182017,0.0008189457,0.00207015,0.4489214,0.0316309,0.2766425,0.2274086,0.0002604696],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1085641,0.01288289,0.7251192,0.0112849,0.005326803,0.0007482213,0.03604605,0.07403465,0.02599317],"genre_scores_gemma":[0.2741241,0.003701847,0.6565786,0.003281307,0.002180849,0.0002034318,0.04116042,0.003528681,0.01524078],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9825467,"threshold_uncertainty_score":0.03410155,"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."}}