{"id":"W3033222122","doi":"","title":"Improving and assessing data quality of knowledge graphs","year":2020,"lang":"en","type":"dissertation","venue":"Ghent University Academic Bibliography (Ghent University)","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"Vlaamse regering; Universiteit Gent; European Commission; Fonds Wetenschappelijk Onderzoek; Agentschap Innoveren en Ondernemen","keywords":"Knowledge graph; Data science; Computer science; Quality (philosophy); Data quality; Information retrieval; Data mining; Natural language processing; Engineering; Epistemology; Operations management; Philosophy","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.03925596,0.001813788,0.001867947,0.01522889,0.001744532,0.0101235,0.004100905,0.003027065,0.0022393],"category_scores_gemma":[0.2633693,0.001195547,0.00204531,0.01091524,0.002832606,0.009781123,0.005135585,0.002767448,0.0006180368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003799811,"about_ca_system_score_gemma":0.003988457,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01382208,"about_ca_topic_score_gemma":0.012448,"domain_scores_codex":[0.9480497,0.01614175,0.005517213,0.005939802,0.0230549,0.001296666],"domain_scores_gemma":[0.7008514,0.1837399,0.0210062,0.03211274,0.05958863,0.002701193],"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":[0.00190211,0.0004736484,0.1039284,0.006013528,0.001815066,0.001027556,0.004370356,0.2347185,0.008776274,0.05009749,0.02782323,0.5590539],"study_design_scores_gemma":[0.0003193576,0.0005285125,0.03694015,0.001666101,0.001040199,0.0007551216,0.003387693,0.7076436,0.01928897,0.1791082,0.04900917,0.000312974],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.2231982,0.0112772,0.7150935,0.006701556,0.001154777,0.001109087,0.01934944,0.01252465,0.009591569],"genre_scores_gemma":[0.6052346,0.003010286,0.3580652,0.000891284,0.0003529068,0.0004899644,0.02793379,0.001714803,0.002307271],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.03925596,"threshold_uncertainty_score":0.2076079,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2436425365669104,"score_gpt":0.4041145478195157,"score_spread":0.1604720112526053,"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."}}