{"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":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow","bibliometrics","open_science"],"consensus_categories":["bibliometrics"],"category_scores_codex":[0.003825003,0.0006172326,0.001231747,0.03776136,0.0006858157,0.0002896558,0.006696504,0.0008823823,0.0001483715],"category_scores_gemma":[0.00052707,0.0007052202,0.0005887733,0.04197406,0.0005676475,0.003967276,0.003568134,0.001559846,0.0000333368],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00008847148,"about_ca_system_score_gemma":0.0003169175,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.001012536,"about_ca_topic_score_gemma":0.0004591095,"domain_scores_codex":[0.9925716,0.001368492,0.001107333,0.002294987,0.002054667,0.0006029459],"domain_scores_gemma":[0.9931927,0.001312529,0.002265897,0.002015423,0.0006585406,0.0005548596],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002567043,0.001041917,0.07141232,0.003456302,0.002646978,0.0003436039,0.007004939,0.00001560196,0.003900211,0.4946084,0.3358399,0.07716283],"study_design_scores_gemma":[0.002628946,0.0001508551,0.08358756,0.0005122473,0.001450353,0.000002253257,0.0791741,0.0005280582,0.0001605772,0.007950171,0.8222827,0.001572122],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.704105,0.01903248,0.04005524,0.003163298,0.006288181,0.004437675,0.01118198,0.001201572,0.2105346],"genre_scores_gemma":[0.8147139,0.1413595,0.003370702,0.0004132176,0.0003127826,8.195551e-7,0.01113823,0.0001440943,0.02854672],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4866582,"threshold_uncertainty_score":0.9995399,"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."}}