{"id":"W3016358231","doi":"10.48550/arxiv.2004.08532","title":"DGL-KE: Training Knowledge Graph Embeddings at Scale","year":2020,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":36,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University","funders":"","keywords":"Knowledge graph; Graph; Training (meteorology); Scale (ratio); Computer science; Mathematics; Artificial intelligence; Theoretical computer science; Physics; Geography; Cartography","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0001687468,0.0005792658,0.0006076798,0.0003449059,0.0003629101,0.0001315124,0.003235656,0.0004173936,0.00003282151],"category_scores_gemma":[0.00003027421,0.0007016659,0.0005059054,0.001687261,0.0002469482,0.0005831798,0.005879243,0.001205853,0.0002295745],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0002727443,"about_ca_system_score_gemma":0.0001507104,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001559286,"about_ca_topic_score_gemma":0.00006773575,"domain_scores_codex":[0.9965072,0.0001617872,0.0003040228,0.002156953,0.0001367294,0.0007332515],"domain_scores_gemma":[0.9973797,0.000189413,0.0003558466,0.001435184,0.000148165,0.0004916427],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"simulation_or_modeling","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001828167,0.0002730523,0.004821682,0.000386269,0.0004340615,0.002383065,0.009151061,0.4857138,0.0009087172,0.4700662,0.01035819,0.01532104],"study_design_scores_gemma":[0.0008081757,0.0001052962,0.000897398,0.0002332663,0.00009949986,0.00002569079,0.0001682363,0.8411219,0.0004010859,0.1500293,0.004754863,0.00135536],"study_design_candidate":"simulation_or_modeling","study_design_consensus":"simulation_or_modeling","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1544835,0.000262136,0.8341252,0.0002973818,0.001445727,0.0004033855,0.00001734403,0.001041312,0.007924038],"genre_scores_gemma":[0.9899368,0.0002116521,0.006685572,0.0002694911,0.0001951419,0.000002015123,0.00002010294,0.00004735655,0.00263187],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8354533,"threshold_uncertainty_score":0.9995434,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1089707518289814,"score_gpt":0.2083999022472589,"score_spread":0.09942915041827745,"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."}}