{"id":"W3127848318","doi":"10.48550/arxiv.2102.02307","title":"Typing Errors in Factual Knowledge Graphs: Severity and Possible Ways Out","year":2021,"lang":"en","type":"preprint","venue":"arXiv (Cornell University)","topic":"Advanced Graph Neural Networks","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Computer science; Benchmark (surveying); Code (set theory); Typing; Artificial intelligence; Word error rate; Quality (philosophy); Natural language processing; Machine learning; Noisy data; Programming language; Speech recognition","routes":{"ca_aff":true,"ca_fund":true,"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":[0.0001804096,0.0003879091,0.0004475125,0.0004281821,0.0001576017,0.0001543908,0.001261671,0.000353123,0.000009951752],"category_scores_gemma":[0.00003551857,0.0004715094,0.0001742096,0.001014347,0.000167006,0.0007377583,0.003367364,0.001065754,0.00001380629],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001539062,"about_ca_system_score_gemma":0.0001631771,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00007866004,"about_ca_topic_score_gemma":0.0009159367,"domain_scores_codex":[0.9975559,0.0001591024,0.0002343053,0.001478469,0.00006692734,0.0005053448],"domain_scores_gemma":[0.9983679,0.000149329,0.0001751921,0.0009885757,0.0001141888,0.0002048174],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001366439,0.0007366972,0.0911154,0.0006950666,0.0003470137,0.004018938,0.01278125,0.3915947,0.00025014,0.4806944,0.0005073017,0.01712244],"study_design_scores_gemma":[0.001032808,0.00006768438,0.03055795,0.0005521705,0.00005235779,0.00002421376,0.0005793606,0.8020823,0.0002452365,0.1630555,0.0003021654,0.001448206],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7235738,0.0006732962,0.2733312,0.00004146855,0.000778227,0.0002288091,0.000005670767,0.0002054459,0.001162027],"genre_scores_gemma":[0.9953831,0.0007540134,0.003394647,0.00007157993,0.00002973756,0.000001008496,0.00001060746,0.00001886738,0.0003364727],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4104876,"threshold_uncertainty_score":0.9997737,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.08504675677406587,"score_gpt":0.2124408258249891,"score_spread":0.1273940690509232,"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."}}