{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.01379022,0.001001835,0.001095,0.006599049,0.00172777,0.005028562,0.002324741,0.002217324,0.002063165],"category_scores_gemma":[0.1816948,0.001007973,0.0008910941,0.006045358,0.002785994,0.009462123,0.003200104,0.002781957,0.0008673514],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001495861,"about_ca_system_score_gemma":0.001705787,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00648413,"about_ca_topic_score_gemma":0.01054901,"domain_scores_codex":[0.981698,0.006201176,0.002117667,0.003920279,0.005131533,0.0009314222],"domain_scores_gemma":[0.7659968,0.1646601,0.01863785,0.02826646,0.02046595,0.001972999],"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":[0.001157024,0.0004918743,0.3400677,0.001973745,0.0006334186,0.002432543,0.00967634,0.06813906,0.008547074,0.05865157,0.03931605,0.4689136],"study_design_scores_gemma":[0.00009772828,0.0002169653,0.07170554,0.001492653,0.0005855728,0.004644278,0.008262115,0.5610619,0.03054544,0.2834719,0.03757199,0.0003439678],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5330738,0.003077712,0.434922,0.006064824,0.0008274029,0.0003123383,0.005663852,0.008037418,0.008020641],"genre_scores_gemma":[0.8511743,0.0008743508,0.1375658,0.0007394642,0.0001565437,0.0001187346,0.005361828,0.001530832,0.002478169],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.01379022,"threshold_uncertainty_score":0.07293051,"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."}}