{"id":"W3156463632","doi":"10.1145/3442381.3449977","title":"Typing Errors in Factual Knowledge Graphs: Severity and Possible Ways Out","year":2021,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":5,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"","keywords":"Computer science; Benchmark (surveying); Code (set theory); Artificial intelligence; Typing; Machine learning; Word error rate; Quality (philosophy); Natural language processing; Noisy data; Programming language; Speech recognition","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":[],"consensus_categories":[],"category_scores_codex":[0.0001498917,0.00007545315,0.0001064821,0.00006966748,0.0000512503,0.00008619885,0.0002168369,0.00004471046,0.00002776699],"category_scores_gemma":[0.00003614463,0.00007150143,0.00002347584,0.0002040573,0.00001617603,0.0002900968,0.0003319718,0.000108287,0.0000235199],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00002132244,"about_ca_system_score_gemma":0.00008038084,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005399206,"about_ca_topic_score_gemma":0.0007790516,"domain_scores_codex":[0.9992584,0.00003127741,0.0001371326,0.0003169682,0.00006733702,0.0001888767],"domain_scores_gemma":[0.9995664,0.00004289887,0.00001600503,0.0002785192,0.00003732908,0.0000588054],"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":[0.000004764296,0.0002204096,0.04156974,0.0001062823,0.00002793269,0.0001106838,0.02957796,0.0002941378,0.00222795,0.6982839,0.0008749685,0.2267013],"study_design_scores_gemma":[0.0008752892,0.00003366441,0.04691682,0.0001017854,0.000005200408,0.00005993697,0.001008031,0.8677727,0.008683956,0.07042108,0.003514506,0.0006070601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5064742,0.0006093682,0.4734625,0.000473245,0.0003530599,0.00005555011,4.827392e-7,0.000113903,0.01845769],"genre_scores_gemma":[0.9459311,0.00002549766,0.05295772,0.0001826143,0.00001579418,0.000002193604,4.99458e-7,0.000003434341,0.0008811551],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.8674785,"threshold_uncertainty_score":0.2915744,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.05126507019639383,"score_gpt":0.2772535504445526,"score_spread":0.2259884802481587,"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."}}