{"id":"W3003238448","doi":"","title":"Towards a Benchmark for Knowledge Base Exchange.","year":2019,"lang":"en","type":"article","venue":"Knowledge Discovery and Data Mining","topic":"Semantic Web and Ontologies","field":"Computer Science","cited_by":3,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Toronto","funders":"","keywords":"Benchmark (surveying); Computer science; Knowledge base; Base (topology); Artificial intelligence; Mathematics; Geology","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":[0.0007208461,0.0002050278,0.0002943584,0.0001125449,0.0001512757,0.0004078182,0.001516925,0.00008315215,0.00002611383],"category_scores_gemma":[0.0003035695,0.0001724583,0.00005414365,0.0002300087,0.00005892259,0.002455958,0.002036369,0.00008170996,0.00007628827],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001979108,"about_ca_system_score_gemma":0.000194593,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001337586,"about_ca_topic_score_gemma":0.0001063483,"domain_scores_codex":[0.9983631,0.00005485685,0.0002260779,0.000831961,0.00009597868,0.0004280029],"domain_scores_gemma":[0.9978231,0.0005453934,0.00007022358,0.001402694,0.00006018202,0.00009839171],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00008845452,0.0004216845,0.008537241,0.001129224,0.000125575,0.00001968133,0.01496991,0.000002163156,0.0007222385,0.08154622,0.07734869,0.8150889],"study_design_scores_gemma":[0.00540668,0.00104866,0.02348133,0.0009780242,0.0001668535,0.0001118931,0.006300933,0.3310945,0.003490946,0.006376818,0.6192675,0.002275936],"study_design_candidate":"design_other","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.394911,0.02876454,0.4653501,0.0007845408,0.005552466,0.001206063,0.0005166355,0.0004004933,0.1025142],"genre_scores_gemma":[0.9438825,0.000201714,0.04887032,0.0001921127,0.00042551,0.00005433085,0.0003094113,0.00002347078,0.006040652],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.812813,"threshold_uncertainty_score":0.7032644,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.06517942266695431,"score_gpt":0.3206417762695815,"score_spread":0.2554623536026271,"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."}}