{"id":"W2970808735","doi":"10.18653/v1/d19-1069","title":"KnowledgeNet: A Benchmark Dataset for Knowledge Base Population","year":2019,"lang":"en","type":"article","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":45,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Alberta","funders":"Natural Sciences and Engineering Research Council of Canada","keywords":"Benchmark (surveying); Computer science; Natural language processing; Base (topology); Population; Artificial intelligence; Knowledge base; Joint (building); Geography; Cartography; Engineering; Demography; Mathematics; Sociology","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":[],"consensus_categories":[],"category_scores_codex":[0.0002702952,0.00008696677,0.0001019254,0.0000668594,0.00004781216,0.00006656735,0.0005075631,0.00004156489,0.0001308185],"category_scores_gemma":[0.00003368627,0.00007776544,0.00003774538,0.0001280445,0.000003833958,0.0003491027,0.0002003113,0.00003887657,0.0004016905],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00003450279,"about_ca_system_score_gemma":0.00004067736,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00003504905,"about_ca_topic_score_gemma":0.00007625273,"domain_scores_codex":[0.9991509,0.00002366592,0.0001632413,0.0003663894,0.00008226457,0.0002135656],"domain_scores_gemma":[0.9990431,0.00009995658,0.00003469871,0.0007062824,0.00004991644,0.00006605159],"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":[0.00001401672,0.0002156259,0.01025584,0.0001836781,0.00002990928,0.000001452829,0.0006722028,0.001559152,0.001470284,0.63778,0.1132863,0.2345315],"study_design_scores_gemma":[0.0003748875,0.00004171668,0.001057841,0.00001052566,0.000003260791,0.000001921327,0.000008798682,0.9157022,0.0004004111,0.005426536,0.07681304,0.0001588578],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.01635056,0.0001515273,0.9727568,0.0001934102,0.0008395255,0.0004414537,0.00008025373,0.00009361705,0.009092826],"genre_scores_gemma":[0.7881288,0.000001779401,0.2076379,0.0002552771,0.0001578536,0.00003324235,0.0007196965,0.000009641004,0.003055759],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.914143,"threshold_uncertainty_score":0.5163053,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03238429445618977,"score_gpt":0.2885714976084831,"score_spread":0.2561872031522933,"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."}}