{"id":"W2188957661","doi":"","title":"Linguistic Resources for 2011 Knowledge Base Population Evaluation.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"NIST; Computer science; Annotation; Knowledge base; Information extraction; Entity linking; Resource (disambiguation); Population; Information retrieval; Natural language processing; Artificial intelligence; Data science; World Wide Web","routes":{"ca_aff":false,"ca_fund":false,"ca_venue":true,"about_ca":false,"invisible_to_affiliation_only":true},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.008393687,0.00007356898,0.0001421386,0.0001431495,0.0002092222,0.00004429696,0.0003370911,0.00003244124,0.0003909956],"category_scores_gemma":[0.001664074,0.00005806372,0.00003883374,0.0001900053,0.0001956427,0.0001519158,0.00008801401,0.00002844967,0.00005546135],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000007728562,"about_ca_system_score_gemma":0.00002342157,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005040381,"about_ca_topic_score_gemma":0.00003374664,"domain_scores_codex":[0.9987589,0.0002464734,0.000392869,0.0002459575,0.0002576649,0.00009812115],"domain_scores_gemma":[0.9975335,0.001249357,0.0002050555,0.0005041974,0.0004618817,0.00004601907],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00006473711,0.00006394879,0.0002175626,0.00001936454,0.000009638625,1.517051e-8,0.003032863,0.000002866885,0.00001370786,0.9224995,0.0005370373,0.07353878],"study_design_scores_gemma":[0.000154116,0.00003159798,0.004381375,0.000003170652,0.00005959384,2.807027e-7,0.00224067,0.0001508814,0.0003720798,0.936503,0.05603423,0.00006899745],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0804024,0.002840982,0.7563149,0.0002066142,0.0002767921,0.002845629,0.0002968782,0.0001002575,0.1567155],"genre_scores_gemma":[0.9958867,0.00001497891,0.001696024,0.00003292629,0.0000780657,0.0003939252,0.00005047193,0.000005200649,0.001841749],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9154842,"threshold_uncertainty_score":0.4281128,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1597058808970285,"score_gpt":0.4099887425248145,"score_spread":0.250282861627786,"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."}}