{"id":"W2187127363","doi":"","title":"Linguistic Resources for 2012 Knowledge Base Population Evaluations","year":2012,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":24,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"NIST; Computer science; Annotation; Knowledge base; Selection (genetic algorithm); Population; Information extraction; Resource (disambiguation); Entity linking; Track (disk drive); Information retrieval; Base (topology); Natural language processing; Data science; Artificial intelligence","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":[0.00100616,0.00007018273,0.00009030248,0.00008330976,0.0001918303,0.00003503275,0.000249962,0.00003941718,0.000005062488],"category_scores_gemma":[0.0002428641,0.00006088136,0.00002328496,0.0002034674,0.00008165577,0.0003468714,0.00007047677,0.00004348096,0.000002589444],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001083121,"about_ca_system_score_gemma":0.00001841023,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000005760404,"about_ca_topic_score_gemma":0.00000175691,"domain_scores_codex":[0.9994724,0.00006281383,0.0001492892,0.0001202271,0.00006537783,0.0001299306],"domain_scores_gemma":[0.9989728,0.0004401376,0.00009597767,0.0002766736,0.0001661995,0.00004826638],"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":[0.000005953988,0.00003500112,0.000109444,0.00004226958,0.000003827535,5.690766e-9,0.001493534,6.369693e-7,0.0004416204,0.9570556,0.0000453944,0.04076666],"study_design_scores_gemma":[0.00006616021,0.00001700224,0.0003941614,0.000009913317,0.00002382965,0.000002053936,0.00006810408,0.0002412852,0.008219618,0.9834858,0.00738559,0.0000864383],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.002546487,0.01219372,0.9834414,0.00006965967,0.00004178505,0.0003380084,0.000007711288,0.000160517,0.001200706],"genre_scores_gemma":[0.885408,0.00001128217,0.1138044,0.0000197806,0.0001429503,0.0002810057,0.00001391128,0.000005428853,0.0003131525],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.8828616,"threshold_uncertainty_score":0.248267,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01694563726183529,"score_gpt":0.3279130043055564,"score_spread":0.3109673670437211,"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."}}