{"id":"W2807441601","doi":"","title":"Overview of Linguistic Resources for the TAC KBP 2015 Evaluations: Methodologies and Results.","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Linguistics; Natural language processing; Artificial intelligence; Philosophy","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.02182427,0.002161038,0.001714457,0.01349617,0.00286999,0.004995826,0.004658085,0.002039516,0.01812846],"category_scores_gemma":[0.07235658,0.0009474303,0.001252483,0.009009898,0.001159618,0.007370712,0.005872658,0.002518187,0.01302641],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003125106,"about_ca_system_score_gemma":0.008026792,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02708571,"about_ca_topic_score_gemma":0.03207611,"domain_scores_codex":[0.9740636,0.01247093,0.003000952,0.001792598,0.007752414,0.0009193931],"domain_scores_gemma":[0.9419708,0.02305673,0.001932307,0.00665133,0.02391542,0.002473385],"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":[0.004246365,0.003011617,0.01033624,0.01684674,0.001039375,0.0006125349,0.003680299,0.0125278,0.01271648,0.0084858,0.3356572,0.5908395],"study_design_scores_gemma":[0.002612622,0.002584145,0.0363195,0.008233937,0.0027089,0.001375182,0.007168818,0.05654673,0.05172282,0.01490057,0.8150134,0.0008133234],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1905467,0.0357514,0.1832742,0.005592255,0.00154509,0.02595524,0.362339,0.0424852,0.1525109],"genre_scores_gemma":[0.2140833,0.005700143,0.2987906,0.001179353,0.0002924372,0.0196595,0.4382547,0.003859253,0.01818066],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02708571,"threshold_uncertainty_score":0.1154191,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1006083672297149,"score_gpt":0.4152044565674748,"score_spread":0.31459608933776,"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."}}