{"id":"W2805879805","doi":"","title":"The 2016 TAC KBP BeSt Evaluation.","year":2016,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Topic Modeling","field":"Computer Science","cited_by":2,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science","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":[0.02012013,0.002961839,0.002306683,0.008467178,0.004381975,0.01075608,0.00528188,0.003648643,0.04807052],"category_scores_gemma":[0.09291692,0.001256908,0.001503493,0.005920022,0.001872091,0.0129806,0.007135543,0.004275957,0.05390538],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.004933879,"about_ca_system_score_gemma":0.009554579,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.06860908,"about_ca_topic_score_gemma":0.07422434,"domain_scores_codex":[0.9779662,0.008984576,0.001519196,0.002154963,0.008255203,0.001119806],"domain_scores_gemma":[0.9379873,0.01493202,0.001420028,0.00858861,0.03161904,0.005452952],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0006288141,0.0001985531,0.000698833,0.0006614655,0.00006697932,0.00008192293,0.0001801664,0.001087426,0.0006935309,0.002166899,0.9380705,0.055465],"study_design_scores_gemma":[0.001651312,0.0004469059,0.007773308,0.001696599,0.0003373783,0.0004784204,0.001258225,0.0209022,0.005808852,0.01472269,0.9446579,0.0002662562],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.04685632,0.02082381,0.04938192,0.04104441,0.02338306,0.002885616,0.4751851,0.05084198,0.2895978],"genre_scores_gemma":[0.07981133,0.00301843,0.06313191,0.004152257,0.001954533,0.002989556,0.7390485,0.01001777,0.09587575],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.06860908,"threshold_uncertainty_score":0.1608119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01721926072958735,"score_gpt":0.2739869869615991,"score_spread":0.2567677262320118,"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."}}