{"id":"W4235795010","doi":"10.32920/ryerson.14661732","title":"Benchmarking of semantic annotation systems","year":2021,"lang":"en","type":"preprint","venue":"","topic":"Topic Modeling","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Toronto Metropolitan University","funders":"","keywords":"Computer science; Benchmarking; Annotation; Natural language processing; Information retrieval; Semantic annotation; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.06453384,0.001832142,0.001488314,0.009161702,0.003208888,0.007497363,0.003660603,0.003069371,0.006315471],"category_scores_gemma":[0.1207667,0.0007116192,0.001503781,0.0063498,0.001967951,0.0108068,0.006769691,0.001895572,0.005438419],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003113991,"about_ca_system_score_gemma":0.003689379,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.003266775,"about_ca_topic_score_gemma":0.004176205,"domain_scores_codex":[0.8991154,0.05711244,0.008420585,0.01061514,0.02250468,0.002231794],"domain_scores_gemma":[0.8825113,0.04762902,0.004100754,0.02726654,0.03591998,0.002572411],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003220415,0.003286914,0.04201537,0.00786321,0.001964505,0.0008581761,0.01197138,0.04982503,0.0453159,0.02866009,0.04845027,0.7565687],"study_design_scores_gemma":[0.0005886261,0.005346079,0.1031423,0.003221202,0.001376825,0.002310583,0.01799078,0.3593332,0.1520523,0.04757979,0.3061111,0.000947157],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.4622283,0.007469304,0.4108097,0.002371416,0.002237285,0.003376784,0.01002686,0.02324635,0.07823396],"genre_scores_gemma":[0.6669275,0.001959624,0.2655307,0.0005701125,0.0003346567,0.001965262,0.04794322,0.003935444,0.01083343],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.06453384,"threshold_uncertainty_score":0.3412916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03099480714304642,"score_gpt":0.2569854635718852,"score_spread":0.2259906564288388,"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."}}