{"id":"W2404580422","doi":"","title":"Benchmarks for Enterprise Linking: Thomson Reuters R&D at TAC 2013.","year":2013,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"Benchmark (surveying); Task (project management); Computer science; Domain (mathematical analysis); Named-entity recognition; Entity linking; Information retrieval; Artificial intelligence; Mathematics; Knowledge base; Management","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":[0.01542784,0.002491388,0.001489622,0.01288129,0.002423399,0.00477343,0.003107559,0.002643082,0.01248734],"category_scores_gemma":[0.05501535,0.0007666594,0.001091839,0.02582224,0.0009521564,0.004445591,0.004813166,0.002297934,0.02565238],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003322671,"about_ca_system_score_gemma":0.006172992,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02545273,"about_ca_topic_score_gemma":0.03063249,"domain_scores_codex":[0.9778105,0.005481333,0.001946468,0.002677658,0.01062572,0.001458241],"domain_scores_gemma":[0.9516458,0.0103848,0.00316922,0.01057002,0.0203984,0.003831785],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0002115803,0.0002439398,0.002174502,0.0005644886,0.0001148134,0.0001088534,0.0001158383,0.004120585,0.0006823919,0.004548035,0.9259407,0.06117438],"study_design_scores_gemma":[0.0005310004,0.0002876265,0.02473056,0.000355901,0.0001398955,0.0005796518,0.0005014648,0.03721898,0.01301782,0.02635459,0.8961053,0.0001771723],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.061802,0.02247549,0.05504611,0.01498901,0.002958704,0.0009652324,0.5918558,0.07710902,0.1727987],"genre_scores_gemma":[0.07064866,0.001937998,0.05940076,0.001044805,0.0003692947,0.0006484881,0.8439688,0.005955915,0.01602526],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02545273,"threshold_uncertainty_score":0.08159119,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.03887689956804048,"score_gpt":0.3441753447018895,"score_spread":0.305298445133849,"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."}}