{"id":"W2188957661","doi":"","title":"Linguistic Resources for 2011 Knowledge Base Population Evaluation.","year":2011,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Data Quality and Management","field":"Decision Sciences","cited_by":7,"is_retracted":false,"has_abstract":true,"ca_institutions":"","funders":"","keywords":"NIST; Computer science; Annotation; Knowledge base; Information extraction; Entity linking; Resource (disambiguation); Population; Information retrieval; Natural language processing; Artificial intelligence; Data science; World Wide Web","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":[0.0436629,0.001348568,0.001260466,0.01211283,0.004366966,0.007929853,0.004076935,0.002331771,0.0410835],"category_scores_gemma":[0.1101181,0.0009405939,0.001039794,0.0103016,0.001025094,0.007169896,0.006593428,0.0023582,0.02636562],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.007483495,"about_ca_system_score_gemma":0.02239804,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.03030334,"about_ca_topic_score_gemma":0.02965655,"domain_scores_codex":[0.9560475,0.01789091,0.004134378,0.001815497,0.01896383,0.00114787],"domain_scores_gemma":[0.9141062,0.02056509,0.003162211,0.01062274,0.04858893,0.002954813],"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":[0.0007466685,0.0007211486,0.003319688,0.001542495,0.00009866398,0.0003004343,0.001648166,0.006040591,0.004496214,0.03620684,0.4621817,0.4826974],"study_design_scores_gemma":[0.0002887481,0.0002527538,0.006165475,0.001479245,0.0001615221,0.000322426,0.001718158,0.02098911,0.01697135,0.02203791,0.9293756,0.0002377404],"study_design_candidate":"not_applicable","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.03476488,0.003466616,0.3506032,0.01432841,0.002230749,0.01499038,0.2035677,0.03479347,0.3412546],"genre_scores_gemma":[0.07393109,0.001244643,0.5885644,0.001552768,0.0002683686,0.01254396,0.2623339,0.005181313,0.05437948],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.0436629,"threshold_uncertainty_score":0.2309142,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1597058808970285,"score_gpt":0.4099887425248145,"score_spread":0.250282861627786,"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."}}