{"id":"W3157747653","doi":"","title":"A Baseline Fine-Grained Entity Extraction System for TAC-KBP2019.","year":2019,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Baseline (sea); Computer science; Extraction (chemistry); Information retrieval; Chemistry; Chromatography; Geology","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":[0.001890381,0.001702591,0.001489962,0.005411849,0.001732511,0.002494272,0.002773303,0.002340976,0.01868094],"category_scores_gemma":[0.00809327,0.0008787706,0.001004832,0.005785867,0.0004868537,0.005860289,0.002508771,0.00170786,0.02879137],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001043247,"about_ca_system_score_gemma":0.003414278,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02570707,"about_ca_topic_score_gemma":0.03146778,"domain_scores_codex":[0.9980797,0.0002412745,0.0002877254,0.0006680141,0.0005420022,0.0001813967],"domain_scores_gemma":[0.9957513,0.0007430034,0.0001946825,0.001488333,0.001613158,0.0002095468],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0009499243,0.0005387408,0.003159534,0.001990937,0.0003864546,0.0009004473,0.000365132,0.003908102,0.04863082,0.005145358,0.5850356,0.348989],"study_design_scores_gemma":[0.0004925534,0.0004688428,0.02021985,0.0005003847,0.0005435125,0.002390954,0.000967146,0.149334,0.07065576,0.01703699,0.7371008,0.0002891514],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.04304145,0.00506419,0.282708,0.001884932,0.001336587,0.002208027,0.3701208,0.2602725,0.03336344],"genre_scores_gemma":[0.05688725,0.0006447723,0.2658995,0.0005030723,0.0001116633,0.0006379989,0.6600444,0.002786625,0.01248466],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02570707,"threshold_uncertainty_score":0.06249392,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.006244639929203409,"score_gpt":0.2644843899912733,"score_spread":0.2582397500620698,"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."}}