{"id":"W2917198466","doi":"","title":"Overview of Linguistic Resources for the TAC KBP 2017 Evaluations: Methodologies and Results.","year":2017,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":28,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Natural language processing; Linguistics; Artificial intelligence; Philosophy","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":[0.01948491,0.002272131,0.001777961,0.01453921,0.003103657,0.005169583,0.004499431,0.002074613,0.02063076],"category_scores_gemma":[0.06674006,0.0009044532,0.001260413,0.009711851,0.001304751,0.007916971,0.006574382,0.002987369,0.01717913],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002873591,"about_ca_system_score_gemma":0.00916582,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.02253355,"about_ca_topic_score_gemma":0.02702193,"domain_scores_codex":[0.9755078,0.01120493,0.002725906,0.00169753,0.007914618,0.0009490895],"domain_scores_gemma":[0.9414638,0.02178839,0.001847477,0.006723507,0.0254965,0.002680463],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.003752984,0.003102959,0.009488537,0.01630199,0.0009077265,0.0007354934,0.003590522,0.01100499,0.0124085,0.008756733,0.3627498,0.5671999],"study_design_scores_gemma":[0.002046845,0.001978291,0.02499066,0.007276762,0.002000799,0.001356833,0.00777691,0.04396117,0.04486612,0.01458952,0.8484793,0.0006766998],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"dataset","genre_gemma":"empirical","genre_scores_codex":[0.1867094,0.03809331,0.1735306,0.006335504,0.002043497,0.02371073,0.3616185,0.04085147,0.167107],"genre_scores_gemma":[0.182567,0.006782835,0.2534846,0.001117086,0.0003805197,0.02071271,0.5110499,0.004243813,0.01966144],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.02253355,"threshold_uncertainty_score":0.1030474,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.0975557432067578,"score_gpt":0.4224822658712334,"score_spread":0.3249265226644756,"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."}}