{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.002392531,0.00006790884,0.0001377124,0.00003609639,0.000528046,0.0001106343,0.0008318693,0.00003641844,5.080399e-7],"category_scores_gemma":[0.003304768,0.0000433698,0.00002379749,0.00005683117,0.0006624168,0.0001513831,0.0002578648,0.00005116888,1.385464e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00000258932,"about_ca_system_score_gemma":0.00002581094,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00002539556,"about_ca_topic_score_gemma":0.000003512219,"domain_scores_codex":[0.9993861,0.00009260669,0.0002098413,0.0001612807,0.0000811861,0.00006901207],"domain_scores_gemma":[0.9961319,0.002456547,0.0003890479,0.0007857406,0.0002224515,0.00001429209],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"theoretical_or_conceptual","study_design_scores_codex":[0.00002653988,0.000005008718,0.000007874874,0.00007706674,0.00001026674,2.80101e-8,0.001176876,5.622273e-7,0.0004407597,0.879262,0.0000507908,0.1189423],"study_design_scores_gemma":[0.0001004071,0.00003723402,0.0004013983,0.00002807205,0.00003585487,0.000002147224,0.0001913141,0.0001497321,0.01539158,0.9798995,0.003709722,0.00005309712],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.0009275092,0.04133109,0.9557145,0.0009604141,0.00002646288,0.0004368201,0.00002742028,0.00006249527,0.0005132608],"genre_scores_gemma":[0.691043,0.00134499,0.3071107,0.00003217273,0.00004641935,0.0002302007,0.000002231289,0.000004037197,0.0001863517],"genre_candidate":"methods","genre_consensus":null,"teacher_disagreement_score":0.6901155,"threshold_uncertainty_score":0.4061356,"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."}}