{"id":"W2807441601","doi":"","title":"Overview of Linguistic Resources for the TAC KBP 2015 Evaluations: Methodologies and Results.","year":2015,"lang":"en","type":"article","venue":"Theory and applications of categories","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":48,"is_retracted":false,"has_abstract":false,"ca_institutions":"","funders":"","keywords":"Computer science; Linguistics; Natural language processing; 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":[0.003186126,0.00006718492,0.0001341967,0.00004804275,0.0001097769,0.00003963986,0.0004242481,0.00003523933,3.781615e-7],"category_scores_gemma":[0.002618525,0.00004263598,0.00001855649,0.0001953773,0.0003772283,0.0001038793,0.0001604566,0.00004833289,1.7764e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000004577609,"about_ca_system_score_gemma":0.00004697259,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001839102,"about_ca_topic_score_gemma":0.000002134897,"domain_scores_codex":[0.9992948,0.0001509809,0.0002326545,0.0001485149,0.0001050991,0.0000679786],"domain_scores_gemma":[0.9964221,0.002601381,0.0002071844,0.0003835037,0.0003621748,0.00002368932],"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":[0.00003977304,0.000006806415,0.000004251195,0.00005866864,0.000009424331,2.050682e-8,0.002695046,0.000002878943,0.00020252,0.9285728,0.000189256,0.06821857],"study_design_scores_gemma":[0.000124538,0.00006271082,0.00003401119,0.00001730606,0.00003284262,0.00000249501,0.0006530017,0.0002265164,0.01036862,0.9810881,0.007337791,0.00005205518],"study_design_candidate":"theoretical_or_conceptual","study_design_consensus":"theoretical_or_conceptual","genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0004991512,0.07320347,0.9248008,0.000778708,0.00002041517,0.0003722958,0.00001846316,0.00007620857,0.0002305594],"genre_scores_gemma":[0.4761576,0.0007127702,0.5225286,0.00006353795,0.00005388173,0.0002951375,0.000004750516,0.000005565593,0.0001781811],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.4756584,"threshold_uncertainty_score":0.3134808,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1006083672297149,"score_gpt":0.4152044565674748,"score_spread":0.31459608933776,"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."}}