{"id":"W2576107865","doi":"","title":"WaterlooClarke: TREC 2015 LiveQA Track","year":2015,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Expert finding and Q&A systems","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Question answering; Computer science; NIST; Track (disk drive); Task (project management); Questions and answers; Information retrieval; World Wide Web; Natural language processing; Artificial intelligence","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0009642526,0.0002629746,0.0003445182,0.0001321171,0.0001183468,0.0004585874,0.001491978,0.0001789553,0.00007235672],"category_scores_gemma":[0.0002396754,0.0002164383,0.00008826743,0.0005092427,0.00009630847,0.0006323537,0.0002605269,0.0002909956,0.001571012],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000108742,"about_ca_system_score_gemma":0.0004197662,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0002099641,"about_ca_topic_score_gemma":0.000025866,"domain_scores_codex":[0.997572,0.0002054823,0.0003830396,0.0006271611,0.0006806047,0.0005317181],"domain_scores_gemma":[0.9979772,0.0001030674,0.0001384525,0.0009258086,0.0004092084,0.0004462752],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.0007172155,0.001063634,0.01095162,0.0002583996,0.0003032281,0.0008573324,0.1039513,0.00009077547,0.03420467,0.3353814,0.3728289,0.1393915],"study_design_scores_gemma":[0.00833809,0.00399003,0.007896209,0.0008093908,0.00008043162,0.001029466,0.003323647,0.1436398,0.1340751,0.02533995,0.6665015,0.00497641],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5073421,0.003147336,0.3238462,0.009884744,0.007761229,0.00124671,0.0000289307,0.00294714,0.1437955],"genre_scores_gemma":[0.9833311,0.0000223231,0.002705927,0.0001977614,0.0002060854,0.000006670024,0.000005634276,0.00001619914,0.0135083],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.475989,"threshold_uncertainty_score":0.9992064,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.07404688050771699,"score_gpt":0.2936623825454258,"score_spread":0.2196155020377088,"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."}}