{"id":"W3013646476","doi":"","title":"WaterlooClarke at the TREC 2019 Conversational Assistant Track.","year":2019,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":7,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo","funders":"","keywords":"Computer science; Track (disk drive); Artificial intelligence; Natural language processing; World Wide Web; Multimedia; Operating system","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":["insufficient_payload"],"category_scores_codex":[0.0005942879,0.0002038469,0.0002045284,0.00007034636,0.0001705446,0.0003480388,0.001588475,0.0001269182,0.001066134],"category_scores_gemma":[0.000105695,0.0001292948,0.00008369771,0.0003747712,0.0001329897,0.0005487673,0.0004663368,0.000340288,0.001012359],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001566166,"about_ca_system_score_gemma":0.0002361978,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005056483,"about_ca_topic_score_gemma":0.0000159351,"domain_scores_codex":[0.9981271,0.0001159956,0.0002640739,0.0005277212,0.0006180558,0.0003470314],"domain_scores_gemma":[0.9984084,0.0002396548,0.0001603895,0.0008455554,0.0002632367,0.00008279458],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.000542384,0.0001768826,0.00607563,0.0001639561,0.0001325073,0.00009404372,0.005848021,0.000009616446,0.2294655,0.6223268,0.03023195,0.1049328],"study_design_scores_gemma":[0.002677105,0.0008625705,0.01867818,0.0003647645,0.00006950647,0.0003344819,0.0002235381,0.03827024,0.7318508,0.1070977,0.09723498,0.002336183],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6724924,0.006636634,0.2653591,0.02354282,0.002543878,0.002168749,0.00009349308,0.002989321,0.0241736],"genre_scores_gemma":[0.9658635,0.00002359162,0.0134878,0.0006280161,0.00004147689,0.000004732053,0.00001722283,0.00001169704,0.01992199],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5152291,"threshold_uncertainty_score":0.9998471,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01528003651922833,"score_gpt":0.2526781807060182,"score_spread":0.2373981441867898,"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."}}