{"id":"W3176031132","doi":"","title":"WaterlooClarke at the Trec 2020 Conversational Assistant Track.","year":2020,"lang":"en","type":"article","venue":"Text REtrieval Conference","topic":"Natural Language Processing Techniques","field":"Computer Science","cited_by":0,"is_retracted":false,"has_abstract":false,"ca_institutions":"University of Waterloo; Toronto Metropolitan University","funders":"","keywords":"Computer science; Track (disk drive); Natural language processing; Information retrieval; Artificial intelligence; World Wide Web; 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":[],"consensus_categories":[],"category_scores_codex":[0.0003396251,0.0002015264,0.0001984815,0.00002745365,0.0002353395,0.0003616718,0.001606771,0.0001044876,0.0006326144],"category_scores_gemma":[0.0003214529,0.0001317534,0.00008222913,0.0005286945,0.0001724955,0.0004389538,0.0005301621,0.000373385,0.0002656237],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009666692,"about_ca_system_score_gemma":0.0002242679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001890748,"about_ca_topic_score_gemma":0.00001059413,"domain_scores_codex":[0.9981703,0.0001224674,0.0002754725,0.0005437655,0.0005849024,0.0003031028],"domain_scores_gemma":[0.9988093,0.0001829272,0.0001447742,0.0004698621,0.0002293521,0.0001638175],"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":[0.001098517,0.0001767809,0.002135748,0.000292083,0.0001985339,0.0005841198,0.02465628,0.00001329413,0.2811158,0.4125749,0.08646134,0.1906927],"study_design_scores_gemma":[0.001916329,0.0008737104,0.004012567,0.0001664882,0.00008076974,0.000223779,0.0003119119,0.09378064,0.7347364,0.05226417,0.109754,0.001879235],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.07645247,0.0046914,0.7492498,0.157557,0.000704942,0.001058019,0.00007613689,0.003019702,0.007190541],"genre_scores_gemma":[0.9734399,0.00002831091,0.02202192,0.003070656,0.0001034808,0.000005840418,0.00001371596,0.00001132783,0.00130479],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.8969875,"threshold_uncertainty_score":0.6926684,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02848932088982083,"score_gpt":0.2593781473952529,"score_spread":0.2308888265054321,"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."}}