{"id":"W3175609992","doi":"10.21428/594757db.ae6ae665","title":"Direct Answer Threshold Optimization in Dialogue Systems","year":2021,"lang":"en","type":"article","venue":"","topic":"Speech and dialogue systems","field":"Computer Science","cited_by":1,"is_retracted":false,"has_abstract":true,"ca_institutions":"National Bank of Canada","funders":"","keywords":"Computer science; Set (abstract data type); Point (geometry); Focus (optics); Task (project management); Information retrieval; Machine learning; Artificial intelligence; Mathematics","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":"metacan-v3-hybrid-931329e0061c","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.00442564,0.001614747,0.002562757,0.002400151,0.0009060666,0.002375086,0.001747337,0.002343828,0.002935225],"category_scores_gemma":[0.02006596,0.0006733416,0.0009792504,0.001248846,0.00114682,0.002432548,0.002081095,0.002211129,0.00118183],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00138077,"about_ca_system_score_gemma":0.001835143,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004319866,"about_ca_topic_score_gemma":0.003753061,"domain_scores_codex":[0.9943655,0.002012064,0.000515983,0.001353111,0.001275652,0.0004777357],"domain_scores_gemma":[0.9886805,0.008531219,0.0006169448,0.0004664847,0.00133279,0.000372007],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.001126714,0.0005006907,0.005737653,0.000873489,0.000164789,0.0002621807,0.0008760409,0.3751323,0.02242192,0.01139371,0.01080791,0.5707027],"study_design_scores_gemma":[0.00004036268,0.00009959457,0.0007159951,0.00002839035,0.00002336213,0.00006849267,0.000090755,0.9835265,0.004220878,0.00969884,0.001463359,0.00002343647],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.04933799,0.00261888,0.9394589,0.0005709131,0.0001022681,0.0001966074,0.0004268471,0.005138027,0.002149677],"genre_scores_gemma":[0.6453132,0.0004250582,0.3476579,0.0004517522,0.0002089248,0.0003577694,0.001502562,0.0006053937,0.003477447],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.00442564,"threshold_uncertainty_score":0.02340531,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.01697210482856354,"score_gpt":0.2254107716638141,"score_spread":0.2084386668352506,"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."}}