{"id":"W6910509767","doi":"10.48448/cg6v-4y14","title":"Explain by Evidence: An Explainable Memory-based Neural Network for Question Answering","year":2020,"lang":"en","type":"other","venue":"Underline Science Inc.","topic":"","field":"","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Waterloo","funders":"","keywords":"Interpretability; Question answering; TRACE (psycholinguistics); Artificial neural network; Process (computing); Quality (philosophy); Generalization; Deep neural networks","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":[0.0006337352,0.0007720367,0.0004284951,0.000621487,0.0002876988,0.000866835,0.001786436,0.001353821,0.003668913],"category_scores_gemma":[0.003371754,0.0003161959,0.0006571687,0.000561331,0.0005663192,0.001982367,0.001208128,0.00164711,0.0007038416],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0007631454,"about_ca_system_score_gemma":0.0008093721,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.007516684,"about_ca_topic_score_gemma":0.01519625,"domain_scores_codex":[0.9998116,0.00004239835,0.0000108508,0.00007827548,0.00003348604,0.00002341107],"domain_scores_gemma":[0.9993199,0.0003255953,0.00008540611,0.0001557784,0.00007997081,0.00003333183],"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":[0.0005051728,0.0002818769,0.006182383,0.0002908898,0.0002861987,0.0003130623,0.0003739065,0.2603968,0.009153481,0.02843985,0.01627552,0.6775008],"study_design_scores_gemma":[0.00001750355,0.00004841812,0.0007425262,0.0000330913,0.00005646552,0.00004665984,0.00002174894,0.9644212,0.002333551,0.02954356,0.002719105,0.00001624601],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.1129764,0.003779008,0.8595895,0.004224455,0.0002964185,0.0001799224,0.002641909,0.007861814,0.008450486],"genre_scores_gemma":[0.8058134,0.0009550356,0.1798356,0.0009348823,0.0001239809,0.0001813592,0.002884102,0.0001958744,0.009075706],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.007516684,"threshold_uncertainty_score":0.01494586,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04717623683347327,"score_gpt":0.3336192800388499,"score_spread":0.2864430432053766,"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."}}