{"id":"W4281817583","doi":"10.1186/s12859-022-04751-6","title":"CoQUAD: a COVID-19 question answering dataset system, facilitating research, benchmarking, and practice","year":2022,"lang":"en","type":"article","venue":"BMC Bioinformatics","topic":"Topic Modeling","field":"Computer Science","cited_by":34,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto; Public Health Ontario","funders":"Institute of Health Services and Policy Research; Canadian Institutes of Health Research","keywords":"Benchmarking; Coronavirus disease 2019 (COVID-19); 2019-20 coronavirus outbreak; Data science; Severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2); Computer science; Computational biology; Information retrieval; Biology; Virology; Medicine; Business","routes":{"ca_aff":true,"ca_fund":true,"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":[0.008619918,0.002912077,0.001249274,0.008067946,0.001697674,0.002815226,0.004725655,0.003753671,0.01323655],"category_scores_gemma":[0.02595321,0.0005920781,0.001779287,0.004995091,0.0009141659,0.005598519,0.006058862,0.002814153,0.01180475],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.003043669,"about_ca_system_score_gemma":0.004086695,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0153892,"about_ca_topic_score_gemma":0.02231098,"domain_scores_codex":[0.9919307,0.002532318,0.001347038,0.001834161,0.001951665,0.0004041399],"domain_scores_gemma":[0.9882428,0.004201639,0.001115874,0.002614662,0.002888116,0.0009368641],"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":[0.001213912,0.0008148309,0.008541645,0.004273827,0.0002642634,0.0004569204,0.0009345002,0.003636982,0.009874526,0.006015397,0.8282717,0.1357017],"study_design_scores_gemma":[0.001240972,0.001012741,0.02486654,0.0008387875,0.000208475,0.0008827318,0.001520735,0.08225365,0.02562059,0.01406787,0.8470841,0.0004028225],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.03507074,0.005731333,0.0684531,0.004244152,0.001110489,0.005236099,0.7471319,0.1150175,0.01800472],"genre_scores_gemma":[0.02355969,0.0004982368,0.09231154,0.001161105,0.0001624036,0.002708752,0.8754614,0.001156735,0.002980227],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.0153892,"threshold_uncertainty_score":0.04558706,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1278480297286422,"score_gpt":0.3884872227123956,"score_spread":0.2606391929837534,"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."}}