{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.007207085,0.0001143785,0.0001355288,0.000228085,0.0009978873,0.0003433583,0.0006804579,0.00003841246,0.000009018647],"category_scores_gemma":[0.002538565,0.0001200249,0.00002048652,0.000436672,0.00005817269,0.001386086,0.001490717,0.0003774777,0.0000165446],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0003826328,"about_ca_system_score_gemma":0.0003470862,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003776847,"about_ca_topic_score_gemma":0.00002531294,"domain_scores_codex":[0.9974675,0.0006245322,0.0004719911,0.0002546295,0.0008273631,0.0003539795],"domain_scores_gemma":[0.9970567,0.001767994,0.0002096693,0.0006774558,0.00008764365,0.0002005982],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"theoretical_or_conceptual","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001339506,0.0001732022,0.001909483,0.007774338,0.00007891807,0.0001411908,0.1039516,0.2853598,0.00008095319,0.4546516,0.05503751,0.09070744],"study_design_scores_gemma":[0.0002170966,0.00008589749,0.00001716233,0.00002871628,0.000004489938,0.0002949362,0.01427382,0.91088,0.000001772224,0.0001662018,0.07390195,0.0001278991],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.0009476531,0.0001646384,0.9963729,0.0004124888,0.0002482886,0.0003433049,0.0001969471,0.000174692,0.001139084],"genre_scores_gemma":[0.02349941,0.00001619151,0.9754121,0.0007105208,0.00005133342,0.00007148561,0.0002065643,0.000007199248,0.00002517014],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.6255202,"threshold_uncertainty_score":0.7675044,"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."}}