{"id":"W6958884918","doi":"10.6084/m9.figshare.c.6028481.v1","title":"CoQUAD: a COVID-19 question answering dataset system, facilitating research, benchmarking, and practice","year":2022,"lang":"en","type":"other","venue":"Figshare","topic":"Plant pathogens and resistance mechanisms","field":"Agricultural and Biological Sciences","cited_by":0,"is_retracted":false,"has_abstract":true,"ca_institutions":"Institute for Clinical Evaluative Sciences; Trillium Health Centre; Public Health Ontario; University of Toronto","funders":"","keywords":"Question answering; Component (thermodynamics); Natural language; Questions and answers; Natural (archaeology); Variety (cybernetics)","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":[0.009316402,0.002556749,0.001179972,0.007541203,0.001642856,0.003026268,0.004997552,0.003477737,0.01187854],"category_scores_gemma":[0.02657432,0.0005786595,0.001613989,0.004892191,0.0008928214,0.005506049,0.005593375,0.002584859,0.01017459],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.002892569,"about_ca_system_score_gemma":0.003634805,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.01506665,"about_ca_topic_score_gemma":0.02053303,"domain_scores_codex":[0.9916068,0.002679536,0.001345988,0.002004807,0.001946157,0.0004166032],"domain_scores_gemma":[0.9882995,0.004203502,0.0009234696,0.002784467,0.002917412,0.0008716618],"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":[0.001433705,0.001004588,0.009999909,0.003809256,0.0002742559,0.0004824923,0.0009217889,0.005585936,0.01151344,0.007597264,0.7892179,0.1681594],"study_design_scores_gemma":[0.001332821,0.001111012,0.0255498,0.0007580672,0.0002261392,0.0008488636,0.001540203,0.1413244,0.03276855,0.01618067,0.7779314,0.0004281059],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"software","genre_scores_codex":[0.05681445,0.006944065,0.1032912,0.005414532,0.001321194,0.005882814,0.6274533,0.1693365,0.02354197],"genre_scores_gemma":[0.04256694,0.0005859017,0.1329805,0.001409244,0.0001881637,0.002888385,0.813782,0.001803788,0.003795126],"genre_candidate":"software","genre_consensus":null,"teacher_disagreement_score":0.01506665,"threshold_uncertainty_score":0.04927039,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1213818863534584,"score_gpt":0.3469148522142255,"score_spread":0.2255329658607671,"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."}}