{"id":"W4292940196","doi":"10.21203/rs.3.rs-1871614/v1","title":"SARS-CoV-2 Genomic Contextual Data Harmonization: Recommendations from a Mixed Methods Analysis of COVID-19 Case Report Forms Across Canada","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Data-Driven Disease Surveillance","field":"Medicine","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Simon Fraser University; University of British Columbia","funders":"Genome British Columbia; Genome Canada","keywords":"Harmonization; Pandemic; Identification (biology); Data sharing; Data science; Standardization; Data integration; Data collection; Public health; Coronavirus disease 2019 (COVID-19); Computer science; Data mining; Medicine; Infectious disease (medical specialty); Disease; Biology; Pathology; Sociology","routes":{"ca_aff":true,"ca_fund":true,"ca_venue":false,"about_ca":true,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","metaepi_narrow","open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.008887329,0.0004116961,0.00161874,0.0006351389,0.0006608569,0.0001413668,0.001635372,0.0002426164,0.003219939],"category_scores_gemma":[0.01469069,0.0004172613,0.0003538135,0.002777618,0.0003241975,0.0001645134,0.009009435,0.001793804,0.000008036088],"about_ca_system_candidate":true,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00330092,"about_ca_system_score_gemma":0.01434612,"about_ca_topic_candidate":true,"about_ca_topic_consensus":true,"about_ca_topic_score_codex":0.8539906,"about_ca_topic_score_gemma":0.9002571,"domain_scores_codex":[0.9908357,0.002855109,0.001557437,0.001960367,0.00196875,0.0008226854],"domain_scores_gemma":[0.9872313,0.002770333,0.0008232611,0.007078081,0.001394581,0.0007024077],"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":[0.00203556,0.001416279,0.1104736,0.004393297,0.03113412,0.2131862,0.004942104,0.003374434,0.003094028,0.0001102707,0.5836878,0.0421523],"study_design_scores_gemma":[0.003990887,0.0002393616,0.0534679,0.0003866141,0.004640704,0.00259359,0.02967163,0.05146882,0.001481207,0.0003261901,0.8502983,0.001434836],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6137575,0.002050386,0.02089458,0.005953661,0.0006131497,0.002777453,0.3534772,0.0001317258,0.0003442959],"genre_scores_gemma":[0.625557,0.0003435701,0.01207108,0.0005297801,0.00016814,0.0004462372,0.3603949,0.00009813599,0.000391121],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2666104,"threshold_uncertainty_score":0.9998279,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2568860167304794,"score_gpt":0.5453981565113779,"score_spread":0.2885121397808985,"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."}}