{"id":"W4283583762","doi":"10.20944/preprints202206.0335.v1","title":"The Dataharmonizer: a Tool for Faster Data Harmonization, Validation, Aggregation, and Analysis of Pathogen Genomics Contextual Information","year":2022,"lang":"en","type":"preprint","venue":"Preprints.org","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":8,"is_retracted":false,"has_abstract":true,"ca_institutions":"St. John’s Health Sciences Centre; BC Centre for Disease Control; McMaster University; Ottawa Public Health; Nova Scotia Health Authority; Simon Fraser University; Public Health Agency of Canada; Hospital for Sick Children; University of British Columbia; Public Health Ontario; University of Alberta; Saskatchewan Disease Control Laboratory; Institut National de Santé Publique du Québec","funders":"","keywords":"Metadata; Data sharing; Data science; Harmonization; Computer science; Interoperability; Big data; Data integration; Contextual design; World Wide Web; Database; Data mining; Medicine","routes":{"ca_aff":true,"ca_fund":false,"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","open_science"],"consensus_categories":[],"category_scores_codex":[0.01791405,0.0002501606,0.0005144617,0.000761872,0.0007508756,0.0008819547,0.00464426,0.00009858038,0.0006057161],"category_scores_gemma":[0.00996612,0.0001976814,0.0001718166,0.00147989,0.0001818052,0.001012354,0.01613287,0.0002506654,0.00009772542],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00009290669,"about_ca_system_score_gemma":0.0002580812,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00005818117,"about_ca_topic_score_gemma":0.00001793509,"domain_scores_codex":[0.9943677,0.0004335183,0.002008016,0.001419679,0.001509469,0.0002616835],"domain_scores_gemma":[0.9882182,0.001797173,0.001949359,0.006690564,0.001265773,0.00007891723],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00020529,0.0001310415,0.7900175,0.0001288059,0.002316218,9.230242e-7,0.006605393,0.04065656,0.0001983996,0.003205011,0.02308985,0.133445],"study_design_scores_gemma":[0.0005203844,0.00001475193,0.2880351,0.00001999734,0.001142777,0.000001142821,0.002193507,0.2688693,0.0003769577,0.005026603,0.4334037,0.0003958408],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.6756107,0.0001987752,0.3060548,0.001351532,0.001589138,0.002068037,0.01265754,0.00006688371,0.0004026796],"genre_scores_gemma":[0.9649276,0.0002811489,0.003434041,0.0002701847,0.0001016141,0.0002455828,0.02904831,0.00002305073,0.001668527],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5019825,"threshold_uncertainty_score":0.9983733,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.321146004430793,"score_gpt":0.4154555473716058,"score_spread":0.09430954294081278,"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."}}