{"id":"W4293056786","doi":"10.21203/rs.3.rs-1668271/v3","title":"Evaluating the harmonisation potential of diverse cohort datasets","year":2022,"lang":"en","type":"preprint","venue":"Research Square","topic":"Health, Environment, Cognitive Aging","field":"Environmental Science","cited_by":1,"is_retracted":false,"has_abstract":false,"ca_institutions":"Institute of Aging","funders":"Economic and Social Research Council; Medical Research Council; Dementias Platform UK; National Institute of Neurological Disorders and Stroke; National Institute for Health and Care Research; UK Research and Innovation; University of East Anglia; Institut National de la Santé et de la Recherche Médicale; Government of the United Kingdom; National Institute on Aging; University of Manchester; Wellcome Trust; McGill University; Scottish Government; University College London; Scottish Funding Council; National Institutes of Health; U.S. Department of Health and Human Services","keywords":"Comparability; Computer science; Rigour; Data mining; Granularity; Data science; Mathematics","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":["open_science","insufficient_payload"],"consensus_categories":[],"category_scores_codex":[0.0124581,0.0002000228,0.0002309654,0.0001160531,0.0009822526,0.0000704392,0.001059787,0.0001297139,0.01922062],"category_scores_gemma":[0.0009388734,0.0001710895,0.0001107351,0.0003367119,0.0006687418,0.000147515,0.008793133,0.002087274,0.0004596106],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001215488,"about_ca_system_score_gemma":0.0001745314,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005055883,"about_ca_topic_score_gemma":0.00007650715,"domain_scores_codex":[0.991115,0.002991131,0.0004168324,0.00099721,0.003838157,0.0006416702],"domain_scores_gemma":[0.997679,0.0005197499,0.0002470056,0.001366286,0.00003350148,0.0001544745],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.0003661693,0.0009288366,0.52477,0.001191354,0.0002775346,0.0002020037,0.006208286,0.2213656,0.02871402,0.0001192644,0.02093958,0.1949173],"study_design_scores_gemma":[0.0004530669,0.0003760711,0.9541047,0.0001490188,0.00007415054,0.000004794622,0.003399798,0.0316176,0.0007970361,0.001478352,0.007197673,0.0003477184],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9908057,0.0001101293,0.0003704816,0.0009117561,0.0001971797,0.002969903,0.001392194,0.00002647115,0.003216161],"genre_scores_gemma":[0.9967055,0.0003408591,0.0004976189,0.00008601018,0.00009246675,0.000483817,0.001488113,0.00003401727,0.0002716037],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.4293347,"threshold_uncertainty_score":0.9992236,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.1816193945383935,"score_gpt":0.4726507712147601,"score_spread":0.2910313766763667,"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."}}