{"id":"W4321748937","doi":"10.1093/jamia/ocad009","title":"Reproducible variability: assessing investigator discordance across 9 research teams attempting to reproduce the same observational study","year":2023,"lang":"en","type":"article","venue":"Journal of the American Medical Informatics Association","topic":"Meta-analysis and systematic reviews","field":"Decision Sciences","cited_by":12,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Calgary","funders":"Alnylam Pharmaceuticals; AstraZeneca","keywords":"Observational study; Interquartile range; Cohort; Cohort study; Computer science; Inclusion (mineral); Variable (mathematics); Baseline (sea); Medicine; Implementation; Psychology; Statistics; Mathematics; Surgery; Pathology","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":"codex-gemma-dda1882f352a","candidate_categories":["metaresearch","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.6351774,0.0001877579,0.001860474,0.0002832738,0.0009262203,0.00186444,0.003923033,0.00005876593,0.0001341822],"category_scores_gemma":[0.7880476,0.00007316605,0.0007350433,0.009457461,0.0002467043,0.0008047941,0.0009331034,0.001182527,0.0004021735],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0005630727,"about_ca_system_score_gemma":0.001057263,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00006843477,"about_ca_topic_score_gemma":0.00003304377,"domain_scores_codex":[0.9155634,0.030366,0.01657745,0.0006676746,0.03602871,0.0007967555],"domain_scores_gemma":[0.8594069,0.06816155,0.04887883,0.009457326,0.01301925,0.001076111],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"observational","study_design_gemma":"observational","study_design_scores_codex":[0.000006707122,0.00008429438,0.8097333,0.00001817444,0.0002116288,0.000001877718,0.01238759,0.00113679,0.00006355341,0.00008228608,0.1606709,0.01560297],"study_design_scores_gemma":[0.0002110436,0.0001530945,0.8824299,0.0001631129,0.0001004809,0.00001453932,0.07295793,0.02152448,0.00003168306,0.005020039,0.01724481,0.0001489008],"study_design_candidate":"observational","study_design_consensus":"observational","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9267662,0.00001035602,0.001980635,0.06964254,0.0006800764,0.0006862355,0.000005539525,0.000006702383,0.0002216696],"genre_scores_gemma":[0.9880404,0.00001085969,0.003800809,0.004507501,0.0007230356,0.00003262359,0.000001742929,0.00001339511,0.00286964],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1528702,"threshold_uncertainty_score":0.9991717,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.7985450138999625,"score_gpt":0.6273149303618455,"score_spread":0.171230083538117,"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."}}