{"id":"W4406160197","doi":"10.1186/s13040-024-00412-x","title":"The Venus score for the assessment of the quality and trustworthiness of biomedical datasets","year":2025,"lang":"en","type":"article","venue":"BioData Mining","topic":"Artificial Intelligence in Healthcare and Education","field":"Medicine","cited_by":10,"is_retracted":false,"has_abstract":true,"ca_institutions":"University of Toronto","funders":"HORIZON EUROPE European Research Council; Ministero dell'Università e della Ricerca; HORIZON EUROPE Framework Programme; Dipartimenti di Eccellenza; European Commission; Alexander von Humboldt-Stiftung","keywords":"Computer science; Quality (philosophy); Informatics; Usability; Data science; Data quality; Data mining; Artificial intelligence","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":[],"consensus_categories":[],"category_scores_codex":[0.001191684,0.00004611109,0.0001147635,0.00002010565,0.0002203221,0.00001032641,0.000181477,0.00004011493,0.000004436397],"category_scores_gemma":[0.001115358,0.00002072986,0.00002908295,0.0001756361,0.0002993085,0.00002573567,0.00008645692,0.00007845483,1.326111e-7],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00001573843,"about_ca_system_score_gemma":0.0003254679,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0003931977,"about_ca_topic_score_gemma":0.00009772377,"domain_scores_codex":[0.9992637,0.00005383006,0.0003370503,0.0001059812,0.000143546,0.00009590737],"domain_scores_gemma":[0.9979889,0.001313363,0.0001375344,0.0004579192,0.00007850109,0.00002381322],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"observational","study_design_scores_codex":[0.0001458802,0.0001275535,0.2834719,0.0006322511,0.0001035494,3.415571e-7,0.001290315,0.00000117467,0.001400459,0.00555711,0.02157002,0.6856995],"study_design_scores_gemma":[0.0001999757,0.0001729923,0.8663014,0.0007483834,0.0002326292,0.000005107978,0.01100365,0.003057357,0.007029041,0.0008682584,0.1102996,0.00008162911],"study_design_candidate":"observational","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9646404,0.001511877,0.001897226,0.02948074,0.001184713,0.0006843893,0.0005241935,0.000006000145,0.00007047819],"genre_scores_gemma":[0.9988261,0.000126402,0.0004429555,0.0003079801,0.00009192425,0.00002856732,0.0001390496,0.000002623609,0.00003436738],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.6856179,"threshold_uncertainty_score":0.1694561,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.3350027862965513,"score_gpt":0.5494247029763654,"score_spread":0.214421916679814,"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."}}