{"id":"W4408224138","doi":"10.1101/2025.03.06.641840","title":"DORA AI Scientist: Multi-agent Virtual Research Team for Scientific Exploration Discovery and Automated Report Generation","year":2025,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Scientific Computing and Data Management","field":"Decision Sciences","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto","funders":"","keywords":"Scientific discovery; Computer science; Data science; Psychology; Cognitive science","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","metaepi_narrow","sts","scholarly_communication"],"consensus_categories":["metaresearch"],"category_scores_codex":[0.03402025,0.0005295062,0.0006632197,0.002679862,0.002301073,0.01530428,0.002028187,0.0003800078,0.00001531958],"category_scores_gemma":[0.01084812,0.0004907913,0.000208117,0.003855474,0.0008056872,0.001739194,0.003876577,0.000675184,0.0000923976],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004804855,"about_ca_system_score_gemma":0.002204312,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00009373209,"about_ca_topic_score_gemma":0.00006206329,"domain_scores_codex":[0.9886173,0.0007663791,0.001755724,0.004468276,0.003476945,0.0009153855],"domain_scores_gemma":[0.9891157,0.0006777182,0.0008424699,0.004619945,0.004395208,0.0003490278],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.0001304001,0.001386591,0.00565689,0.0005735369,0.000302474,0.0002021767,0.000352501,0.01380249,0.3584637,0.0159576,0.6027415,0.0004301088],"study_design_scores_gemma":[0.001161055,0.000120268,0.01639633,0.0005263357,0.0001181268,1.205454e-7,0.0001166322,0.8005332,0.04045913,0.0001153561,0.1392843,0.001169093],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.5757919,0.0004012519,0.3979111,0.001169818,0.01969434,0.003072473,0.001106341,0.0008339843,0.00001879802],"genre_scores_gemma":[0.9779581,0.00002613768,0.018363,0.0001274189,0.0006129144,0.0004657744,0.00002071624,0.00005190006,0.002374044],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.7867307,"threshold_uncertainty_score":0.9997544,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.199705360971549,"score_gpt":0.406082448694008,"score_spread":0.2063770877224591,"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."}}