{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch"],"consensus_categories":[],"category_scores_codex":[0.008833291,0.0009251032,0.0006342161,0.001742164,0.0007961483,0.002310445,0.002537637,0.001239078,0.01339776],"category_scores_gemma":[0.0164831,0.0007284352,0.0009651612,0.0007312744,0.0007142989,0.002020454,0.004227081,0.001412026,0.008394239],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0006825202,"about_ca_system_score_gemma":0.00254704,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0008215256,"about_ca_topic_score_gemma":0.0008634256,"domain_scores_codex":[0.9963633,0.001639009,0.0002539275,0.0008194156,0.0007351087,0.0001892266],"domain_scores_gemma":[0.9895509,0.004442876,0.0007710161,0.002623028,0.00123426,0.001377931],"domain_codex":null,"domain_gemma":"methods","domain_candidate":"methods","domain_consensus":null,"study_design_codex":"design_other","study_design_gemma":"simulation_or_modeling","study_design_scores_codex":[0.003413056,0.001216385,0.00715723,0.00116261,0.0003471292,0.001075445,0.00211412,0.02970286,0.05101157,0.04180885,0.1902705,0.6707202],"study_design_scores_gemma":[0.001527103,0.0007856685,0.002017963,0.0001391161,0.0001754284,0.0006317227,0.0003868817,0.5172246,0.05755325,0.03760071,0.381671,0.0002866625],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"methods","genre_scores_codex":[0.01461637,0.0003183729,0.8646905,0.001024989,0.0004040964,0.001016654,0.00166202,0.1084005,0.007866506],"genre_scores_gemma":[0.09597762,0.0002413336,0.8797308,0.0005060196,0.0001729889,0.001631866,0.003982407,0.00382631,0.01393066],"genre_candidate":"methods","genre_consensus":"methods","teacher_disagreement_score":0.9911667,"threshold_uncertainty_score":0.04671544,"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."}}