{"id":"W4388234122","doi":"10.1101/2023.10.30.564783","title":"Mining the neuroimaging literature","year":2023,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Biomedical Text Mining and Ontologies","field":"Biochemistry, Genetics and Molecular Biology","cited_by":3,"is_retracted":false,"has_abstract":true,"ca_institutions":"McGill University; Montreal Neurological Institute and Hospital","funders":"","keywords":"Computer science; Workflow; Upload; Process (computing); Information retrieval; Task (project management); Information extraction; Data science; Biomedical text mining; Data mining; Text mining; World Wide Web; Database","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":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0006381633,0.0004846362,0.0003470234,0.0001201304,0.0002414543,0.0003101448,0.0009577938,0.0007489239,0.000006355858],"category_scores_gemma":[0.0007947716,0.0003799399,0.0002159845,0.0003875596,0.0002913134,0.000004123627,0.001233081,0.0008432936,0.00004441091],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.00004071139,"about_ca_system_score_gemma":0.0003531172,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.00001435787,"about_ca_topic_score_gemma":0.000002334951,"domain_scores_codex":[0.9975182,0.0001778278,0.0003709863,0.001045928,0.0003040281,0.0005830114],"domain_scores_gemma":[0.997775,0.00006867776,0.0002429494,0.001511521,0.0002335373,0.0001682889],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"not_applicable","study_design_scores_codex":[0.00004214874,0.00004930037,0.005329362,0.0003133682,0.0002734972,0.000165022,0.00003959474,0.00008457607,0.9689391,0.0000926822,0.02463083,0.00004052372],"study_design_scores_gemma":[0.001161259,0.0003225073,0.1382331,0.001845311,0.0003145779,3.790007e-7,0.00005310918,0.00120226,0.4258048,0.00001490285,0.428333,0.002714757],"study_design_candidate":"bench_or_experimental","study_design_consensus":null,"genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.9822962,0.008538168,0.001761097,0.002802846,0.003365224,0.0004558259,0.0002033475,0.0005558729,0.00002139067],"genre_scores_gemma":[0.9920586,0.0008458218,0.004212294,0.0009069074,0.001595283,0.000139622,0.000002715656,0.0001548255,0.00008392593],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.5431343,"threshold_uncertainty_score":0.9998652,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.02011087088969365,"score_gpt":0.2459407135775096,"score_spread":0.2258298426878159,"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."}}