{"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":"metacan-v3-hybrid-931329e0061c","candidate_categories":["metaresearch","bibliometrics"],"consensus_categories":[],"category_scores_codex":[0.006080458,0.0008883917,0.0008863672,0.0512669,0.001609067,0.004045762,0.001826692,0.001003114,0.01136983],"category_scores_gemma":[0.03348253,0.0004559031,0.001237068,0.02660515,0.001012858,0.002996203,0.003533688,0.001045722,0.005697633],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.001673354,"about_ca_system_score_gemma":0.00699869,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.004786985,"about_ca_topic_score_gemma":0.009229951,"domain_scores_codex":[0.9952117,0.001280412,0.0008308403,0.000930225,0.001583316,0.0001635505],"domain_scores_gemma":[0.9752035,0.01230842,0.002698863,0.002162699,0.0068001,0.0008264483],"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":[0.0002208109,0.0001263784,0.01373469,0.01263079,0.0004898143,0.003841529,0.003036297,0.00163631,0.01076074,0.02810105,0.1770854,0.7483361],"study_design_scores_gemma":[0.00007393129,0.00007178662,0.01707009,0.006171129,0.0006948064,0.002518882,0.002838047,0.00716459,0.01155109,0.0678634,0.8838795,0.0001027538],"study_design_candidate":"simulation_or_modeling","study_design_consensus":null,"genre_codex":"methods","genre_gemma":"empirical","genre_scores_codex":[0.09492111,0.09392494,0.3056056,0.02675115,0.003250883,0.003908671,0.3036064,0.01332342,0.1547078],"genre_scores_gemma":[0.1704705,0.04146601,0.546598,0.00266679,0.001893722,0.002963078,0.2141499,0.002139161,0.01765291],"genre_candidate":"empirical","genre_consensus":null,"teacher_disagreement_score":0.9939196,"threshold_uncertainty_score":0.03803587,"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."}}