{"id":"W3203937348","doi":"10.1038/s41597-021-01033-3","title":"The “Narratives” fMRI dataset for evaluating models of naturalistic language comprehension","year":2021,"lang":"en","type":"article","venue":"Scientific Data","topic":"Neurobiology of Language and Bilingualism","field":"Neuroscience","cited_by":153,"is_retracted":false,"has_abstract":true,"ca_institutions":"BC Children's Hospital; University of British Columbia; McGill University; Montreal Neurological Institute and Hospital","funders":"Eunice Kennedy Shriver National Institute of Child Health and Human Development; National Institute of Mental Health; Advanced Research Projects Agency; U.S. Department of Health and Human Services; National Institutes of Health; National Institute of Biomedical Imaging and Bioengineering; Intel Corporation; Defense Advanced Research Projects Agency; U.S. Department of Defense","keywords":"Narrative; Computer science; Metadata; Comprehension; Neuroimaging; Variety (cybernetics); Benchmark (surveying); Data collection; Natural language processing; Psychology; Artificial intelligence; Linguistics; World Wide Web; Neuroscience","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":[],"consensus_categories":[],"category_scores_codex":[0.001592715,0.001259389,0.0004213242,0.0009778963,0.0006203449,0.0006794954,0.001426484,0.001090822,0.007291493],"category_scores_gemma":[0.007017462,0.0003093645,0.000874189,0.0006747083,0.0005960677,0.0006993709,0.001255965,0.001044822,0.005129272],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0004880216,"about_ca_system_score_gemma":0.0009722618,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.005903044,"about_ca_topic_score_gemma":0.01770069,"domain_scores_codex":[0.9994617,0.0002097153,0.00005574099,0.0001365205,0.00009499938,0.00004139839],"domain_scores_gemma":[0.998226,0.0008247644,0.0001350744,0.0004540312,0.0002251913,0.0001350612],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"not_applicable","study_design_gemma":"not_applicable","study_design_scores_codex":[0.002284026,0.001272724,0.03560604,0.003931297,0.001189447,0.00264969,0.002446175,0.01927046,0.02974381,0.006697807,0.7829411,0.1119675],"study_design_scores_gemma":[0.001751419,0.001786535,0.149403,0.0009144583,0.0008821567,0.009057369,0.002635229,0.08200864,0.03404682,0.03611228,0.6809604,0.0004417546],"study_design_candidate":"not_applicable","study_design_consensus":"not_applicable","genre_codex":"dataset","genre_gemma":"dataset","genre_scores_codex":[0.2624947,0.002619112,0.03851255,0.001989082,0.0004399001,0.001030396,0.6674145,0.01041227,0.01508746],"genre_scores_gemma":[0.1470914,0.0004960718,0.03914541,0.0004360896,0.000128862,0.001678655,0.805869,0.001118118,0.004036319],"genre_candidate":"dataset","genre_consensus":"dataset","teacher_disagreement_score":0.007291493,"threshold_uncertainty_score":0.02439249,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.2473092512972187,"score_gpt":0.4295171565604403,"score_spread":0.1822079052632216,"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."}}