{"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":"codex-gemma-dda1882f352a","candidate_categories":[],"consensus_categories":[],"category_scores_codex":[0.001267522,0.0001005132,0.0001400109,0.00003589362,0.0006749462,0.0001844863,0.00137491,0.00003520173,0.00004030271],"category_scores_gemma":[0.002973639,0.00006570567,0.00003528221,0.0003007924,0.0005612801,0.000302567,0.0009650465,0.0001220863,0.00001295217],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.000006397534,"about_ca_system_score_gemma":0.0001312925,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.000007881589,"about_ca_topic_score_gemma":0.00006231725,"domain_scores_codex":[0.9980662,0.0002922432,0.0002642288,0.0008168192,0.0003044851,0.0002559728],"domain_scores_gemma":[0.9964652,0.001121804,0.0001448116,0.002106592,0.000120506,0.00004110069],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.00001999636,0.00003322263,6.181043e-7,0.00002166403,0.000003546843,0.00004817158,0.0008626437,0.00003294813,0.9360586,0.0006580873,0.05995823,0.002302214],"study_design_scores_gemma":[0.0008802984,0.00009664438,0.00001071572,0.00008031198,0.00005319115,0.0002501753,0.004513923,0.06786964,0.8238451,0.009164152,0.0929156,0.0003201784],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.8620178,0.001909843,0.001298702,0.002064248,0.004318538,0.0007912776,0.1271446,0.00006103427,0.0003939027],"genre_scores_gemma":[0.9469437,0.00002041283,0.004825233,0.0009447853,0.0001141926,0.00001342403,0.04441571,0.00002013192,0.002702406],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.1122135,"threshold_uncertainty_score":0.5191209,"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."}}