{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"institution":[{"name":"bioRxiv"}],"indexed":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T12:53:54Z","timestamp":1791204834631,"version":"4.1.0"},"posted":{"date-parts":[[2026,9,30]]},"group-title":"Neuroscience","reference-count":38,"publisher":"openRxiv","license":[{"start":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T00:00:00Z","timestamp":1790726400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"accepted":{"date-parts":[[2026,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                <jats:p>Resting-state connectivity can predict task-evoked fMRI activation, but correspondence with an individual task map may partly reflect a shared population pattern. We evaluated the Variational Resting-state-to-Task Prediction TransformeR (VRPTR), a three-dimensional encoder-decoder combining a compressed Transformer bottleneck, variational latent sampling, and multiscale skip connections. Models were trained in 360 healthy adults from the WU-Minn Human Connectome Project and evaluated in 40 held-out participants from the same dataset for the story-versus-math language contrast. VRPTR achieved mean voxel-map Pearson r=0.642 and Dice AUC=0.519, exceeding compact volumetric BrainSurfCNN-like and SWIFUN-like comparators by \u0394r=0.0376 and 0.0335, respectively. A template fixed from the 360 training maps yielded residual correlation 0.364; VRPTR improved correlation but not mean absolute or root mean squared error over this template. A matched factorial ablation associated Transformer processing with improved map correlation (\u0394r=0.0168); the variational main effect did not survive multiple-comparison correction. Component swaps indicated that subject-specific activation patterns depended more on multiscale skip features than on the bottleneck representation. Latent sampling produced a modest association between posterior standard deviation and voxelwise absolute error (mean Spearman \u03c1=0.091). Raw 95% intervals covered only 4.7% of observed values. Five-fold calibration within the held-out cohort increased coverage to 94.8%, and spatially varying uncertainty modestly improved probabilistic scores over a constant-width model. Uncertainty also increased under input degradation. These findings support the contribution of Transformer processing to language-map prediction and distinguish it from subject-specific spatial conditioning and relative uncertainty estimation. Independent validation of calibrated uncertainty and evaluation in clinical cohorts remain necessary.<\/jats:p>","DOI":"10.64898\/2026.09.24.754231","type":"posted-content","created":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T21:20:20Z","timestamp":1790803220000},"source":"Crossref","is-referenced-by-count":0,"title":["VRPTR prediction of individual language activation and uncertainty from resting state fMRI"],"prefix":"10.64898","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-6105-2103","authenticated-orcid":false,"given":"Daniel A.","family":"Di Giovanni","sequence":"first","affiliation":[{"name":"RI-MUHC, McGill University, Montreal, QC, Canada"},{"name":"Department of Diagnostic Radiology, McGill University, Montreal, QC, Canada"},{"name":"McConnell Brain Imaging Centre, Montreal Neurological Institute and Hospital, McGill University, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"D. Louis","family":"Collins","sequence":"additional","affiliation":[{"name":"McConnell Brain Imaging Centre, Montreal Neurological Institute and Hospital, McGill University, Montreal, QC, Canada"},{"name":"Department of Neurology and Neurosurgery, McGill University, Montreal, QC, Canada"},{"name":"Department of Biomedical Engineering, McGill University, Montreal, QC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"54368","reference":[{"key":"2026100505200950000_2026.09.24.754231v1.1","doi-asserted-by":"publisher","DOI":"10.3389\/fninf.2014.00014"},{"key":"2026100505200950000_2026.09.24.754231v1.2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-25089-1"},{"key":"2026100505200950000_2026.09.24.754231v1.3","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.05.033"},{"key":"2026100505200950000_2026.09.24.754231v1.4","doi-asserted-by":"publisher","DOI":"10.1002\/hbm.23661"},{"key":"2026100505200950000_2026.09.24.754231v1.5","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1995.tb02031.x"},{"key":"2026100505200950000_2026.09.24.754231v1.6","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.46.4.978"},{"key":"2026100505200950000_2026.09.24.754231v1.7","doi-asserted-by":"publisher","DOI":"10.1148\/radiol.2482071214"},{"key":"2026100505200950000_2026.09.24.754231v1.8","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1801582115"},{"key":"2026100505200950000_2026.09.24.754231v1.9","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2014.05.014"},{"key":"2026100505200950000_2026.09.24.754231v1.10","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4406"},{"key":"2026100505200950000_2026.09.24.754231v1.11","doi-asserted-by":"publisher","DOI":"10.1038\/nrn1246"},{"key":"2026100505200950000_2026.09.24.754231v1.12","unstructured":"Di Giovanni, D. A . (2024). Deep Learning and Statistical Methods for Clinical Application of Functional Magnetic Resonance Imaging. McGill University (Canada). https:\/\/mcgill.scholaris.ca\/items\/a1cefd32-060e-4855-8294-55ee5d4f3e59"},{"key":"2026100505200950000_2026.09.24.754231v1.13","doi-asserted-by":"publisher","DOI":"10.1007\/s10143-023-02154-6"},{"key":"2026100505200950000_2026.09.24.754231v1.14","doi-asserted-by":"publisher","DOI":"10.1177\/0956797620916786"},{"key":"2026100505200950000_2026.09.24.754231v1.15","doi-asserted-by":"publisher","DOI":"10.1038\/nn.4135"},{"key":"2026100505200950000_2026.09.24.754231v1.16","doi-asserted-by":"publisher","DOI":"10.1198\/016214506000001437"},{"key":"2026100505200950000_2026.09.24.754231v1.17","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2017.07.011"},{"key":"2026100505200950000_2026.09.24.754231v1.18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2018.03.035"},{"key":"2026100505200950000_2026.09.24.754231v1.19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"2026100505200950000_2026.09.24.754231v1.20","doi-asserted-by":"publisher","DOI":"10.1016\/S1053-8119(02)91132-8"},{"key":"2026100505200950000_2026.09.24.754231v1.21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2011.09.015"},{"key":"2026100505200950000_2026.09.24.754231v1.22","doi-asserted-by":"publisher","DOI":"10.1016\/S1361-8415(01)00036-6"},{"key":"2026100505200950000_2026.09.24.754231v1.23","doi-asserted-by":"publisher","DOI":"10.1561\/2200000056"},{"key":"2026100505200950000_2026.09.24.754231v1.24","doi-asserted-by":"publisher","DOI":"10.1186\/s40644-020-00327-w"},{"key":"2026100505200950000_2026.09.24.754231v1.25","doi-asserted-by":"publisher","DOI":"10.1162\/imag_a_00440"},{"key":"2026100505200950000_2026.09.24.754231v1.26","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2015.06.037"},{"key":"2026100505200950000_2026.09.24.754231v1.27","doi-asserted-by":"publisher","DOI":"10.3390\/s22155540"},{"key":"2026100505200950000_2026.09.24.754231v1.28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"2026100505200950000_2026.09.24.754231v1.29","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2020.3006437"},{"key":"2026100505200950000_2026.09.24.754231v1.30","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2012.12.028"},{"key":"2026100505200950000_2026.09.24.754231v1.31","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2021.118849"},{"key":"2026100505200950000_2026.09.24.754231v1.32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"2026100505200950000_2026.09.24.754231v1.33","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhx179"},{"key":"2026100505200950000_2026.09.24.754231v1.34","doi-asserted-by":"publisher","DOI":"10.1212\/WNL.0000000000003532"},{"key":"2026100505200950000_2026.09.24.754231v1.35","doi-asserted-by":"publisher","DOI":"10.1126\/science.aad8127"},{"key":"2026100505200950000_2026.09.24.754231v1.36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2013.05.041"},{"key":"2026100505200950000_2026.09.24.754231v1.37","unstructured":"Vaswani, A. , Shazeer, N. , Parmar, N. , Uszkoreit, J. , Jones, L. , Gomez, A. N. , Kaiser, \u0141. , & Polosukhin, I . (2017). Attention is all you need. Advances in neural information processing systems, 30. https:\/\/papers.nips.cc\/paper\/7181-attention-is-all-you-need"},{"key":"2026100505200950000_2026.09.24.754231v1.38","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2014.01.060"}],"container-title":[],"original-title":[],"link":[{"URL":"https:\/\/syndication.highwire.org\/content\/doi\/10.64898\/2026.09.24.754231","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,5]],"date-time":"2026-10-05T12:20:17Z","timestamp":1791202817000},"score":1,"resource":{"primary":{"URL":"http:\/\/biorxiv.org\/lookup\/doi\/10.64898\/2026.09.24.754231"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,30]]},"references-count":38,"URL":"https:\/\/doi.org\/10.64898\/2026.09.24.754231","relation":{},"subject":[],"published":{"date-parts":[[2026,9,30]]},"subtype":"preprint"}}