{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T06:22:30Z","timestamp":1787638950440,"version":"build-2736575974"},"reference-count":31,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Robot. Autom. Lett."],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1109\/lra.2026.3723337","type":"journal-article","created":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T19:12:57Z","timestamp":1786561977000},"page":"11212-11219","source":"Crossref","is-referenced-by-count":0,"title":["Auditing Instruction\u2013Trajectory Mismatches in Multimodal Robot Demonstrations"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5727-8140","authenticated-orcid":false,"given":"Simon","family":"Holk","sequence":"first","affiliation":[{"name":"AI Robot Association (AIRoA)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ryosuke","family":"Takanami","sequence":"additional","affiliation":[{"name":"AI Robot Association (AIRoA)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1537-7770","authenticated-orcid":false,"given":"Tatsuya","family":"Matsushima","sequence":"additional","affiliation":[{"name":"AI Robot Association (AIRoA)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yusuke","family":"Iwasawa","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2106-8907","authenticated-orcid":false,"given":"Yutaka","family":"Matsuo","sequence":"additional","affiliation":[{"name":"The University of Tokyo","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6283-9883","authenticated-orcid":false,"given":"Yueh-Hua","family":"Wu","sequence":"additional","affiliation":[{"name":"AI Robot Association (AIRoA)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5744-3027","authenticated-orcid":false,"given":"Kei","family":"Ota","sequence":"additional","affiliation":[{"name":"AI Robot Association (AIRoA)","place":["Tokyo, Japan"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.025"},{"key":"ref2","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10611477"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2024.xx.090"},{"key":"ref5","first-page":"2679","article-title":"OpenVLA: An open-source vision-language-action model","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Kim","year":"2025"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref7","first-page":"17","article-title":"$\\pi _{0.5}$: A vision-language-action model with open-world generalization","volume-title":"Proc. 9th Conf. Robot Learn.","volume":"305","author":"Black"},{"key":"ref8","first-page":"2907","article-title":"CUPID: Curating data your robot loves with influence functions","volume-title":"Proc. 9th Conf. Robot Learn.","volume":"305","author":"Agia"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.023"},{"key":"ref10","article-title":"DataMIL: Selecting data for robot imitation learning with datamodels","volume-title":"Proc. 14th Int. Conf. Learn. Representations","author":"Dass"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.071"},{"key":"ref12","article-title":"SCIZOR: A self-supervised approach to data curation for large-scale imitation learning","volume-title":"Proc. IEEE Int. Conf. Robot. Automat.","author":"Zhang"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2023.xix.029"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/icra57147.2024.10610606"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2026.3726383"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3773904"},{"key":"ref18","article-title":"Evaluating uncertainty and quality of visual language action-enabled robots","author":"Valle"},{"key":"ref19","first-page":"145","article-title":"Re-mix: Optimizing data mixtures for large scale imitation learning","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Hejna","year":"2025"},{"key":"ref20","first-page":"4158","article-title":"Scaling robot policy learning via zero-shot labeling with foundation models","volume-title":"Proc. 8th Conf. Robot Learn.","volume":"270","author":"Blank","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1613\/jair.1.12125"},{"key":"ref22","first-page":"540","article-title":"Deep K-NN for noisy labels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Bahri","year":"2020"},{"key":"ref23","first-page":"74447","article-title":"LEMoN: Label error detection using multimodal neighbors","volume-title":"Proc. 42nd Int. Conf. Mach. Learn.","volume":"267","author":"Zhang"},{"key":"ref24","article-title":"Seeing whats wrong: A trajectory-guided approach to caption error detection","volume-title":"Proc. 14th Int. Conf. Learn. Representations","author":"Afriat"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556596"},{"key":"ref27","article-title":"Generalized product of experts for automatic and principled fusion of Gaussian process predictions","author":"Cao","year":"2014"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1939"},{"key":"ref29","article-title":"When vision overrides language: Evaluating and mitigating counterfactual failures in vlas","author":"Fang","year":"2026"},{"key":"ref30","article-title":"Cosmos world foundation model platform for physical AI"},{"key":"ref31","article-title":"SmolVLA: A vision-language-action model for affordable and efficient robotics","author":"Shukor"}],"container-title":["IEEE Robotics and Automation Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7083369\/11656882\/11652885.pdf?arnumber=11652885","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,25]],"date-time":"2026-08-25T05:34:05Z","timestamp":1787636045000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11652885\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":31,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/lra.2026.3723337","relation":{},"ISSN":["2377-3766","2377-3774"],"issn-type":[{"value":"2377-3766","type":"electronic"},{"value":"2377-3774","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10]]}}}