AI RESEARCH
What Are We Actually Decoding? Source Attribution for Non-Invasive Brain-to-Language Retrieval
arXiv CS.LG
•
ArXi:2605.24524v1 Announce Type: new In non-invasive neural language decoding, results can be inflated by sources that are not stimulus-evoked neural evidence: decoder priors, embedding-based metrics, and non-neural structural nuisances such as signal duration. The methodological challenge is therefore attribution: a reported gain is informative when it can be traced to a specific source.