Introduces NeuroDoc and NeuroAudit to create a community-reviewed corpus of 53 EEG benchmark entries with 245 task definitions using a rulebook-guided task document and executable kernel.
Frontiers in Human Neuroscience , year =
5 Pith papers cite this work, alongside 11 external citations. Polarity classification is still indexing.
5
Pith papers citing it
11
external citations · external index
citation-role summary
background 1
citation-polarity summary
years
2026 5verdicts
UNVERDICTED 5roles
background 1polarities
background 1representative citing papers
Subject identity variance dominates frozen representations in three EEG foundation models by 13-89x over null, and erasing the linear subject axis improves label decoding where within-subject label variation exists.
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
EEG foundation models encode 68.6% of a 63-feature clinical lexicon in a representation-causal way, with frequency-domain features dominant; these recover 79.3% of the models' advantage over random baselines on average.
Controlled comparison finds that a pretrained time-series foundation model can be effectively used as a frozen temporal feature extractor in EEG foundation models, with task-specific performance differences.
citing papers explorer
-
EEG Benchmarking Needs a Task Specification Layer: NeuroDoc for Rulebook-Guided, Executable Benchmark Construction
Introduces NeuroDoc and NeuroAudit to create a community-reviewed corpus of 53 EEG benchmark entries with 245 task definitions using a rulebook-guided task document and executable kernel.
-
The Identity Trap in EEG Foundation Models: A Diagnostic Audit
Subject identity variance dominates frozen representations in three EEG foundation models by 13-89x over null, and erasing the linear subject axis improves label decoding where within-subject label variation exists.
-
DARE-EEG: A Foundation Model for Mining Dual-Aligned Representation of EEG
DARE-EEG is a self-supervised EEG foundation model that enforces mask-invariance via contrastive mask alignment and momentum anchor alignment, plus conv-linear-probing for heterogeneous setups, achieving SOTA accuracy and cross-dataset portability.
-
What Do EEG Foundation Models Capture from Human Brain Signals?
EEG foundation models encode 68.6% of a 63-feature clinical lexicon in a representation-causal way, with frequency-domain features dominant; these recover 79.3% of the models' advantage over random baselines on average.
-
Temporal Feature Extractors in EEG Foundation Models: A Controlled Comparison Including a Pretrained Time-Series Model
Controlled comparison finds that a pretrained time-series foundation model can be effectively used as a frozen temporal feature extractor in EEG foundation models, with task-specific performance differences.