AWhat changed
Tests correlations with gradient/erasure importance and searches permuted or adversarial attention distributions that preserve predictions in selected text classification, QA and inference models.
Scientific scope
Tests correlations with gradient/erasure importance and searches permuted or adversarial attention distributions that preserve predictions in selected text classification, QA and inference models. Per-instance attention is detached while encoded states remain fixed. Results do not prove that all attention or transformer circuits are unexplainable; later controlled-model diagnostics raise a different experimental question. Only non-medical text tasks and general methods are curated.
Evidence
The linked original sources describe the stated contribution and its evidence limits. WRS has not independently rerun the experiments or certified a proof. Per-instance attention is detached while encoded states remain fixed. Results do not prove that all attention or transformer circuits are unexplainable; later controlled-model diagnostics raise a different experimental question. Only non-medical text tasks and general methods are curated.
Contributors
- Source-listed authors and technical contributors · SCIENCE: Source-listed authors or explicitly credited technical contributors for the cited versions. Family entries retain source-specific attribution; a combined list is not one original-paper byline or equal individual work. Names alone do not establish resolved identities.
Provisional WRS assessment, edition 2026-10-16.1. Independent expert calibration is pending. This grade does not certify correctness or assign ownership.
Full scientific record · Browse contribution grades · Request a correction