finding
active
finding:spd-recovers-tms-ground-truth-robustly-across-seeds-with-less-tuning-than-apdSPD recovers TMS ground truth robustly across seeds with less tuning than APD
Robustness.
Source paper
extracted_from(2025) · Lucius Bushnaq · Dan Braun · Lee Sharkey
Neighborhood — ranked by edge-count
Papers (1)
paper
Claims (1)
claim
- Central claim.
Related by similarity (8)
cosine ≥ 0.65 · no typed edgeEntities in the same semantic neighborhood but without a typed relation to this one — candidates for new edges or unrecognized duplicates.
- New models harder for APD.
- SPD avoids shrinkage.
- Ground truth mechanisms identified.
- Author interpretation.
- SPD's robustness comes from trained importance functions, gradient flow, no simplicity loss, and direct causal importancehypothesis0.753Four hypothesized sources.
- Key quote connecting path redundancy to interferometric information encoding.
- Variance decomposition showing the disentanglement of polarity from truth across model depth.
- SPD avoids shrinkage because importance norm penalizes mask probability, not singular valuesclaim0.738Mechanism.