wassnameandClaude Opus 4.7 64adf9267d SI tables v2: SI_best, SI_k1, fix/broke rates; paired prompts; IID syc ...

- Pair prompt baselines as alpha=-1/0/+1 (dishonest/base/honest) under
  simple and engineered families, giving full bidirectional SI for
  prompts (same as dW)
- Add SI_best = max(si_fwd, si_rev) * pmass^2 * 100 -- sign-aligned
  upper bound (snooping-aware robustness probe)
- Add SI_k1 (symmetric, breaks weighted 1x) alongside default SI_k2
  to expose how much the class-imbalance-driven 2x penalty contributes
- Expose fix_rate / broke_rate columns so the SI components are visible
- Add IID syc table (held-out persona claims) using
  cross_adapter_ablation/sycophancy_per_row.csv with variant=full_all_tensors
- Add raw mean +- std logratio table per (method, coeff) for OOD

The IID/OOD split shows: dW interventions land hard on IID (PiSSA biggest,
+5.7 mean shift) but most break OOD via the broke_rate channel. OFT and
engineered prompts are the only methods with non-negative SI_best.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-04-28 08:29:49 +08:00

..

ablation_analysis.py

T6/T7/T8 ablations + lens-search hold pending multiseed

2026-04-27 19:05:20 +08:00

honesty_tables.py

SI tables v2: SI_best, SI_k1, fix/broke rates; paired prompts; IID syc

2026-04-28 08:29:49 +08:00