diff options
Diffstat (limited to 'protocol/EVIDENCE_SUMMARY.md')
| -rw-r--r-- | protocol/EVIDENCE_SUMMARY.md | 3 |
1 files changed, 2 insertions, 1 deletions
diff --git a/protocol/EVIDENCE_SUMMARY.md b/protocol/EVIDENCE_SUMMARY.md index d1d6d9b..2591c97 100644 --- a/protocol/EVIDENCE_SUMMARY.md +++ b/protocol/EVIDENCE_SUMMARY.md @@ -102,7 +102,7 @@ Even in the meaningful regime (vanilla DFA at ep 1, ‖g‖ ~ 10⁻⁶), DFA's local credit signal `e_T B_l^T` is essentially uncorrelated with BP grad on deep layers. **Caught by direct per-layer cosine measurement.** -### Five independent validations of the converged framing +### Six independent validations of the converged framing | # | evidence | result | reproduce | |---|---|---|---| @@ -111,6 +111,7 @@ on deep layers. **Caught by direct per-layer cosine measurement.** | 3 | Hypothesis B disambiguation (vanilla early-epoch) | vanilla deep cos -0.008 ± 0.013 across 3 seeds × ep 1, even with ‖g‖ in meaningful regime | `experiments/vanilla_dfa_early_ckpt.py` + measure script | | 4 | BP+penalty capacity-cost 2×2 control | BP+pen acc 0.530 (-8 pp); DFA+pen 0.363 (+5.5 pp); 17 pp residual gap consistent with credit quality | `experiments/bp_with_penalty_control.py` | | 5 | Multi-seed lock-in (round 20) | 24 measurements (3 seeds × 2 epochs × 4 deep layers) all in [-0.04, +0.02] | iterate measure script over s42/s123/s456 × ep1/ep2 | +| 6 | **Perturbation correlation triangulation** (round 19 alt metric) | vanilla deep ρ +0.002, penalized deep ρ +0.080 ± 0.011 (3 seeds). Different metric (no eps clamp, sample-level loss change), same pattern as cos | `experiments/perturbation_correlation_audit.py` | ### Penalty rescue 3-seed table (lam=1e-2) |