Source: research note experiments/notes/2026-06-09T01-xi-true-robustness-uuid-fix.md (from closed PR #216).
Finding: xi_robustness_v2's genuine adversarial robustness is ≈0.2326 (3-trial deterministic 0.14789x). The earlier ~0.56 average was a UUID-ordering artifact — the mean of adversarials attacking successfully (xi≈0.23) and adversarials self-disrupting (xi→1.0), an illusion of robustness. Deterministic adversarial UUIDs are now set at build time in build_adversarial_set_l5, so xi is stable and the 0.23 is real.
Content-based chirality (Attempt A in the note) was catastrophic (carrier_e→0.000, transfer→0.379) and is a frozen axis — do not modify stage_chiral_perturbation sort.
Build-on directions to raise xi 0.23→>0.5:
- Amplitude pruning during dreaming — prune high-amplitude memories lacking phase coherence with their cluster (adversarials sit slightly off-phase).
- Frequency-band enforcement — adversarials are stored at
frequency=0.1 yet attack the attention band; stricter band filtering could isolate them.
- Phase authentication — corpus memories have deterministic encoder-derived initial phases; adversarials use random phases. A phase-consistency check could reject them.
Source: research note
experiments/notes/2026-06-09T01-xi-true-robustness-uuid-fix.md(from closed PR #216).Finding: xi_robustness_v2's genuine adversarial robustness is ≈0.2326 (3-trial deterministic 0.14789x). The earlier ~0.56 average was a UUID-ordering artifact — the mean of adversarials attacking successfully (xi≈0.23) and adversarials self-disrupting (xi→1.0), an illusion of robustness. Deterministic adversarial UUIDs are now set at build time in
build_adversarial_set_l5, so xi is stable and the 0.23 is real.Content-based chirality (Attempt A in the note) was catastrophic (carrier_e→0.000, transfer→0.379) and is a frozen axis — do not modify
stage_chiral_perturbationsort.Build-on directions to raise xi 0.23→>0.5:
frequency=0.1yet attack the attention band; stricter band filtering could isolate them.