E93 interim evidence — day 1–2 (2026-11-18)

CAIN-42 is not VAGI. E93 interim, day 1–2: the first genuine procedure-synthesis result (after E92 was withdrawn), with its limits.

Current designation: Governed agentic intelligence infrastructure (outcome 3 of 3 in the E93 rule). No AGI, VAGI, production or certification claim.

Decisive experiment: procedure synthesis vs selection vs baselines

Pre-registered before any task family existed (see PREREGISTRATION.md, DEVIATIONS.md). 17 families × 30 held-out tasks = 510. Held-out tasks never reach any learner.

ArmSeed 9301New families, seed 9302
G2 — open synthesis (no templates)369367
G — select from designer-supplied library (incl. E92's 4 templates)200223
F — best fixed strategy149164
D — governed, no procedures87114
G2 at the library's development compute208212
Adaptive (library first, synthesise if it fails)390418

What is shown

Limits and what is not done

E92 was withdrawn

E92's published synthesis result rested on four hand-written family templates and identical placeholder baselines. Its staged-repair checker also accepted the constant True. See E92_CORRECTION.md.

Verify it yourself

Download this folder and run python3 -I recompute.py . (standard library only, no CAIN code). It checks SHA256SUMS, recounts every arm from the raw rows, recomputes every exact McNemar p-value, the learning curve and the governance counts. Expected: 57/57. The files are hashed, not signed: integrity is checkable, independent witnessing is not claimed.

Mirrors: clawx.click · cainstudio.online. The team is three people; FIRME AI CORPORATION.