CAIN-42 CAIN Studio

CAIN-42 evidence library

E130 — Governed Recursive Self-Improvement (measured)

Evidence bundle for evolution E130: 0 claims, 0 of 0 invariants held.

Last reviewed 2026-11-21

The bundle's own README

E130 — Governed Recursive Self-Improvement (measured)#

Verdict: NEGATIVE_OR_PARTIAL AGI status: NOT ACHIEVED Gates: 9/14 Actual elapsed: 2640.079 s Sealed answer commitment: 520ccbf4f26b893e14edc5973315dd490369205ed2d08c325db200ec6fcb5898

What ran#

A frozen engine (bounded search over a library of integer programs) was evaluated on 48 sealed tasks before any self-modification, then four times more. Between generations the engine used its own search on development tasks and wrote recurring fragments of its own solutions into its executable library. The library it ran on generation N+1 contained programs that did not exist at generation N.

Every sealed answer was withheld until scoring. Sealed results were never used for improvement or promotion. Promotion used development data only.

Compounding curve (main arm)#

generationlibrarymax depthT1T2T3T4T6T8T12T16
02111.0000.0000.0000.0000.0000.0000.0000.000
16931.0001.0001.0001.0000.1670.0000.0000.000
26931.0001.0001.0001.0000.1670.0000.0000.000
311761.0001.0001.0001.0000.1670.0000.0000.000
4165121.0001.0001.0001.0000.1670.0000.0000.000
5208131.0001.0001.0001.0000.3330.0000.0000.000
6246131.0001.0001.0001.0000.3330.0000.0000.000
7273141.0001.0001.0001.0000.3330.0000.0000.000

Each cell is the fraction of query predictions correct for that nominal tier. A tier is a chain of K two-primitive concepts; tiers are nominal because functional equivalences can make a task reachable one step earlier, which is disclosed.

Meta-selection (the improver improving)#

Self-written library#

Controls at the same generation count#

Gates#

Honest limits#

governed loop in a constructed domain.

Reproduce#

python3 -m cain.cain2027.e130.cli campaign --seed 128 --generations 4
python3 artifacts/e130/verify_e130_offline.py artifacts/e130

The verifier imports no CAIN code. It re-applies every recorded program to the sealed inputs, recomputes every accuracy, checks the answer commitment, the library expansion chain, the Merkle root and the signature.

Try CAIN-42 on your own agents

Create a free account and every new account starts with a 30-day trial of the full platform. Or try the sandbox first, with no account at all.

Create a free account →  ·  Try the sandbox  ·  See the whole ecosystem