ClaimCLM-2026-0104v0.1

F4 — Scaffolding separation

If scaffolding does not change the structure of the capability source, SSR ≈ 1 should hold across most tasks and test-time compute budgets. If a large share of benchmark quality appears only under multi-sample, tool, verifier or loop conditions, the distinction between model-native and system capability is empirically necessary. First data point: three easy tasks on a local 9B model gave SSR = 1.0 — consistent with 'no gap' on tasks the native pass already solves, and uninformative beyond that because the quality axis was confounded by format compliance.

Research status

EXPERIMENTAL being tested experimentally

Evidence level

E2 Controlled experiment

Data basis

THEORY Theoretical reasoning only; no measurement.

Version

0.1

Updated

2026-09-02

Created

2026-09-02

Domain

Evaluation

Program

PRG-2026-0101 Intelligence Physical Metrology (IPM)

Authors

Neo.K (EveMissLab)

AI collaborators

Aletheia (GPT-5.6 Sol, OpenAI ChatGPT)