TheoryTHY-2026-0109v0.1
Scaffolding capability record: SSR, SDR, SCM and the ablation ladder
A system is (model M, scaffolding vector S) with S = (tool, retry, multi-sample, verifier, environment, memory, planner). Single-pass quality Q_SP = Q(M, 0) and full quality Q_F = Q(M, S_F) define the scaffolding survival ratio SSR = Q_SP / Q_F, the dependence ratio SDR = 1 − SSR, the scaffold cost multiplier SCM_j = C_j^F / C_j^SP and marginal yields along a controlled ladder A0 native single pass → A1 extended budget → A2 multi-sample → A3 verifier → A4 tool/environment → A5 full agentic. The record also carries scaffold interactions (Shapley-style attribution), discarded and hidden work, and a capability vector (single-pass, loop, tool, verification, environment intelligence). A loop is not cheating; high dependence is a structure, not a defect — what destroys comparability is hiding the capability source and its physical cost.
Definitions
definitions- Scaffolding vector S = (S_T, S_R, S_N, S_V, S_E, S_M, S_P); Q_SP = Q(M, 0), Q_F = Q(M, S_F).
- SSR = Q_SP / Q_F; SDR = 1 − SSR; SCM_j = C_j^F / C_j^SP; marginal scaffolding yield Y_S,k = (Q_{k+1} − Q_k) / (C_{k+1} − C_k); scaffolding physical overhead ΔP_S = P_F ⊖ P_SP (typed).
- Capability vector I = (I_SP, I_L, I_T, I_V, I_E); Scaffolding Capability Record 𝔖_C = (𝔔_SP, 𝔔_F, ΔQ_S, SSR, P_SP, P_F, ΔP_S, G_S, φ, P_waste, Grade_S).
- S-grades E unknown harness / D declared components / C execution trace / B controlled ablations / A factorial interaction / A+ physical-causal attribution.
Assumptions
assumptions- Conditions start from the same initial information (A0–A3); A4/A5 information gain is marked separately.
- Scaffold contributions interact (verifier needs candidates), so one-at-a-time ablation is not unique attribution.
Claims
claims- Loop ≠ Cheating; SystemCapability ≠ ModelNativeCapability; Pass@k ≠ Pass@1; BestOfN ≠ SingleTrajectory.
- GenerationAbility ≠ VerificationAbility; ToolAccess ≠ ToolUtilizationIntelligence; ExternalMemory ≠ InternalLearning.
- ScaffoldingDependence ≠ SystemDefect; Loopless ≠ SuperiorByDefinition; InvisibleOutput ≠ ZeroCost; HiddenRetry ≠ FreeRetry.
- TransparencyOfCompute ≠ DisclosureOfPrivateReasoning; ScaffoldMeasurement ⇒ QualityAndCostTogether.
Formalisation
formalization- Shapley-like attribution φ_i = Σ_A w(A)[Q(A ∪ {i}) − Q(A)] with sampling approximation and uncertainty U_φ.
- Brute-force region: ΔQ ≪ 1 with ΔC ≫ 1; selection waste ratio SWR = C_discarded / C_total; P_waste = Σ discarded attempts.
Predictions
predictions- A stable scaffolding response curve exists for a fixed model and task set; SSR < 1 on non-trivial tasks (Falsifiable Claim 4).
Falsification / failure conditions
falsification_conditions- If Q_F ≈ Q_SP across most tasks, models and compute budgets, the native/system separation loses empirical necessity (F4).
Known limitations
known_limitations- First real data point (2026-09-03): SSR = 1.0 on three easy tasks with a 3.1× energy multiplier — a null result on an instrument whose quality axis was itself confounded; no factorial or Shapley analysis yet.
Evidence
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
EXP-2026-0101 Experiment A — single-pass vs scaffolded controlled measurement (protocol v0.1) | tests | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0463 |
EXP-2026-0103 XA-06 first real-model pilot — Qwythos-9B-v2 on the A0→A5 ladder (36 trials, 2026-09-03) | tests | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0479 |
Relations
| Source | Relation | Target | Status | ID |
|---|---|---|---|---|
THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | extends | THY-2026-0101 Turn decomposition and externally loopless intelligence | ACTIVE | REL-2026-0374 |
THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | extends | THY-2026-0105 Physical computation cost vector and computational spacetime | ACTIVE | REL-2026-0375 |
THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | extends | THY-2026-0108 Typed, versioned quality ontology for high-ambiguity artifacts | ACTIVE | REL-2026-0376 |
RES-2026-0103 Capability line — how much intelligence remains without the loop, and the unified intelligence event | develops | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0366 |
THY-2026-0110 The canonical intelligence event, Pareto comparison and no premature scalarization | extends | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0377 |
PAP-2026-0109 Paper 09 — How much intelligence remains without the loop? Single-pass capability, scaffolding dependence, and hidden computational cost | formalizes | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0424 |
BEN-2026-0101 XA-02 — 30-task pilot pack for the A0→A5 scaffolding response | evaluates | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0446 |
SYS-2026-0102 XA-04 — A0→A5 model runner and scaffold orchestrator | implements | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0452 |
SYS-2026-0103 XA-06 — real-model pilot gate | implements | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0455 |
EXP-2026-0101 Experiment A — single-pass vs scaffolded controlled measurement (protocol v0.1) | tests | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0463 |
EXP-2026-0103 XA-06 first real-model pilot — Qwythos-9B-v2 on the A0→A5 ladder (36 trials, 2026-09-03) | tests | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0479 |
RST-2026-0101 Scaffolding response on three easy tasks: SSR = 1.0, 3.1× device energy at A5, 7.9–9.3× at A2–A4 | qualifies | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0486 |
RST-2026-0102 Diagnostic: the measured 'quality' was format compliance on 2 of 3 tasks; verifier serialization failed 3/18; the A3/A4 rise is a missingness artifact | qualifies | THY-2026-0109 Scaffolding capability record: SSR, SDR, SCM and the ablation ladder | ACTIVE | REL-2026-0491 |
History and provenance
- Canonical URL
- https://evemisslab.com/ai/theory/THY-2026-0109/
- Machine-readable
/ai/theory/THY-2026-0109/index.json- Snapshot
AI-SNAPSHOT-v0.1-fe85b9694a45- Provenance
source- EveMissLab research collection: Intelligence Physical Metrology (真本體論13)
extracted_by- Splice (Claude Code), reading the canonical UTF-8 sources and each package's own reports
extracted_at- 2026-09-11
generator- tools/extract_all.py
claim_boundary- status, evidence level and result type follow the source artifact's own stated claim boundary; nothing is upgraded beyond what the report supports