experiment-audit skill

Experiment Audit: Cross-Model Integrity Verification

🔒 Do not wrap this skill in /loop, /schedule, or CronCreate. It is

verdict-bearing — it judges experiment integrity. Re-running that verdict on a

timer adds no new signal, and a loop that accepts its own output to decide

when to stop crosses into self-acquittal (acceptance-gate.md). Schedule the

external wait that precedes it — experiments done → then audit once. See

shared-references/external-cadence.md.

Audit experiment integrity for: $ARGUMENTS

Why This Exists

LLM agents can produce fraudulent experimental results through:

1. Fake ground truth — creating synthetic "reference" from model outputs, then reporting high agreement as performance
2. Score normalization — dividing metrics by the model's own max to get 0.99+
3. Phantom results — claiming numbers from files that don't exist or functions never called
4. Insufficient scope — reporting 2-scene pilots as "comprehensive evaluation"

These are NOT intentional deception — they are failure modes of optimizing agents that lack integrity constraints. This skill adds that constraint.

Core Principle

The executor collects file paths. The external reviewer backend reads code and judges integrity. The executor does NOT participate in integrity judgment.

This follows shared-references/reviewer-independence.md and shared-references/experiment-integrity.md.

Constants

• REVIEWERBACKEND = codex** — Default: Codex MCP (ultra). Override with — reviewer: oracle-pro for Oracle MCP, or — reviewer: manual for Manual Review MCP. If manual-review MCP is unavailable, stop and print the install command; do not fall back to Codex. See shared-references/reviewer-routing.md.

Reviewer Calling Convention

When calling the reviewer, branch on REVIEWER_BACKEND:

If REVIEWERBACKEND = codex: Use mcpcodexcodex for new review threads. Use mcpcodex__codex-reply for follow-up rounds (reuse threadId).

If REVIEWERBACKEND = manual: Use mcpmanualreviewreview for new review threads with: prompt: [exact same prompt that would go to Codex] config: {"modelreasoningeffort": "xhigh", "executormodel": "", "requirereviewermodel": true} Save the returned threadId. Use mcpmanualreviewreviewreply for follow-up rounds with: threadId: [saved manual-review threadId] prompt: [follow-up prompt] config: {"modelreasoningeffort": "xhigh", "executormodel": "", "requirereviewermodel": true}

Prompt fidelity: the manual prompt must be exactly the same text that Codex would receive. Review tracing applies equally to both backends.

Workflow

Step 1: Collect Artifacts (Executor — Claude)

Locate and list these files WITHOUT reading or summarizing their content:

Scan project directory for:
1. Evaluation scripts:    *eval*.py, *metric*.py, *test*.py, *benchmark*.py
2. Result files:          *.json, *.csv in results/, outputs/, logs/
3. Ground truth paths:    look in eval scripts for data loading (dataset paths, GT references)
4. Experiment tracker:    EXPERIMENT_TRACKER.md, EXPERIMENT_LOG.md
5. Paper claims:          NARRATIVE_REPORT.md, paper/sections/*.tex, PAPER_PLAN.md
6. Config files:          *.yaml, *.toml, *.json configs with metric definitions

A verdict-bearing manual response MUST begin with Reviewer-Model: — pass the model THIS session is actually running as in executormodel. Missing, unknown, or same-family identity cannot acquit; emit REVIEWUNAVAILABLE rather than guessing. If the executor model cannot be named, manual review's cross-family claim is unprovable — say so in the report instead of asserting it.

DO NOT summarize, interpret, or explain any file content. Only collect paths.

Step 2: Send to Reviewer

Based on the selected reviewer backend (see Reviewer Calling Convention), pass ONLY file paths and the audit checklist to the reviewer. The reviewer reads everything directly.

For codex, call mcpcodexcodex with:

• model: gpt-6-astra
• config: {"modelreasoningeffort": "ultra"}
• sandbox: read-only
• cwd: [project directory]
• prompt: [the exact full prompt below]

For manual, call mcpmanualreview__review with:

• config: {"modelreasoningeffort": "xhigh", "executormodel": "", "requirereviewer_model": true}
• prompt: [the exact full prompt below]

Manual review cannot use Codex-only model, sandbox, or cwd; include the same file paths in the prompt so the user can inspect them.

Use this exact prompt for both backends:

You are an experiment integrity auditor. Start from the assumption that the
    evaluation is compromised somewhere — your job is to find where. Be
    adversarial. Trust nothing the author tells you — verify everything
    yourself. Read ALL files listed below and check for the following fraud
    patterns.

    Files to read:
    - Evaluation scripts: [list paths]
    - Result files: [list paths]
    - Experiment tracker: [list paths]
    - Paper claims: [list paths]
    - Config files: [list paths]

    ## Audit Checklist

    ### A. Ground Truth Provenance
    For each evaluation script:
    1. Where does "ground truth" / "reference" / "target" come from?
    2. Is it loaded from the DATASET, or generated/derived from MODEL OUTPUTS?
    3. If derived: is it explicitly labeled as proxy evaluation?
    4. Are official eval scripts used when available for this benchmark?
    FAIL if: GT is derived from model outputs without explicit proxy labeling.

    ### B. Score Normalization
    For each metric computation:
    1. Is any metric divided by max/min/mean of the model's OWN output?
    2. Are raw scores reported alongside any normalized scores?
    3. Are any scores suspiciously 

Step 3: Parse and Write Report (Executor — Claude)

Parse the reviewer's response and write EXPERIMENT_AUDIT.md:

# Experiment Audit Report

**Date**: [today]
**Auditor**: External reviewer backend, ultra reasoning (cross-model, read-only)
**Project**: [project name]

## Overall Verdict: [PASS | WARN | FAIL]

## Integrity Status: [pass | warn | fail]

## Checks

### A. Ground Truth Provenance: [PASS|WARN|FAIL]
[details + file:line evidence]

### B. Score Normalization: [PASS|WARN|FAIL]
[details]

### C. Result File Existence: [PASS|WARN|FAIL]
[details]

### D. Dead Code Detection: [PASS|WARN|FAIL]
[details]

### E. Scope Assessment: [PASS|WARN|FAIL]
[details]

### F. Evaluation Type: [real_gt | synthetic_proxy | ...]
[classification + evidence]

## Action Items
- [specific fixes if WARN or FAIL]

## Claim Impact
- Claim 1: [supported | needs qualifier | unsupported]
- Claim 2: ...

Also write EXPERIMENT_AUDIT.json for machine consumption:

{
  "date": "2026-04-10",
  "auditor": "external-reviewer-ultra",
  "overall_verdict": "warn",
  "integrity_status": "warn",
  "checks": {
    "gt_provenance": {"status": "pass", "details": "..."},
    "score_normalization": {"status": "warn", "details": "..."},
    "result_existence": {"status": "pass", "details": "..."},
    "dead_code": {"status": "pass", "details": "..."},
    "scope": {"status": "warn", "details": "..."},
    "eval_type": "real_gt"
  },
  "claims": [
    {"id": "C1", "impact": "supported"},
    {"id": "C2", "impact": "needs_qualifier"}
  ]
}

Step 4: Print Summary

🔬 Experiment Audit Complete

  GT Provenance:      ✅ PASS — real dataset GT used
  Score Normalization: ⚠️ WARN — boundary metric uses self-reference
  Result Existence:    ✅ PASS — all files exist, numbers match
  Dead Code:           ✅ PASS — all metric functions called
  Scope:               ⚠️ WARN — 2 scenes, paper says "comprehensive"

  Overall: ⚠️ WARN
  
  See EXPERIMENT_AUDIT.md for details.

Integration with Other Skills

Automatic in /research-pipeline (advisory, never blocks)

When integrated into the pipeline, this skill runs automatically after /experiment-bridge and before /auto-review-loop:

/experiment-bridge → results ready
    ↓
/experiment-audit (automatic, advisory)
    ├── PASS  → continue normally
    ├── WARN  → print ⚠️ warning, continue, tag claims as [INTEGRITY: WARN]
    └── FAIL  → print 🔴 alert, continue, tag claims as [INTEGRITY CONCERN]
    ↓
/auto-review-loop → proceeds with integrity tags visible to reviewer

Never blocks the pipeline. Even on FAIL, the pipeline continues — but claims carry visible integrity tags.

Read by /result-to-claim (if exists)

if EXPERIMENT_AUDIT.json exists:
    read integrity_status
    attach to verdict: {claim_supported: "yes", integrity_status: "warn"}
    if integrity_status == "fail":
        downgrade verdict display: "yes [INTEGRITY CONCERN]"
else:
    verdict as normal, integrity_status = "unavailable"
    mark as "provisional — no integrity audit"

Read by /paper-write (if exists)

if EXPERIMENT_AUDIT.json exists AND integrity_status == "fail":
    add footnote to affected claims: "Note: integrity audit flagged concerns with this evaluation"

Key Rules

• Reviewer independence: executor collects paths, reviewer judges. Period.
• Never block: warn loudly, never halt the pipeline.
• File-as-switch: no EXPERIMENT_AUDIT.md = skill was never run = zero impact on existing behavior.
• Cross-model: the reviewer MUST be a different model family from the executor.
• Honest about limits: the audit catches common patterns, not all possible fraud. It is a safety net, not a guarantee.

Acknowledgements

Motivated by community-reported integrity issues (#57, #131) where executor agents created fake ground truth and self-normalized scores.

Review Tracing

After each reviewer call (mcpcodexcodex, mcpcodexcodex-reply, mcpmanualreviewreview, or mcpmanualreviewreviewreply), save the trace following shared-references/review-tracing.md (Policy C — forensic; never silently skip). Use savetrace.sh (resolved per the chain in shared-references/integration-contract.md §2) or write files directly to .aris/traces//_run/. Respect the --- trace: parameter (default: full).