experiment-forensics

Featured

Audit experiment integrity against the evidence ledger. At L2 (repo + result files present) a fresh cross-model reviewer reads the eval code line-by-line for fake/derived ground truth, score self-normalization, phantom results (a paper number with no backing file/key), dead/uncalled metric code, verified-scope inflation, method-described ≠ method-evaluated drift, synthesized-looking results, placeholder/fake data still wired into a released result, code-output ≠ reported-number mismatch, and missing reproducibility artifacts (an empirical/agent/LLM paper shipping neither code nor the prompts/configs its results need) — every finding span-anchored to a ledger claim_id. At L0/L1 (PDF / source only) the same patterns are surfaced as info-level 'could-not-verify' signals where the ledger gives an anchor (observability_level_required:2) — NEVER a fraud verdict from a PDF. The reviewer PROPOSES findings; tools/adjudicate_findings.py computes the verdict. Detect-only. Triggers: "experiment forensics", "audit the res

AI & Automation 139 stars 8 forks Updated 3 days ago MIT

Install

View on GitHub

Quality Score: 89/100

Stars 20%
71
Recency 20%
100
Frontmatter 20%
70
Documentation 15%
100
Issue Health 10%
80
License 10%
100
Description 5%
100

Skill Content

# Experiment Forensics — are the reported results what the code computes? Audit experiment integrity for: **$ARGUMENTS** (a paper-dir or repo-dir; use an ABSOLUTE path — it is referred to as `TARGET` below). Emit span-anchored `experiment-forensics.findings.json`. > 🔒 **Do not wrap this skill in `/loop`, `/schedule`, or `CronCreate`.** It is > verdict-bearing input — it proposes the findings the deterministic adjudicator > turns into the report. Re-firing it on a wall-clock timer adds no signal: what > unlocks new conclusions is a higher **observability level** (a repo / result > files arriving → L2), not elapsed time. Schedule the *external wait that precedes > it* — artifacts released → run **once** at the new level. (Mirrors ARIS's > external-cadence doctrine.) > Adapted from ARIS `experiment-audit` (#57/#131), reframed for the reviewer side. > The original audits *your own* experiment before you claim results; this audits a > *third party's* submission. The crucial reframe: at **L0/L1 (no code)** these > patterns are **not decidable** — they appear only as info-level "could-not-verify" > signals. **Code-level fraud requires L2.** A PDF can never produce a fraud verdict. ## Why this exists LLM-driven research pipelines (and rushed human work) produce results that *look* computed but are not what the paper claims. The repeatable failure modes — ported from ARIS's experiment-integrity audit — are: 1. **Fake ground truth** — the eval "reference/target" is *derived from...

Details

Author
wanshuiyin
Repository
wanshuiyin/Anti-Autoresearch
Created
1 months ago
Last Updated
3 days ago
Language
Python
License
MIT

Integrates with

Similar Skills

Semantically similar based on skill content — not just same category

AI & Automation Featured

experiment-audit

Audit experiment integrity before claiming results. Uses cross-model review (external reviewer backend) to check for fake ground truth, score normalization fraud, phantom results, and insufficient scope. Use when user says "审计实验", "check experiment integrity", "audit results", "实验诚实度", or after experiments complete before writing claims.

14,964 Updated today
wanshuiyin
AI & Automation Featured

eval-design-forensics

Audit whether a paper's EVALUATION DESIGN actually measures what it claims and whether its reporting is complete — the validity layer family D (experiment-forensics) cannot reach. Three patterns: train/test leakage means the reported score may not measure generalization (HP-EVAL-LEAKAGE — adopts the Kapoor & Narayanan 8-type / 3-category leakage taxonomy; the illegitimate-proxy / sampling-bias / pretraining-contamination subtypes hand off as needs_external_check, naming but NEVER running Oren-2023 exchangeability / Shi-2023 Min-K% / Golchin-2023 Time-Travel / BIG-bench canary); a load-bearing LLM judge is conflicted (same model/family as a compared system) or unvalidated (no human-agreement, no bias control) (HP-JUDGE-VALIDITY); a declared condition/metric is dropped or switched to favor the method, or 'best' is chosen with no held-out set (HP-SELECTIVE-REPORTING). Verdict-bearing at L0/L1 from the DESCRIBED protocol — NOT repo-gated like experiment-forensics; L2 only CONFIRMS against split/preprocessing/resu

139 Updated 3 days ago
wanshuiyin
AI & Automation Featured

evidence-ledger

Build the deterministic evidence ledger (artifact_manifest.json + claims.json) that every other Anti-Autoresearch auditor reads. One pass inventories artifacts, derives the observability level (L0 PDF-only / L1 +LaTeX / L2 +repo+results) by fixed rule, and extracts span-anchored, hashed, checkable claims (numbers, comparisons, scope, method, baselines, citations, captions, table cells) into claims.json. An OPTIONAL additive cross-model pass ADDS span-anchored semantic claims — method, theorem statements with their assumptions, definitions, proof/derivation steps and equations, scope, baselines, conclusions, the motivation span, and reproducibility-artifact references (the proof, derivation, and structure anchors the family B/D/G auditors need) — it never invents a number, emits a finding, or computes a verdict. Run FIRST, before any audit skill. Triggers: "build the ledger", "extract claims", "prep for integrity audit", "evidence ledger", "建证据账本".

139 Updated 3 days ago
wanshuiyin