experiment-forensics skillA
experiment-forensics is agent-read markdown (skill) from wanshuiyin/anti-autoresearch: 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 mis.
Indexed from public GitHub and served as immutable, content-addressed versions. Install it pinned to an exact SHA-256 with the mdr CLI, and every file is verified against the hash recorded here before it reaches your agent. The deterministic audit below grades the latest version, and the same file always earns the same grade.
How to install
mdr add wanshuiyin/anti-autoresearch/experiment-forensics@git:20260810.98a75fcmdr add wanshuiyin/anti-autoresearch/experiment-forensics@sha256:fdeb56ec8ffc445ePin to a label to follow the author's releases, or to a sha256 to freeze the exact bytes forever. Either way the resolved hash is written to mdr.lock, and mdr install reproduces it on any machine.
[](https://markdownregistry.com/a/art_7oqrcow4n5kco5h2)
0 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260810.98a75fc latest | 2026-08-10 | 98a75fc | 52,773 B | A | view · diff |
| git:20260810.94439ad | 2026-08-10 | 94439ad | 52,762 B | A | view · diff |
| git:20260710.16f7480 | 2026-07-10 | 16f7480 | 52,762 B | A | view · diff |
| git:20260710.a1a963f | 2026-07-10 | a1a963f | 52,428 B | A | view · diff |
| git:20260628.b35080d | 2026-06-28 | b35080d | 52,215 B | A | view |
Audit of the latest version
- pass: Frontmatter block present
- pass: Frontmatter declares a name
- pass: Frontmatter declares a description
- pass: Size between 200 bytes and 200 KB (52773 bytes)
- pass: No zero-width or bidi control characters
- pass: No instruction hidden inside an HTML comment
- pass: No link to an exfiltration or paste host
- pass: No credential-shaped string
- pass: No instruction to send local credentials anywhere
- pass: No text hidden with inline styles
- pass: No prompt-injection phrasing
- pass: No curl or wget piped into a shell
- pass: No recursive delete of root, home or parent
- pass: No instruction to read or print local credentials
- pass: No base64 blob over 200 characters
- pass: No link to a raw IP address
- pass: No script tag
Source
wanshuiyin/anti-autoresearch · 154 stars · license MIT · pushed 2026-09-09 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7oqrcow4n5kco5h2 GET https://markdownregistry.com/api/v1/resolve?ref=wanshuiyin/anti-autoresearch/experiment-forensics GET https://markdownregistry.com/api/v1/blob/fdeb56ec8ffc445eb7f68ca87fc79c1a5477ac0d000a8a22f85f50672bede3d7
Agents talk at modelranch.com: hand yours the instructions there and it joins the network that reads files like this one.