artifact-detection skillA
artifact-detection is agent-read markdown (skill) from yogsoth-ai/de-anthropocentric-research-engine: Detect annotation artifacts and shortcuts in benchmarks.
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.
What the file says
# Artifact Detection Tactic Systematically probe benchmarks for annotation artifacts, dataset shortcuts, and spurious correlations that allow models to achieve high scores without the intended capability. ## Stages ### Stage 1: Hypothesis-Only Baseline Test Search literature for evidence that partial-input baselines achieve unexpectedly high performance: - Hypothesis-only baselines (NLI without premise) - Question-only baselines (QA without context) - Label-word frequency baselines - Majority-class and surface-pattern baselines **Search queries**: "[benchmark] annotation artifacts", "[benchmark] hypothesis only", "[benchmark] spurious correlations", "[benchmark] dataset bias" If published partial-input results exist, record performance gap between partial and full input. Gap < 10 points above random indicates severe artifacts. ### Stage 2: Contrast Set Construction Identify whether contrast sets or adversarial evaluations exist: - Search for "[benchmark] contrast sets", "[benchmark] adversarial examples" - Check if CheckList-style behavioral tests have been applied - Look for counterfactual data augmentation studies …
Read the whole file at its exact version.
How to install
mdr add yogsoth-ai/de-anthropocentric-research-engine/artifact-detection@git:20260615.7a62936mdr add yogsoth-ai/de-anthropocentric-research-engine/artifact-detection@sha256:a4fc474451467404Pin 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_7szej6pj2lcdxpfi)
1 badge views in 30 days
Versions
| version | committed | commit | size | audit | |
|---|---|---|---|---|---|
| git:20260615.7a62936 latest | 2026-06-15 | 7a62936 | 3,076 B | A | view · diff |
| git:20260519.dc15fe2 | 2026-05-19 | dc15fe2 | 3,107 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 (3076 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
yogsoth-ai/de-anthropocentric-research-engine · 498 stars · license Apache-2.0 · pushed 2026-09-17 · branch main
API
GET https://markdownregistry.com/api/v1/artifacts/art_7szej6pj2lcdxpfi GET https://markdownregistry.com/api/v1/resolve?ref=yogsoth-ai/de-anthropocentric-research-engine/artifact-detection GET https://markdownregistry.com/api/v1/blob/a4fc4744514674042cdbaafe211a4babf0f0fb79339ca9c0b700b6bc647d5453
Your agent does the legwork. You hear about the deals worth your word. Hand yours the standing instructions at modelranch.com and it joins the network that reads files like this one.