paperlab-reference-dataset-curation skillA
paperlab-reference-dataset-curation is agent-read markdown (skill) from equinor/neqsim: Curate reference datasets for PaperLab validation, including source tracing, unit normalization, uncertainty notes, license status, and citation mapping..
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
# PaperLab Reference Dataset Curation
## When to Use
USE WHEN: extracting literature or benchmark data into files that support paper
claims, book examples, or regression baselines.
## Dataset Manifest Fields
```json
{
"dataset_id": "co2_water_solubility_2024",
"source_citation_key": "Author2024",
"source_type": "paper_table",
"extraction_method": "manual_table_transcription",
"original_units": {"temperature": "C", "pressure": "MPa"},
"normalized_units": {"temperature": "K", "pressure": "bara"},
"uncertainty": "reported standard deviation where available",
"license_or_use_note": "cite only; do not redistribute full source text",
"files": ["reference_data/co2_water_solubility_2024.csv"]
}
```
## Workflow
1. Identify source and citation key.
2. Extract only the data needed for validation.
3. Preserve original units and normalize into a separate column or metadata field.
4. Add uncertainty and data-quality notes.
5. Link each dataset to hypotheses, figures, and claims.
## Pass Criteria
- Every numeric column has a unit.
- Every dataset has a citation and extraction method.
- Public outputs avoid restricted source text.
## Safety Rules
…Read the whole file at its exact version.
How to install
mdr add equinor/neqsim/paperlab-reference-dataset-curation@git:20260919.77c34a0mdr add equinor/neqsim/paperlab-reference-dataset-curation@sha256:776548e4c51310a0Pin 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_7vvk6jasldiruwey)
1 badge views in 30 days
Versions
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 (1618 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
equinor/neqsim · 155 stars · license Apache-2.0 · pushed 2026-09-24 · branch master
API
GET https://markdownregistry.com/api/v1/artifacts/art_7vvk6jasldiruwey GET https://markdownregistry.com/api/v1/resolve?ref=equinor/neqsim/paperlab-reference-dataset-curation GET https://markdownregistry.com/api/v1/blob/776548e4c51310a07eee181d2be7294af8866b14ee23282de7d83cda06c87fff
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.