A public research experiment
The paper stops being the point.
A datasetpaper is a versioned, forkable, executable research object built on an open dataset.
The data, the code, the environment, the figures, and each individual claim are all addressable.
The written narrative is just one view of it. Built to be verified, cited, and forked, by people and by AI agents.
This is an experimental prototype, not a finished product or service.
Not a data descriptor. A data paper describes a dataset and omits the analysis on purpose.
A datasetpaper is the analysis: hypotheses, methods, results, and claims, made machine-readable and forkable.
Read one
Every datasetpaper is also a story
Same claims, same data, same provenance — rendered as an evidence-linked, multimodal article instead of a paper.
Charts, images, interactives, and a click-through evidence viewer on every sentence.
Browse all data stories →
Why now
Generating an analysis and its write-up is no longer the hard part. That changes what is valuable.
If anyone can produce a plausible analysis in minutes, plausibility is worthless, and the scarce thing is trust:
knowing which claim was re-executed from the data and which was merely asserted.
datasetpapers explores how verification and provenance can become the centre of the research object.
The prose is a by-product.
The object has parts, and every part is addressable
Because the parts are addressable, an agent can build on one claim without parsing a whole document,
and a person can cite a single figure with a stable identifier.
Dataset
Referenced and pinned to a version. Never silently updated. Retraction propagates to everything derived from it.
Code and environment
A notebook plus a pinned container and lockfile, so the analysis re-runs deterministically, not approximately.
Figures and tables
Each one points back to the exact code that produced it, so no result is orphaned from its computation.
Claims
Atomic statements, individually citable and machine-checkable, each carrying the figures that support it.
Provenance
A graph tying every output back to the data, and recording whether a human or an AI produced each step.
Narrative
Compiled from the object, not hand-edited. Available as a web page, a PDF, or structured XML.
How it works, in plain steps
- 1 Start from an open dataset, pinned to a version so results are reproducible.
- 2 Ask a question the dataset can answer, and check it is not a restatement of something already known.
- 3 Run the analysis in a captured environment, so the exact computation can be re-run later.
- 4 Break the result into parts: data, code, environment, figures, claims, and provenance.
- 5 Pass it through a gate that scores novelty, checks integrity, and runs an adversarial review before publishing.
- 6 Give it persistent identifiers and publish it in formats both people and machines can read.
- 7 Let others verify individual claims, and let anyone fork the whole thing to ask a new question.
Agent access
Connect to the live machine-readable corpus
Agents can use ten open read tools at https://datasetpapers.com/mcp, or fetch the public
JSON, RO-Crate, claims, and verification files directly. The agent guide has connection configuration,
prompt examples, the complete tool list, and trust guidance.
Current status
Static and hosted MCP reads are live. Allowlisted writes create private jobs; the separate generation runner is not connected.
Static read access · live
Fetch the corpus index, complete research objects, claim graphs, RO-Crates, and independent re-execution records over ordinary HTTPS.
Hosted MCP · live
Add https://datasetpapers.com/mcp as a Streamable HTTP server. Read tools need no key or account.
Trust travels with the claim
Check the independent re-execution record before relying on a claim. Engine self-reports and independent verification are not the same thing.
Writes and forking · gated
Allowlisted collaborators can queue proposals, forks, and verification evidence. A queued job is not an executed or published result.
Open the agent & MCP guide →
In concrete terms, datasetpapers builds on open datasets from repositories such as Figshare and Zenodo,
credits their depositors via ORCID, packages each result as an RO-Crate with a Croissant dataset description,
mints persistent ARK identifiers, and passes new work through an adversarial review gate before publishing.
Credit where it is due
Every datasetpaper starts from someone's dataset. datasetpapers records that debt explicitly,
notifies the original depositor that their data was used, and gives them a first-class place in the credit graph.
The people who share data have been under-credited for as long as data sharing has existed.
A world where machines analyse open data at scale makes that worse unless credit is designed in. Here it is.
What we are asking people to do
Read a datasetpaper the way you would read a pull request, not a journal article.
Check the claims you care about. Fork it if you can do better. Bring your dataset if you want it analysed.
Treat it as a starting point that is honest about its own uncertainty, not a finished verdict.
Questions, answered
Is datasetpapers a product?
No. It is a public research experiment and working prototype, not a commercial product or service. Its interfaces, methods, and outputs may change. Independently verify an analysis before relying on it for research or decisions.
What is a datasetpaper?
A datasetpaper is a versioned, forkable, executable research object built on an open dataset. Its data, code, environment, figures, and individual claims are each addressable, and the written narrative is one rendered view of it. It is built to be verified, cited, and forked by people and by AI agents.
How is a datasetpaper different from a data paper?
A data paper describes a dataset and deliberately omits the analysis. A datasetpaper is the analysis itself — hypotheses, methods, results, and claims — made machine-readable and forkable.
Who is datasetpapers for?
Researchers who want to build on open data, data depositors who want credit when their data is reused, and AI agents that need machine-readable, verifiable analyses to build on.
How can AI agents use datasetpapers?
Agents can connect to the live hosted MCP at https://datasetpapers.com/mcp or read the corpus over ordinary HTTPS. The agent guide provides configuration, prompt examples, tool behavior, and the deliberately limited write path.
What does datasetpapers build on?
It builds on open datasets from repositories such as Figshare and Zenodo, credits depositors via ORCID, packages each result as an RO-Crate with a Croissant dataset description, mints persistent ARK identifiers, and passes new work through an adversarial review gate before publishing.
