data-to-paper

data-to-paper supports traceable AI driven scientific research from data.

github.com/Technion-Kishony-lab/data-to-paper
data-to-paper homepage screenshot

About data-to-paper

data-to-paper is an open-source Python automation framework that uses interacting AI and rule-based agents to carry out a research workflow from raw data to a written paper. The stated workflow covers data exploration, literature search, hypothesis generation, data analysis, interpretation, and step-by-step paper writing. Its distinguishing aim is transparency: the generated manuscripts are described as backward-traceable and human-verifiable.

The framework can run fully autonomously or be guided by a person through the Copilot App, where users can set goals, review results, and rewind the process. The project is described as a research project that studies the capacities and limitations of LLM-driven research, so it should be understood as a research tool rather than a finished commercial product. Installation requires the dependencies listed in the project's INSTALL file. Pricing is not stated.

Key features

  • End-to-end pipeline from raw data to a complete research paper.
  • Traces numeric values in manuscripts back to generating code lines.
  • Autopilot mode or human-guided Copilot App operation.
  • Copilot App: set goals, request AI reviews, rewind steps.
  • Records and replays runs; tracks API costs.
  • Overrides standard statistical packages with guardrails against common LLM coding errors.
Best for: Researchers and developers who want to study or run AI-driven research workflows that produce traceable, human-verifiable analysis outputs.
Good for
  • Open source, with the code available in a public GitHub repository.
  • Generated manuscripts can be traced from numeric values to the code that produced them.
  • Users can choose between fully autonomous runs and human-guided operation.
Watch out for
  • Described as a research project studying the limitations of LLM-driven research, not a finished product.
  • Installation requires additional dependencies listed in the INSTALL file.

data-to-paper at a glance

Type
Open-source project
Pricing
Not confirmed. Check the site
Open source
Yes · Source code
Language
English
Last checked
Oct 6, 2026 · Online when checked
Listed
Oct 5, 2026

data-to-paper alternatives

Tools and sites you could use instead, ranked by how closely they match.

All 24 alternatives

Popular in AI Search & Research

Well-known listings from the same topic.

All 125

data-to-paper FAQ

How do I try data-to-paper?
Install it with pip install data-to-paper, then run data-to-paper. The project's INSTALL file lists the dependencies required.
Can a person stay involved in the research process?
Yes. The Copilot App lets users oversee and inspect the research, set goals, request on-demand AI reviews, and rewind the process to earlier steps.
Is something wrong or out of date?

Tell us and an editor will check it.

Own this website?

Claim the listing and suggest updates yourself. An editor checks every claim first.

Claim this listing