External pipelines · RISE project catalogue
data-to-paper
An end-to-end framework that takes annotated data and produces *backward-traceable* scientific manuscripts: every numeric value in the output can be click-traced to the specific code line that generated it. Navigates interacting LLM and rule-based agents through data exploration, literature search, hypothesis raising, code-debugging, interpretation, and step-by-step paper writing. Released alongside an NEJM AI peer-reviewed paper (Ifargan et al., 2024 — DOI:10.1056/AIoa2400555).
Where it sits
left: what it builds on · right: what builds on it · pale: exampleContributed by Roy Kishony Lab
How studies reach it
No published study reaches it yet.
Disciplines it reaches
No study reaches it yet.
Solid: published studies. Light: examples.
Computed from the records on this site: what each study, template and specialist names as used, which study extends which, and who contributed what. 0 studies in total.
What it does
The "data-chained" provenance design is unique in the catalog: the manuscript is constructed so that traceability is intrinsic, not a reporting add-on — any reported number resolves backward through the data analysis steps. Ships both Autopilot and Copilot modes (oversee / inspect / guide / rewind / replay) and overrides standard statistical packages with coding guardrails to minimize common LLM coding errors.
- Focus
- end-to-end
- Inputs
- annotated-dataset, research-goal
- Outputs
- traceable-manuscript, data-chained-paper, code
- Architecture
- multi-agent, human-in-loop, tool-use, artifact-versioning, dag-orchestration
- Maintained by
- Roy Kishony Lab (Technion)
- Started
- 2023
Description
Data model- Discipline
- General
- Method family
- not specified
- Design
- not specified
- Research stage
- HypothesesLiterature discoveryResearch designData analysisCode generationDraftingRevision and editing
- Contributors
- Roy Kishony Lab
- Usage
- not used in published research yet
- Source
- RISE project catalogue · projects/landscape · @4c17bae
- Record
- pipeline:data-to-paper · JSON
Solid tags are declared by the source or mapped from its terms; dashed tags are inferred by a published rule. Hover a tag for its provenance.
Bring it into the standard
A pipeline built outside E2ER can meet the standard by describing its steps as a template, attaching the floor of checks and publishing evaluation records. Its authors keep ownership and credit.