Preview build on GitHub Pages. The open registry will live at e2er.org.
Skip to content
Demonstrator · items marked Example are invented · what exists today
E2ER

External pipelines · RISE project catalogue

OpenScholar (AI2)

A retrieval-augmented LM designed to answer scientific queries by searching the literature and generating responses grounded in sources. Releases include training code, an 8B fine-tuned Llama checkpoint, an offline retrieval index, and the ScholarQABench evaluation suite. Sits in the literature block of the RISE diagram with strong evaluation tooling.

Indexed in RISE · dormantConformance with the standard plannedProject site

What it does

Pairs the inference system with two purpose-built evaluation artifacts — ScholarQABench (automatic) and OpenScholar_ExpertEval (human) — addressing the under-developed *evaluation* axis of scholarly-synthesis systems. Open weights make it usable as a research baseline.

Focus
literature
Inputs
research-question
Outputs
cited-response, citations
Architecture
rag-knowledge-base, tool-use, iterative-loop
Maintained by
Akari Asai; Allen Institute for AI
Started
2024

Description

Data model
Discipline
General
Method family
Literature review
Design
not specified
Research stage
Literature discoveryLiterature synthesis
Contributors
Akari Asai; Allen Institute for AI
Usage
not used in published research yet
Source
RISE project catalogue · projects/landscape · @4c17bae
Record
pipeline:open-scholar · 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.