Pith. sign in

REVIEW 4 cited by

Ai2 Scholar QA: Organized Literature Synthesis with Attribution

Not yet reviewed by Pith; the record is open.

Re-run · record.json Download PDF Read on arXiv ↗

This paper has not been read by Pith yet. Machine review is queued; the pith claim, tier, and objections will appear here once it completes.

SPECIMEN: schema-true, not a live event

T0 review · schema-true

One-sentence machine reading of the paper's core claim.

pith:XXXXXXXX · record.json · timestamp

arxiv 2504.10861 v2 pith:TZGDTYO3 submitted 2025-04-15 cs.CL

Amanpreet Singh , Joseph Chee Chang , Chloe Anastasiades , Dany Haddad , Aakanksha Naik , Amber Tanaka , Angele Zamarron , Cecile Nguyen
show 10 more authors
Jena D. Hwang Jason Dunkleberger Matt Latzke Smita Rao Jaron Lochner Rob Evans Rodney Kinney Daniel S. Weld Doug Downey Sergey Feldman
This is my paper · ORCID
classification cs.CL
keywords scholarscientificansweringliteraturepublicsystemsaccessiblealong
verification ladder T0 review T1 audit T2 compute T3 formal
0 comments
read the original abstract

Retrieval-augmented generation is increasingly effective in answering scientific questions from literature, but many state-of-the-art systems are expensive and closed-source. We introduce Ai2 Scholar QA, a free online scientific question answering application. To facilitate research, we make our entire pipeline public: as a customizable open-source Python package and interactive web app, along with paper indexes accessible through public APIs and downloadable datasets. We describe our system in detail and present experiments analyzing its key design decisions. In an evaluation on a recent scientific QA benchmark, we find that Ai2 Scholar QA outperforms competing systems.

Discussion (0). Continue with ORCID to comment.

Forward citations

Cited by 4 Pith papers

Reviewed papers in the Pith corpus that reference this work. Sorted by Pith novelty score. Full citation record

  1. Idea2Plan: Exploring AI-Powered Research Planning

    cs.CL 2025-10 conditional novelty 6.0 of 10

    GPT-5 scores 62% on Idea2Plan, a new benchmark that grades AI-generated research plans against rubrics built from 200 post-cutoff ICML 2025 papers — the strongest result, with substantial headroom.

  2. DeepWriter: A Fact-Grounded Multimodal Writing Assistant Based On Offline Knowledge Base

    cs.CL 2025-07 reject novelty 6.0 of 10

    DeepWriter is a pipeline that generates fact-grounded, multimodal long-form documents from a curated offline knowledge base, but the reported evidence does not support the abstract's claim that it surpasses baselines.

  3. Compare: A Framework for Scientific Comparisons

    cs.DL 2025-09 conditional novelty 5.0 of 10

    Compare is a RAG-based system that generates qualitative, citation-supported comparisons of scientific contributions at institution and publication granularity.

  4. Literature-Grounded Novelty Assessment of Scientific Ideas

    cs.IR 2025-06 conditional novelty 5.0 of 10

    An LLM retrieval-augmented system that judges whether a research idea is novel by comparing it against reranked relevant papers and expert-labeled examples.

Pith tools