# chiphuyen/sotawhat

Returns latest research results by crawling arxiv papers and summarizing abstracts. Helps you stay afloat with so many new papers everyday.

Repository: https://github.com/chiphuyen/sotawhat
Canonical: https://ross.abutalabs.com/products/sotawhat
Homepage: https://huyenchip.com/2018/10/04/sotawhat.html
Language: Python
License Family: other
Topics: script, python, arxiv, summarization, research-tool
Last push: 2024-02-02T04:30:15+00:00

## Health v2 (maintenance only)
Score: 23/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 8, longevity 100
- inputs: {"age_days": 2892, "days_push": 943, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1418, forks 189 (observed 2026-08-28T04:04:40.265215+00:00)

## What it is
A Python CLI script that crawls arXiv for papers matching a keyword and returns summarized abstracts with title, author, date, and link. It prioritizes abstracts containing numbers to surface the latest state-of-the-art results.

## Use cases
- find the latest state-of-the-art results for a research topic
- search arxiv papers by keyword from the terminal
- summarize paper abstracts containing benchmark numbers
- track new papers on a model, dataset, task, or metric
- keep up with daily AI research output

## When to choose
- you want quick terminal-based arXiv lookups with number-focused summaries
- you need to check current SOTA results for a keyword without browsing arXiv

## When to avoid
- you need a full-featured paper search or citation analysis
- you need a maintained library with a license and active development
- you need a GUI or web-based research discovery tool

## Facets
- artifact type: cli-tool
- maturity: maintenance
- function: web-scraping, nlp, search-engine, cli
- domain: artificial-intelligence, developer-tools
- platform: python, cli, cross-platform
- tags: arxiv, summarization, research-tool, state-of-the-art, papers, natural-language-processing, research, command-line

## Member repositories
- chiphuyen/sotawhat (main) score 23

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:40.265215+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T04:37:56.329050+00:00, confidence not recorded.
  - readme: https://github.com/chiphuyen/sotawhat (fetched 2026-08-28T04:04:40.265215+00:00, sha ab44deba3267)
  - homepage: https://huyenchip.com/2018/10/04/sotawhat.html (fetched 2026-08-29T11:50:21.826101+00:00, sha fa1caee55450)
- Data as of 2026-08-30T08:39:29.467469+00:00.