How to cite

Plain-text, BibTeX, and Markdown citation patterns for aievals.co, plus the CC BY 4.0 reuse and attribution rules.

How to cite

Cite a specific page when you quote it, paraphrase a non-obvious claim from it, or use its taxonomy in your own work. The site's content license is CC BY 4.0, which requires attribution but allows commercial reuse and derivative work. The code in the public GitHub repository is MIT.

Plain-text citation

Use this shape when a footnote or bibliography is rendered as plain text.

Bharatiya, O. (2026). <Page title>. AI Evals. <URL>

Replace <Page title> with the page's <h1> and <URL> with the canonical URL shown in the address bar.

BibTeX

For papers, RFCs, and academic write-ups.

@misc{bharatiya_aievals_2026,
  title  = {AI Evals},
  author = {Bharatiya, Om},
  year   = {2026},
  url    = {https://www.aievals.co},
  note   = {Content licensed CC BY 4.0}
}

To cite a specific chapter, swap the title, add an explicit url, and keep the same author and year:

@misc{bharatiya_aievals_2026_judge,
  title  = {LLM-as-Judge: Calibration to Humans},
  author = {Bharatiya, Om},
  year   = {2026},
  url    = {https://www.aievals.co/learn/llm-as-judge/calibration-to-humans},
  howpublished = {AI Evals},
  note   = {Content licensed CC BY 4.0}
}

Markdown citation

When linking from a blog post, README, or another markdown document.

> Quoted line from the page.
>
> [Page title](https://www.aievals.co/path/to/page) by Om Bharatiya. AI Evals. CC BY 4.0.

Reuse under CC BY 4.0

The CC BY 4.0 license lets anyone copy, redistribute, remix, transform, and build on the content (including for commercial work) on three conditions: give credit, link the license, and indicate if changes were made. A short attribution line under a quote or above a reused diagram is enough.

If you publish a derivative work (a translation, an expanded chapter, a remix into a slide deck), keep the attribution and a link to the source page. You do not have to release your derivative under the same license, but you do have to credit the original.

Code reuse

The code in the ombharatiya/evals repository is MIT-licensed. Snippets and full files can be lifted into other projects with the standard MIT notice.

AI Evals

The most useful, opinionated reference for AI evals.

AI Evals is a curated technical reference for evaluating large language model systems in production. The site covers error analysis, LLM-as-judge calibration, RAG evaluation, agentic eval, statistical rigor, and twenty task-specific eval playbooks. Every claim is cited.