Skip to main content

    The NIL Sideline Report

    Why RevU uses the CUAD taxonomy (and what that means for your contract)

    Most contract-analysis products invent their own clause categories, which no one can audit, and cite accuracy numbers no one can verify. RevU is built on the CUAD taxonomy, a 41-class standard The Atticus Project published in 2021. This post explains what CUAD is, why we chose it, what it means for athletes reading their contracts, and what we added on top of it.

    By Max Rusakov, Co-Founder & CEO, RevU

    NIL market analyst · MS in Management, SMU

    Published May 18, 2026Updated November 11, 202612 min read

    Most contract-analysis products do something that raises a problem for anyone who has to rely on them: they invent their own clause categories, train an AI model against those categories, and then publish accuracy numbers (sometimes the famous "95% accuracy") without ever showing how the categories were defined, how the ground truth was constructed, or what "accuracy" actually measured. The result is a black-box system citing self-graded results against a private rubric.

    RevU was built on the opposite premise. Our clause categories are based on the CUAD taxonomy, a 41-clause schema that The Atticus Project developed in 2021 and published as a public dataset of expertly-annotated commercial contracts. This post explains what CUAD is, why we chose it as the foundation, what limits it has, and what we built on top of it to fit NIL contracts specifically.

    What CUAD is

    CUAD stands for Contract Understanding Atticus Dataset. It is a corpus of 510 commercial contracts, expert-annotated for 41 categories of clauses that contract attorneys care about most. The categories were chosen by a team of attorneys at Atticus, refined over multiple rounds of annotation, and validated against industry usage. The dataset and benchmarks were published openly in 2021 (arXiv 2103.06268) and have become the de facto standard against which legal-NLP clause-classification systems are evaluated.

    The 41 categories are the familiar contract clauses that show up over and over in commercial agreements: anti-assignment, audit rights, cap on liability, change of control, competitive restriction, covenant not to sue, effective date, exclusivity, expiration date, governing law, ip ownership assignment, insurance, joint ip ownership, license grant, liquidated damages, minimum commitment, most favored nation, no-solicit of customers, no-solicit of employees, non-compete, non-disparagement, non-transferable license, notice period to terminate renewal, post-termination services, price restrictions, renewal term, revenue/profit sharing, rofr/rofo/rofn, source code escrow, termination for convenience, third party beneficiary, uncapped liability, unlimited/all-you-can-eat-license, volume restriction, warranty duration, and a handful of others.

    Why a public taxonomy matters

    When the underlying taxonomy is published openly, several things follow that don't follow with a proprietary one.

    First, the categories are reviewable. RevU's clause categories are based on CUAD's, and each CUAD category has a public definition. If you want to know what "non-compete" means, you can read the CUAD documentation rather than relying on us to define it consistently.

    Second, there is a shared yardstick. CUAD has a public test set with annotated ground truth, and multiple academic and commercial systems have published F1 results against it, so the field agrees on what clause classification is measured against. RevU has not published a result of its own.

    Third, the work is reusable. RevU's NIL-specific clause types sit on top of the same schema, so if a future research group publishes an updated CUAD release, our taxonomy can extend cleanly with it, which a proprietary schema that no external work uses could never do.

    Why we chose CUAD specifically

    Of the academic taxonomies available, CUAD is the largest, most expert-annotated, and most clause-focused. Earlier datasets like LEDGAR are organized at the document level (what kind of contract is this?) rather than the clause level (what does this specific paragraph do?). Datasets focused on specific industries (real estate, employment) are too narrow for general contract analysis. CUAD is industry-agnostic, written by lawyers, and granular enough to drive a clause-by-clause review.

    The other option was to invent our own taxonomy. We rejected it for two reasons. First, inventing a new schema would let us optimize for marketing claims by defining the categories as the ones we are good at and ignoring the rest. That's exactly the criticism leveled at proprietary contract-analysis products. Second, NIL is changing fast enough that any taxonomy built for it would be obsolete within a year; building on an industry-agnostic foundation lets us add NIL-specific categories incrementally without re-architecting.

    What CUAD does not cover (and what we added)

    CUAD is industry-agnostic, which is exactly the point and also a limitation. NIL contracts contain clause types that don't fit cleanly into any CUAD category. We have built additional clause categories on top of CUAD specifically for NIL work, and we treat the additions as transparent extensions to the base taxonomy.

    Examples of NIL-specific clause categories we have added:

    Morality clause structure. CUAD has a generic "termination for cause" category but does not separate out morality language. Our engine looks at morality language on its own: what triggers it, who decides, and what the athlete would lose (our morality clause post walks through the common settings).

    Disclosure-and-compliance clause. CUAD does not have a dedicated category for clauses that govern the athlete's obligations to disclose the contract to school compliance, NIL Go, the FTC, etc. We added this category and built the cross-checks that fire when a contract's disclosure language conflicts with the controlling state regime.

    NCAA compliance representations. School-direct contracts and NIL Go-routed contracts now commonly include representations and warranties about compliance with NCAA rules, the House settlement, and applicable state NIL law. CUAD has a generic "representations and warranties" category; we sub-classified the NIL-specific variants.

    Dollar amounts. Beyond clause classification, RevU reads every dollar amount in the contract and labels what it pays for (base, bonus, signing, royalty, etc.). This is independent of CUAD and is described on our methodology page.

    What this means for athletes reading the output

    RevU's findings use plain-English topic labels rather than CUAD's names, but the categories underneath are based on CUAD's public ones. When a finding is about who owns the content you make, for example, the matching CUAD category is "IP Ownership Assignment". You don't have to take our word for what the category means. You can look it up, read the definition, find example clauses from the CUAD dataset, and form your own view about how the language in your specific contract fits.

    This matters because contract analysis, ultimately, is decision support. The engine surfaces categories and patterns; the human reading the output decides what to do about them. The more the categories are defined transparently, the easier it is to reason about whether the engine's classification is correct in any given case. A proprietary "AI risk rating" is much harder to check, override, or question than a structured clause-level report grounded in published categories.

    How CUAD fits with what RevU flags

    CUAD is a classification taxonomy. It tells you what a clause is; whether that clause is good or bad for you is a separate question.

    For the clauses it looks at, RevU's engine asks the questions an athlete's representative would: how each side can end the deal and whether both get the same rights, what a conduct clause counts and who decides, how long your name and image can be used and whether that use stops when the deal ends. When a clause is worth a closer look, the finding quotes it word for word, names the section, and frames the concern as questions for your agent, attorney or school. The methodology page lists what the analysis looks for.

    The separation matters: if you disagree with a finding, you can point to the quoted clause and the category it sits in, and have a specific conversation about it.

    On the question of "accuracy"

    We have publicly committed to not advertising aggregate "accuracy" numbers (e.g., "95% accurate") because the metric is misleading without specification of the test set, the F1 versus exact-match threshold, the clause-category breakdown, and the contract-type breakdown. RevU does not publish an accuracy figure; the methodology page describes what the analysis looks for and its known limits.

    For the curious: the academic side

    If you want the underlying research, the foundational CUAD paper is Hendrycks et al., "CUAD: An Expert-Annotated NLP Dataset for Legal Contract Review," published on arXiv in 2021. The dataset itself is available on GitHub under a permissive license. The Atticus Project, which led the annotation effort, maintains a public website with documentation. Multiple follow-up papers in the legal-NLP literature have improved on the CUAD baseline; the field is active and the techniques are still advancing.

    The transparency commitment

    Building on CUAD is part of a broader commitment we have made about how RevU operates. The methodology page covers the public CUAD taxonomy, how RevU reads compensation and one-sided or morality clauses in plain terms, what it does not do, and its known limits. The 10-point checklist and the 8-pattern post are the human-readable counterparts to what the engine does mechanically. The goal is output that holds up when a sports-law attorney scrutinizes it.

    If you ever see RevU classify a clause in a way that doesn't match how a contract attorney would describe the same clause, we want to hear about it. Email info+support@revu.deals with the contract excerpt and our output, and we'll log it as a benchmark case. CUAD is a public taxonomy; our application of it is meant to be defensible at the same level of scrutiny.

    Get help

    RevU explains what a contract says. It does not tell you whether to sign it or what to change. Someone who can see your whole deal can answer that:

    • An agent, if you have one. An agent knows your other deals and what you are trying to do.
    • An attorney. A lawyer can give you legal advice about this contract. Your state bar runs a lawyer referral service, and some law schools run free NIL clinics.
    • Your school's compliance office. It is free to use, and it knows what your school, your state and NIL Go require.

    Sources

    1. CUAD: An Expert-Annotated NLP Dataset for Legal Contract ReviewHendrycks et al., arXiv, arXiv:2103.06268
    2. The Atticus Project — CUAD dataset and documentationThe Atticus Project

    About the author

    Max Rusakov

    Co-Founder & CEO, RevU

    Max leads operations and partnerships at RevU and publishes the NIL Sideline Report. He works daily on NIL deal structures, state statutes, and the NCAA/House settlement framework, and writes RevU's coverage of the NIL market and its regulation.

    • Co-Founder & CEO of RevU
    • Publisher of the NIL Sideline Report, covering the college-athlete NIL market
    • MS in Management, Southern Methodist University
    • Focus areas: NIL deal structures, state NIL statutes, NCAA/House settlement framework

    Referenced in this post

    Related posts

    Browse all posts

    Know what you're signing.

    RevU reads your NIL contract, quotes the clauses worth a closer look, and keeps guaranteed pay apart from pay that depends on something. Free for athletes, always.