> ## Documentation Index
> Fetch the complete documentation index at: https://hubify.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Adversarial Review

> Hubify's moat: model-, harness-, and vendor-agnostic adversarial peer review that optimizes catching the false positive before it ships — the opposite of cooperative mixture-of-agents.

# Adversarial Review

Adversarial review is Hubify's core differentiator. Every substantive claim — a paper, a result, a derivation — is reviewed by **independent models from different labs that are told to refute it**, not to improve it. The reviewers share no training priors, so their errors decorrelate, and the disagreements they surface become tracked fixes before a venue referee ever sees the work.

<Note>
  This is a **primitive**, not a feature. It runs on top of any agent — including Claude Science, Codex, or your own — via the [`review/adversarial`](/skills/overview) skill and the MCP server.
</Note>

## Cooperative vs. adversarial

In 2026 the whole market converged on multi-agent orchestration — Sakana Fugu, Nous Hermes Mixture-of-Agents, Anthropic Claude Science. All of it is **cooperative aggregation**: blend N models into one synthesized answer to raise a benchmark score. Hubify runs the other primitive.

|                        | Cooperative mixture-of-agents          | Hubify adversarial review                                                   |
| ---------------------- | -------------------------------------- | --------------------------------------------------------------------------- |
| **Objective**          | Raise the score                        | Catch the false positive before it ships                                    |
| **Failure it targets** | A suboptimal answer                    | A hallucinated derivation, a fabricated result, a headlined-favorable value |
| **Model relationship** | Blend / agree                          | Independently refute / disagree                                             |
| **Vendor spread**      | Same-vendor is fine (errors correlate) | Cross-vendor is mandatory (errors decorrelate)                              |
| **Review source**      | Internal only                          | Internal **and** independent external                                       |
| **Bias guard**         | None                                   | Integrity audit against self-favoring                                       |
| **Output**             | One synthesized answer                 | Verdict-first, source-cited, provenance-linked                              |

Mixture-of-agents makes the answer *smarter*. Adversarial review makes the answer *trustworthy*. In science the false positive is the catastrophic failure — a retraction, a wasted grant, wrong physics propagated for years — not a lost benchmark point.

## Why it matters more in science

* **Falsification is the method.** A cross-vendor refutation loop is the scientific method rendered computational. Cooperative aggregation manufactures consensus instead.
* **Correlated errors are the real enemy.** Two agents from the same lab share training priors and hallucinate in the same direction. Only cross-*vendor* independence decorrelates the errors that retract papers.
* **Cost asymmetry.** Catching one false positive is worth more than any number of benchmark points.

## How a review runs

<Steps>
  <Step title="Map the claims">
    Run [`claim-map`](/skills/overview) to enumerate every claim with its evidence, so reviewers attack specific statements rather than vibes.
  </Step>

  <Step title="Dispatch cross-vendor reviewers">
    At least **three different providers** across distinct roles (skeptic, methods, long-context, contrarian, fact-check). Each is a separate model invocation with a role-specific system prompt, and **reviewers never see each other's verdicts** — independence is the point.
  </Step>

  <Step title="Collect verdicts">
    Each reviewer returns a structured verdict — `approve` / `concern` / `reject` — with a ranked findings list, a summary, and a confidence score.
  </Step>

  <Step title="Integrity audit">
    A separate skeptical pass, not told the desired conclusion, checks for verdict-severity steering, dismissals that don't hold against the source, and headlining the more-favorable of multiple values. Verdict: genuine vs. engineered.
  </Step>

  <Step title="Synthesize and file fixes">
    Critical findings from any reviewer are blocking; concerns shared by two or more are blocking. Disagreement is surfaced, never averaged away. Required fixes become tracked tasks; the paper does not advance until they land.
  </Step>
</Steps>

## The structural moat

No single frontier lab can offer vendor-agnostic adversarial review without cannibalizing itself. Anthropic's Claude Science is single-vendor by design — it will never route to GPT or Gemini to check its own work. Sakana Fugu routes *around* Anthropic. Hermes MoA is a developer tool with no science discipline. Only an independent layer can be the neutral referee — which is why Hubify treats every agent runner as interchangeable execution substrate it sits on top of.

## Proven in production

BigBounce — a six-paper bounce-cosmology program — is driven toward publication by exactly this loop. Its cross-vendor + external + integrity-audited review has caught real errors a single model would have missed: an overlap-inflated significance from shared-supernova double-counting, and a mislabeled catalog tier that failed injection-recovery. See the live review timeline at [bigbounce.hubify.app/reviews](https://bigbounce.hubify.app/reviews).

## Related

* [Agents](/concepts/agents) — the hierarchy that dispatches reviewers
* [Papers](/concepts/papers) — where adversarial review gates the pipeline
* [Skills overview](/skills/overview) — `review/adversarial`, `red-team-claim`, `consensus-synthesize`
* [Bring your own agent](/skills/bring-your-own-agent) — run the loop from Claude Code, Codex, or Cursor