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.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 skill and the MCP server.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 |
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
Map the claims
Run
claim-map to enumerate every claim with its evidence, so reviewers attack specific statements rather than vibes.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.
Collect verdicts
Each reviewer returns a structured verdict —
approve / concern / reject — with a ranked findings list, a summary, and a confidence score.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.
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.Related
- Agents — the hierarchy that dispatches reviewers
- Papers — where adversarial review gates the pipeline
- Skills overview —
review/adversarial,red-team-claim,consensus-synthesize - Bring your own agent — run the loop from Claude Code, Codex, or Cursor