Dissenter / unanimity break (MedMCQA)

[duckyquang]

Replicate the Dissenter / unanimity break (MedMCQA) experiment on MedMCQA, mirroring the MedQA template so results are apples-to-apples across datasets.

• MedQA template issue(s): Dissenter / unanimity break: add one planted CORRECT peer alongside the wrong seed(s) #198
• MedQA template script: experiments/medqa/unanimity_break.py
• Dataset adapter: benchmaxxing/datasets/medmcqa.py (already implemented, Dataset adapter: MedMCQA (text/MCQ) #112)

What it measures

Add one planted CORRECT peer alongside the wrong seed(s) and measure the drop in adoption.

What to do

Run the same experiment on MedMCQA through the existing pipeline and the Gemini API. Replication, not new features: do not change the experiment code, only point it at a MedMCQA manifest (build one with the medmcqa adapter). Write results under experiments/medmcqa/results/ in the same JSON/JSONL convention as experiments/medqa/results/ (not CSV, so the analysis tooling reads them).

Acceptance

• Results committed under experiments/medmcqa/ in the MedQA template's format.
• The same headline statistic the template reports, on MedMCQA.
• Verified against a real API run (no synthetic data, no smoke-test-only claims).
• PR opened that closes this issue.

Part of the MedMCQA standard-battery replication (mirrors the MedQA/NIH template).

[duckyquang]

Delivered in #368: implemented and run against real Gemini (temp 0), committed with summary + per-record jsonl, written up in results/RESULTS.md §8 committee size & pressure. Per-arm cache now committed for keyless replay (#415).