fix(gpqa): write evaluator output to results.json

[skyzer]

Summary

• make the bundled GPQA evaluator write results.json by default
• keep explicit --output overrides unchanged
• add a regression test for the SIA evaluator artifact contract

Why

run_evaluation() treats gen_*/results.json as the canonical evaluator artifact. GPQA previously wrote evaluation_results.json by default, so evaluation could complete but the orchestrator would still report that results.json was missing.

Test plan

• python3 -m pytest tests/test_gpqa_evaluator.py -q
• python3 -m pytest tests/test_gpqa_evaluator.py tests/test_run_evaluation.py tests/test_run_evaluation_outcomes.py -q
• python3 -m ruff check .
• python3 -m pytest -q

[chatgpt-codex-connector]

💡 Codex Review

Here are some automated review suggestions for this pull request.

Reviewed commit: 364f9400af

ℹ️ About Codex in GitHub

Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you

• Open a pull request for review
• Mark a draft as ready
• Comment "@codex review".

If Codex has suggestions, it will comment; otherwise it will react with 👍.

Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".

[chatgpt-codex-connector]

Avoid reusing evaluator output as submission

When --gen-dir is used, find_submission_file() runs before this write and treats any root-level results*.json as the submission candidate, returning it before checking submission*.json. After the first successful evaluation creates gen_dir/results.json, any rerun on the same generation directory will load the previous evaluator output as the model submission, so answers are absent/misread and the new results can overwrite a correct score with incorrect/missing results. Please exclude the evaluator artifact from submission discovery or otherwise disambiguate it before making it the default output name.

Useful? React with 👍 / 👎.