英語版How can labs build shared, tamper-evident benchmarks for test evasion without compromising proprietary datasets?
- 状況
- 一部回答 時点 2026-10-01
- 宛先
- AIラボへ評価機関 (宛先は問いの本文から、2026年10月22日に Clef(Cloudflare)で判定)
- モデル
- Gemini 3.8 Flash
- ラボ
- 日付
- 9月12日~20日
- テーマ
- 透明性
出典の内容(英語のみ)
OpenAI recommended on May 29, 2026 that evaluators prefer private or newly created tasks and check whether models reproduce task-specific details before solving them.[1] How to make shared benchmarks tamper-evident while protecting proprietary datasets remains open.
要約 Sol 6.1, 確認: Claude Opus 5.5
Liz のアトラスで該当:
- Evaluations are Confounded and Biased ↗Threat: Open problem · Trend: → steady · Evidence: estimated
- Alignment Faking & Deceptive Alignment ↗Threat: Severe · Trend: → steady · Evidence: confirmed
確認
状況: Claude Sonnet 5 (調査, 推論強度 高), Claude Opus 5.5 (確認, 推論強度 高)
翻訳: Claude Opus 5.5, 確認: Luna 6 (推論強度 高)
スコア: JEV (TypeSafe), 2026年9月25日時点の推定
Cite and take away
Cite and reuse
Own texts, questions and classifications: CC BY 4.0. Give attribution, link the license and indicate changes. Third-party source reports retain their own rights. CC BY 4.0
AMANi DUNiA. transparency-05 · 独自のデータセットを損なうことなく、ラボはテスト回避について、共有され改ざんが検知可能なベンチマークをどのように構築できるか。. Snapshot: . https://research.amanidunia.berlin/ja/fragen/transparency-05/
Version: transparency-05
BibTeX
@misc{research__ja_fragen_transparency_05_,
author = {{AMANi DUNiA}},
title = {transparency-05 · 独自のデータセットを損なうことなく、ラボはテスト回避について、共有され改ざんが検知可能なベンチマークをどのように構築できるか。},
year = {2026},
url = {https://research.amanidunia.berlin/ja/fragen/transparency-05/},
note = {Snapshot 2026-10-01; CC BY 4.0},
version = {transparency-05}
}Language and review status
Main text: JA · includes English sections. Review notes apply only to the content they name.
Translation available; a completed independent content review is not recorded.
See language coverage and data snapshot →