When Is Benchmark Contamination Detectable? Information Limits and Power-Calibrated Audits

arXiv:2608.07914 · cs.AI · Submitted 2026-08-08 · Read on arXiv

Ibne Farabi Shihab, Sanjeda Akter, Anuj Sharma

cs.AI

Submitted: 2026-08-08

Updated: 2026-08-11

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Terminology

• Calibration — 44× in this paper · explained in 9 episodes
• Benchmark — 39× in this paper · explained in 2 episodes
• Planner — 26× in this paper · explained in 3 episodes
• AUC — 20× in this paper · explained in 2 episodes
• Membership Inference — 9× in this paper · explained in 2 episodes
• Inflation — 8× in this paper · explained in 2 episodes
• Decode — 6× in this paper · explained in 2 episodes
• Exchangeability — 6× in this paper · explained in 2 episodes
• Memorization — 5× in this paper · explained in 4 episodes
• Provenance — 5× in this paper · explained in 5 episodes
• AUROC — 4× in this paper · explained in 3 episodes
• Abstention — 3× in this paper · explained in 1 episode
• Distribution Shift — 3× in this paper · explained in 12 episodes
• Ablation — 2× in this paper · explained in 1 episode
• Adam — 2× in this paper · explained in 3 episodes
• External Validation — 2× in this paper · explained in 2 episodes
• Foundation Model — 2× in this paper · explained in 3 episodes
• Foundation Models — 2× in this paper · explained in 8 episodes
• Hyperparameters — 2× in this paper · explained in 2 episodes
• International Conference on Learning Representations — 2× in this paper
• International Conference on Machine Learning — 2× in this paper
• Papers — 2× in this paper · explained in 3 episodes
• Accountability — 1× in this paper · explained in 2 episodes
• Accuracy — 1× in this paper · explained in 1 episode
• Consistency — 1× in this paper · explained in 3 episodes
• Distillation — 1× in this paper · explained in 2 episodes
• Embeddings — 1× in this paper · explained in 2 episodes
• Empirical Coverage — 1× in this paper · explained in 2 episodes
• Failure Modes — 1× in this paper · explained in 3 episodes
• Generalization — 1× in this paper · explained in 14 episodes
• Meeting of the Association for Computational Linguistics — 1× in this paper
• Non-Gaussianity — 1× in this paper · explained in 3 episodes
• Trace — 1× in this paper · explained in 2 episodes

Sources

• Blind Baselines Beat Membership Inference Attacks for Foundation Models
• Evading Data Contamination Detection for Language Models is (too) Easy
• On The Fragility of Benchmark Contamination Detection in Reasoning Models

Related papers

• MAVEN-T: Reinforced Heterogeneous Distillation for Real-Time Multi-Agent Trajectory Prediction
• Model Discovery Agent: LLM-assisted Bayesian experiment design for data-efficient discovery of mechanistic world models
• Agents' Last Exam
• The Clinician's Veto: Navigating Trust, Liability, and Uncertainty in Autonomous AI Prescribing
• MindHelper: Closed-Loop Embodied Mental-State Reasoning for Precision Intervention
• Incumbent Advantage: Brand Bias and Cognitive Manipulation Dynamics in LLM Recommendation Systems