# Bayesian Inference and Decision Audits for Public Archives of Frontier AI Evaluations

arXiv: https://arxiv.org/abs/2606.17005 · HTML: https://mlsanity.com/paper/2606.17005/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 15 Jun 2026.

## Builds on (most cited first, 23 of 23)

- [Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena](https://mlsanity.com/paper/2306.05685/) (2023)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [SWE-bench: Can Language Models Resolve Real-World GitHub Issues?](https://mlsanity.com/paper/2310.06770/) (2023)
- [WebArena: A Realistic Web Environment for Building Autonomous Agents](https://mlsanity.com/paper/2307.13854/) (2023)
- [Beyond the Imitation Game: Quantifying and extrapolating the capabilities of language models](https://mlsanity.com/paper/2206.04615/) (2022)
- [ToolLLM: Facilitating Large Language Models to Master 16000+ Real-world APIs](https://mlsanity.com/paper/2307.16789/) (2023)
- [τ-bench: A Benchmark for Tool-Agent-User Interaction in Real-World Domains](https://mlsanity.com/paper/2406.12045/) (2024)
- [AgentBench: Evaluating LLMs as Agents](https://mlsanity.com/paper/2308.03688/) (2023)
- [Chatbot Arena: An Open Platform for Evaluating LLMs by Human Preference](https://mlsanity.com/paper/2403.04132/) (2024)
- [GAIA: a benchmark for General AI Assistants](https://mlsanity.com/paper/2311.12983/) (2023)
- [Are Emergent Abilities of Large Language Models a Mirage?](https://mlsanity.com/paper/2304.15004/) (2023)
- [NLP Evaluation in trouble: On the Need to Measure LLM Data Contamination for each Benchmark](https://mlsanity.com/paper/2310.18018/) (2023)
- [LiveBench: A Challenging, Contamination-Limited LLM Benchmark](https://mlsanity.com/paper/2406.19314/) (2024)
- [What Will it Take to Fix Benchmarking in Natural Language Understanding?](https://mlsanity.com/paper/2104.02145/) (2021)
- [Show Your Work: Improved Reporting of Experimental Results](https://mlsanity.com/paper/1909.03004/) (2019)
- [With Little Power Comes Great Responsibility](https://mlsanity.com/paper/2010.06595/) (2020)
- [When Benchmarks are Targets: Revealing the Sensitivity of Large Language Model Leaderboards](https://mlsanity.com/paper/2402.01781/) (2024)
- [Generalization in Adaptive Data Analysis and Holdout Reuse](https://mlsanity.com/paper/1506.02629/) (2015)
- [The Ladder: A Reliable Leaderboard for Machine Learning Competitions](https://mlsanity.com/paper/1502.04585/) (2015)
- [Comparing Test Sets with Item Response Theory](https://mlsanity.com/paper/2106.00840/) (2021)
- [ExplainaBoard: An Explainable Leaderboard for NLP](https://mlsanity.com/paper/2104.06387/) (2021)
- [A Flexible Defense Against the Winner's Curse](https://mlsanity.com/paper/2411.18569/) (2024)
- [Testing for sufficient follow-up in survival data with a cure fraction](https://mlsanity.com/paper/2403.16832/) (2024)

## Abstract (arXiv)

Public AI evaluations are often read as terminal leaderboards, yet the underlying evidence is a selective time series shaped by reporting rules, benchmark revisions, and missingness. Repeated public archives for LiveBench and Open LLM Leaderboard v2 serve as the primary longitudinal record; LMArena provides a preference stress test; and GAIA and tau-bench contribute limited agentic pilots. Together, these archives instantiate a Bayesian inference problem: under a fixed reporting convention, one constructed terminal-only example over 1,000 systems is compatible with two pre-terminal histories, yielding times of 23.03 or 75.13 to reach within 0.05 of the ceiling under the same terminal-tail model. In synthetic posterior comparisons, action-facing diagnostics differ across observation regimes. The candidate selection-aware frontier model fails synthetic recovery, objective-archive prediction, preference transfer, and uncertainty calibration; correspondingly, fixed audit gates reject its stronger claims. An archive-and-adjudication protocol reconstructs public evaluation histories, isolates a verified timing boundary, and falsifies unsupported frontier claims.