pith. sign in

Thanawat Lodkaew

Identifiers

  • name variant Thanawat Lodkaew 0.60 · backfill

Papers (2)

  1. Do Coding Agents Deceive Us? Detecting and Preventing Cheating via Capped Evaluation with Randomized Tests cs.LG · 2026 · author #1
  2. CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting cs.LG · 2025 · author #2

Mentions

  • 2606.07379 #1 · arxiv_oai · confidence 0.70 Thanawat Lodkaew
  • 2505.18102 #2 · arxiv_oai · confidence 0.70 Thanawat Lodkaew

Frequent Coauthors