Spaces:

Boopster
/

oCNT5PcMSQ

Running

Update logbook: Repro — CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting (formerly “How Can I Publish My LLM Benchmark Without Giving the True Answers Away?”)

1caa158 verified 19 days ago

preview code

Raw

History Blame Contribute Delete

632 Bytes

metadata

title: >-
  Repro — CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set
  Overfitting (formerly “How Can I Publish My LLM Benchmark Without Giving the
  True Answers Away?”)
emoji: 🎯
colorFrom: yellow
colorTo: red
sdk: static
pinned: false
tags:
  - trackio
  - trackio-logbook
  - open-experiment
  - icml2026-repro
  - paper-oCNT5PcMSQ

Repro — CapBencher: Give Your LLM Benchmark a Built-in Alarm for Test-Set Overfitting (formerly “How Can I Publish My LLM Benchmark Without Giving the True Answers Away?”)

An open experiment logbook, published with Trackio.