Boopster/DKathyl3XN-artifacts
1.33 MB
Becky Still
Boopster
AI & ML interests
AI Engineer
Recent Activity
updated a collection about 24 hours ago
ANVg7NnupP — Demystifying LLM-as-a-Judge Reproduction updated a collection about 24 hours ago
ANVg7NnupP — Demystifying LLM-as-a-Judge Reproduction updated a collection about 24 hours ago
ANVg7NnupP — Demystifying LLM-as-a-Judge ReproductionOrganizations
ANVg7NnupP — Demystifying LLM-as-a-Judge Reproduction
CPU-only, deterministic Trackio reproduction of the three ICML 2026 challenge claims for OpenReview ANVg7NnupP.
- Running
Repro - Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
🎯Track and share experiment logs with an AI coding agent
-
Boopster/demystifying-llm-judge-scaling-repro-artifacts
1.13 MB -
Boopster/anvg7nnupp-cpu-reproduction-bucket
1.13 MB -
Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
Paper • 2512.19905 • Published
CapBencher ICML 2026 Reproduction — Boopster
Audited reproduction evidence for CapBencher / PhishBencher (ICML 2026).
-
How Can I Publish My LLM Benchmark Without Giving the True Answers Away?
Paper • 2505.18102 • Published • 2 - Running
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?”)
🎯Explore and sync LLM benchmark logs with a collaborative agent
-
Boopster/capbencher-formal-v5-checkpoints
12.4 GB -
ishidalab/capbencher
Viewer • Updated • 15.5k • 25 • 2
ANVg7NnupP — Demystifying LLM-as-a-Judge Reproduction
CPU-only, deterministic Trackio reproduction of the three ICML 2026 challenge claims for OpenReview ANVg7NnupP.
- Running
Repro - Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
🎯Track and share experiment logs with an AI coding agent
-
Boopster/demystifying-llm-judge-scaling-repro-artifacts
1.13 MB -
Boopster/anvg7nnupp-cpu-reproduction-bucket
1.13 MB -
Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
Paper • 2512.19905 • Published
CapBencher ICML 2026 Reproduction — Boopster
Audited reproduction evidence for CapBencher / PhishBencher (ICML 2026).
-
How Can I Publish My LLM Benchmark Without Giving the True Answers Away?
Paper • 2505.18102 • Published • 2 - Running
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?”)
🎯Explore and sync LLM benchmark logs with a collaborative agent
-
Boopster/capbencher-formal-v5-checkpoints
12.4 GB -
ishidalab/capbencher
Viewer • Updated • 15.5k • 25 • 2
spaces 14
Running
Repro - Demystifying LLM-as-a-Judge: Analytically Tractable Model for Inference-Time Scaling
🎯
Track and share experiment logs with an AI coding agent
Running
Repro - On Structured State-Space Duality
🎯
Collaborate with an AI agent to view and edit your logbook
Running
Reproduction: Optimal Unconstrained Self-Distillation in Ridge Regression: Strict Improvements, Precise Asymptotics, and One-Shot Tuning
🎯
Explore a research logbook and sync with coding agents
Running
Reproduction: Flat Minima and Generalization: Insights from Stochastic Convex Optimization
📐
Explore research logbook and sync findings with an AI agent
Running
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?”)
🎯
Explore and sync LLM benchmark logs with a collaborative agent
Running
Repro - A Coin Flip for Safety: LLM Judges Fail to Reliably Measure Adversarial Robustness
🎯
Collaborate with an AI agent to manage a safety logbook
models 0
None public yet
datasets 0
None public yet