Comparing sequential forecasters via confidence sequences & e-processes
-
Updated
Oct 24, 2023 - Jupyter Notebook
#
confidence-sequences
Here are 7 public repositories matching this topic...
Taming False Positives in Out-of-Distribution Detection with Human Feedback (AISTATS '24)
outlier-detection false-positive-control ood-detection confidence-sequences aistats-2024 law-of-iterated-logarithms
-
Updated
Feb 26, 2024 - Python
让 prompt 从"感觉好了"变成"真好了" · Where "feels better" becomes "measurably better" for your AI prompts.
bootstrap shapley confidence-sequences llm-evaluation prompt-optimization agent-skills claude-code skill-iteration
-
Updated
Jun 22, 2026 - Python
Compute confidence Intervals (CLT, Chebyshev, Hoeffding) and Confidence Sequences (in a sequential setting if needed) in Julia
-
Updated
Feb 12, 2024 - Julia
A GxP-purpose-built LLM evaluation framework: anytime-valid validation, judge qualification, ALCOA+ audit, human plus AI workflow validation, drift monitoring, listener hooks, and a high-level facade on Inspect AI. Enables responsible AI use under risk-based assurance.
data-integrity gxp responsible-ai confidence-sequences llm-evaluation inspect-ai anytime-valid computer-software-assurance
-
Updated
Jun 28, 2026 - Python
Always-valid sequential A/B testing engine: mSPRT confidence sequences make peeking safe by construction, CUPED cuts variance up to 49%, SRM gates bad data. Built-in adversarial peeking harness proves the claim: naive daily peeking hit 27.5% false positives in 2,000 simulations; this engine held 1.7%. All numbers reproducible from committed seeds.
python statistics monte-carlo experimentation ab-testing hypothesis-testing causal-inference variance-reduction cuped sequential-testing confidence-sequences always-valid-inference msprt srm-detection
-
Updated
Aug 4, 2026 - Python
Certified Sparse Attention: runtime-verified fidelity for sparse-attention LLM serving. Label-free detection, anytime-valid confidence sequences, elastic probe scheduling. Smoke-scale H1-H4 results on Qwen2.5-0.5B/1.5B (AUC 0.92, Spearman -0.90).
machine-learning research deep-learning statistical-learning transformers pytorch attention-mechanism huggingface kv-cache confidence-sequences sparse-attention llm long-context llm-serving systems-ml
-
Updated
Aug 7, 2026 - Python
Improve this page
Add a description, image, and links to the confidence-sequences topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the confidence-sequences topic, visit your repo's landing page and select "manage topics."