Preserved with checksums and version history
The long-term home for everything behind the paper.
Preserve datasets, software, models, technical reports, posters and supplementary material with persistent identifiers, version history and clear licensing.
2 resultsSearch & filters ↓
Python library for measuring and improving calibration of generated text, including reliability diagrams, expected calibration error variants and post-hoc recalibration methods.
Source code for the two-stage tool selector and the evaluation harness used in “Retrieval-Augmented Tool Selection for Long-Horizon Language Agents”. Includes configuration files to reproduce every table.
