Confidence based selection of compatible inputs
-
Updated
May 15, 2026 - Python
Confidence based selection of compatible inputs
Behavioral Trust Clustering a thermodynamic governance layer that reduces LLM hallucination by 52% on HumanEval. Drop-in wrapper for any decoder. MIT.
We show that a model owner can artificially introduce uncertainty into their model and provide a corresponding detection mechanism.
Deepfake detection with Bayesian uncertainty quantification, selective prediction, and an interactive Streamlit demo.
Code for our paper analyzing the looseness of the upper bound on selective classification performance.
Investigation of how sampling strategies affect Selective Prediction performance in Multi Task Learning
Code Repository for SCoRE paper
Trustworthy medical image classification: noise-robust ConvNeXt-Tiny with 83.5% accuracy, calibrated selective prediction, HAM10000 + ISIC 2019.
BoundaryBench: Benchmark + tool-augmented method for boundary containment under GPS noise
Application materials for the AIRI Summer School 2026. Includes a research proposal on uncertainty calibration in MEDAI and a reproducible simulation environment.
Transform enrichment outputs into verifiable pathway claims via stability distillation, evidence modules, and mechanical PASS/ABSTAIN/FAIL audits.
Reproducible pipeline for silent-failure auditing in ECG accept-sets (MIT-BIH) with Newton–Puiseux onset scoring
Add a description, image, and links to the selective-prediction topic page so that developers can more easily learn about it.
To associate your repository with the selective-prediction topic, visit your repo's landing page and select "manage topics."