Uncertainty based selection of compatible inputs

An editable, auditable 807K-param byte-level LLM: CRUD single facts with provable per-edit locality, and abstain when unsure instead of guessing. CPU, offline.

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.

A comprehensive library for uncertainty quantification in machine learning.

Uncertainty-aware reliability monitor for safety-critical ML models — calibration (ECE), risk-coverage (AURC), selective prediction with human review, and drift detection. React, FastAPI, PostgreSQL, Kafka.

Calibrated trust and abstention for MS/MS molecular annotations

Prompt-only boundary prediction for IFEval-style instruction-checker pass/fail behavior.

Reliable medical QA with Mistral-7B, QLoRA, selective prediction, and learned abstention via warm-start SFT + DPO.

DegradeRisk-Seg: risk-controlled semantic segmentation under degraded multi-modal remote-sensing observations

Code Repository for SCoRE paper

Tsetlin Machines with a certificate on every answer: the exact number of feature flips a prediction survives, computed per sample, with predict-or-abstain when the radius is too small.

Investigation of how sampling strategies affect Selective Prediction performance in Multi Task Learning

Reproducible MEDAI deferral simulation (AIRI 2026). Synthetic research code.

Six from-scratch NumPy classifiers + a cost-sensitive abstention (reject) framework for Human Activity Recognition. 94% base accuracy; hits the 95% target by abstaining on 2.7% (UCI HAR).

Proper scoring rules, reduces LLM overconfidence in multiple-choice QA.

Selective RAG with conformal abstention: a hallucination detector that scores its own confidence and abstains, with a finite-sample precision guarantee.

Code and data release for the paper 'Cherry-pick Override: Unsafe Directional Commitment in LLM Judges under Mixed Evidence'

Selective prediction with calibrated uncertainty for contactless arrhythmia detection from facial video (rPPG). Benchmarks five UQ methods on AF / NSR / Other classification.

Pure-Python calibrated trust routing and split learn-then-test certification for LLM orchestration over science foundation models.