Historical Windows temporal memory-state research artifact for studying time-bound memory observations, validation limits, and defensive visibility.

PCBench: Benchmark for Python API parameter compatibility issues

Code, data, and ontologies for FAOS research papers on ontology-powered enterprise AI agent verification (RA-3 neurosymbolic, RA-6 trust certification).

JSON Schema for decision events as governance evidence units in automated decision and real-time risk systems. MIT.

Evaluation infrastructure for AI systems beyond direct human supervision

Side-channel profiler that detects deceptive intent in LLMs by measuring the computational cost of lying.

Reproducibility package for fixed-ontology GraphRAG court-form filling experiments

Curated code and result summary for world-model inputs in Atari policy experiments.

Research artifact repository containing the AB Genesis Simulator and benchmark framework fo...

A reproducible microservice observability lab for measuring performance overhead, debugging value, failure detection, indexing impact, and orchestration trade-offs.

Python library for evidence sufficiency scoring in governance assessments under delayed ground truth, drift, and decision-readiness constraints.

langquant (LPCI) is a scaffold-as-state research artifact testing whether a refreshing language scaffold can serve as the sole working state for a stateless LLM. In one A/B run (n=1/condition, 20 turns) the model held coherence with zero history; transfer entropy dropped 0.608 to 0.085, a large reduction, not zero. Single observation, not a proof.

Experimental Python runtime for validation-gated program synthesis and adaptive search: multi-level meta-learning (meta-meta loops), analogical transfer, grammar-mediated expansion, anti-cheat verifiers, sealed evaluations, rollback-sensitive self-modification. Bounded adaptive improvement, not unrestricted recursive self-improvement.

REQBench: Benchmark for compatible requirements inference in Python third-party library upgrades

PCART-LLM: Research artifact for LLM-based API compatibility analysis

Artifact for the empirical study of adaptive runtime instrumentation under telemetry budgets

PGP-inspired Post-Quantum text encryption. Features Hybrid Crypto (Kyber + X25519), TPM Hardware Binding, and paranoid memory hygiene.

PCREQ-evaluation: Evaluation artifact for PCREQ

Reference prototype and reproducibility artifact for an ML-KEM-768-based incompleteness-secured commitment framework with claim guards, benchmark scripts, and wrapper portability probes.

Manuscript and arXiv source package for Policy-Constrained Financial Execution for Autonomous Agents (FPCL).