
QWED (Query with Evidence & Determinism) is a deterministic verification protocol that treats LLMs as untrusted translators. It validates AI outputs using 8 specialized engines: math (SymPy), logic (Z3), code security (AST), SQL (SQLGlot), statistics, fact checking, image validation, and consensus. In benchmarks against Claude Opus 4.5, QWED achieved 100% error detection where the model had 73-85% accuracy. Open source under Apache 2.0.
python, formal-verification, machine-learning, llm-safety, hallucination-detection, sympy, ai-verification, z3-prover
python, formal-verification, machine-learning, llm-safety, hallucination-detection, sympy, ai-verification, z3-prover
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 0 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
