Evidence, with citations
Every claim on this site is anchored to a public repository, a merged pull request, a DOI, or a filing number. This page is the citation ledger. It is structured so any claim can be checked at its source.
Technical record4 record classesLast revised 6 August 2026
Validation at a glance
A summary ledger. The detail behind each row lives on its own page: open-source tools, upstream fixes, and research. None of the six papers has completed external peer review; Zenodo assigns a DOI without refereeing. Patents are documented in full below, since this is their only home.
Five current PyPI install paths
lintlang 0.3.8, little-canary 0.3.3, hermeneutic 0.1.8, agent-gorgon 0.1.8, and Fidelis Memory 0.0.93 install from PyPI. Fidelis Memory keeps fidelis as its repository, import, and CLI name; the separate PyPI package named fidelis is unrelated. The active-core page adds the guided entry point and memory-reference tracks without implying that every repository has the same install or maturity level.
LintLang beyond its own repository
3,000+ PyPI registry downloads are download events, not users. Character.AI's public Larch repository pins lintlang 0.3.1 in a recurring CI job, with a public successful execution; that is package execution, not endorsement or outcome validation. The package also has independent Gentoo packaging, and the Agent Lint maintainer attributes parts of that product's roadmap to useful ideas from lintlang. Together these establish public ecosystem evidence, not customers, production fitness, or detector accuracy on external projects.
32 merged, including LangChain and Microsoft Semantic Kernel
Two of the merged pull requests removed runtime failures in the AI frameworks teams build on: a forced tool_choice crash in LangChain and a silent system-prompt deletion in Microsoft Semantic Kernel.
6 papers on Zenodo: 3 preprints, 1 working paper, 2 technical notes
Six papers with distinct roles and evidence classes: a seven-mode taxonomy of epistemic failure modes (preprint, built on 1,461 controlled experiments conducted primarily on GPT-4o), a matched-vignette benchmark for null-result asymmetry (working paper), a twelve-week naturalistic measurement-validity audit of AI agent telemetry proposing the Telemetry-to-Claim Gate (preprint), a conceptual account of the generative horizon and the limits of model self-report (preprint), a bounded static analysis of neighboring AI-agent tool descriptions (technical note), and a prompt-injection sensing architecture that preserves inspection coverage (technical note).
1 non-provisional, 4 provisional
Stateless user identification, adversarial prompt-injection probing, deterministic local inference control, multi-modal classification calibration, and confidence-gated personalization.
Patent filings
Method for Stateless User Identification in Natural Language Processing
The non-provisional application; the provisionals below cover adjacent mechanisms for adversarial probing, deterministic inference, multi-modal classification calibration, and confidence-gated personalization.