Hermes Labs Research Publications https://hermes-labs.ai/atom.xml 2026-07-30T00:00:00Z The Generative Horizon: Applied Hermeneutics, Linguistic Attractors, and the Limits of Model Self-Report https://doi.org/10.5281/zenodo.21659634 Conceptual framework for model self-report, provenance, and recursive interpretive conditioning. Rolando Bosch https://orcid.org/0009-0005-4896-1112 2026-07-30T00:00:00Z 2026-07-30T00:00:00Z Precise Records, Unstable Meanings: Measurement Validity and Unsupported Claims Derived from AI Agent Telemetry https://doi.org/10.5281/zenodo.21652317 Empirical naturalistic audit of measurement validity in AI agent telemetry. Rolando Bosch https://orcid.org/0009-0005-4896-1112 2026-07-30T00:00:00Z 2026-07-30T00:00:00Z A Taxonomy of Epistemic Failure Modes in Large Language Models https://doi.org/10.5281/zenodo.19042469 Empirical taxonomy derived from 1,461 controlled experiments. Rolando Bosch https://orcid.org/0009-0005-4896-1112 2026-03-15T00:00:00Z 2026-03-15T00:00:00Z The Asymmetric Burden of Proof: LLMs Show a Null-Result Asymmetry in a Matched-Vignette Benchmark https://doi.org/10.5281/zenodo.18867694 Empirical matched-vignette study of null-result asymmetry. Rolando Bosch https://orcid.org/0009-0005-4896-1112 2026-03-04T00:00:00Z 2026-03-04T00:00:00Z