Validating AI — The research project so far
Where the project stands as of July 2026 — the starting point for this log.
Lab
Dated, in-progress research notes. Not finished essays — the open work behind the research on post-cognition and the validation of language model outputs.
Paper Structure — Eight sections, Peirce, and building on Quattrociocchi
The paper’s eight-section architecture is finalized, with Peirce as methodological foundation and the framework situated as a direct continuation of Quattrociocchi et al.'s work on epistemia.
Vertical Validation — 180 API runs and the 74-point gap
180 API runs across six claims reveal a 74-point gap between lexical and semantic agreement.
Horizontal Validation — 31 claims across the full taxonomy
31 claims spanning eleven D1 categories demonstrate taxonomic coverage without category collapse.
Coding Manual v2.0 — The annotation protocol for reproducibility
Fifteen variables (V1–V15) operationalize the taxonomy into a reproducible annotation protocol.
Pre-Step 0 — Before classification, verify the speech act
An Austinian check on illocutionary force, added as a mandatory gate before any D1 classification.
The Monaco Case — Causal asymmetry and the limits of validation
A real-world causal claim exposes the asymmetry of causal validation, formalized as a three-outcome procedure for D4.3.
Building the Taxonomy — Seven dimensions, eleven categories
The seven-dimensional taxonomy (D1–D7) takes shape; eleven categories under D1, version 2.2.
Fake News and the Epistemology of Truth — The origin story
The 2018 essay that first raised the ontological question later formalized in the taxonomy.