Research

From one window to many

The program builds windows that measure gaps between what a system shows and what is actually there, starting outside the model with agent transcripts and moving inward to read-only heads on model internals.

Roadmap

01Consistency engine
TESTED
Claim and entity graphs that find contradictions no single sentence reveals.
02Agent transcript monitor
SPECIFIED
Agent claims to be checked against hash-chained tool evidence, with a three-way verdict.
03Harder test corpora
IN PROGRESS
Generated, cross-screened consistency corpora at any size (XonForge).
04Read-only heads
DESIGNED
The strain head first; a catalog of thirty candidate windows into model internals.
05Xon learning core
LONGER TERM
A settling architecture to work alongside standard neural networks.
Result · Benchmark L1

Finding contradictions no single pair reveals

180 synthetic documents: 60 consistent, 60 with a direct contradiction, and 60 with a planted cycle of claims that are pairwise compatible but jointly impossible. The engine met its pre-stated thresholds (direct F1 ≥ 0.85, cycle F1 ≥ 0.75, localization ≥ 0.7) and located the planted claims in every cycle document. Checking claims two at a time catches direct contradictions but misses most cycles.

Method Direct F1 Cycle F1 False-positive rate
Consistency engine 0.916 0.916 0.183
Pairwise checks only 0.916 0.329 0.183
LLM direct (thinking) 0.930 0.930 0.150
LLM direct (no thinking) 0.805 0.805 0.483

A strong model asked directly performs comparably on this benchmark; the engine's advantage is that every flag comes with the specific claims and relations behind it. Harder corpora from XonForge are next.

Every result, with dates, criteria and provenance →

The research series

Six documents, numbered in reading order: the claim, the instruments, and the architecture.

Plans and specifications

Working papers: how the ideas above will be tested and built. They are dated, and revised as the work moves.