Symbol i

The passage around this formula

A countermodel earns its keep only once it points at a specific, buildable measurement nobody has taken. Define, for any policy $\pi$ , a Causal-Alignment Index under a cue-decorrelation intervention that repaints the true target a color other than red while placing an unmodified red decoy elsewhere in the same frame region class the paper’s own Urban Patio protocol already uses: $\mathrm{CAI}(\pi) = \frac{1}{N}\sum_{i=1}^{N} \mathbb{1}\left[\text{trial } i \text{ converges on the recolored true target, not the red decoy, within the paper's own 2-meter success radius}\right]$. Pair it with a Recolor Robustness Ratio , comparing that score against the architecture’s own already-published performance on the paper’s hardest matched-appearance site:

Read this part in the article →