index: retitle thesis bullet "Inequality as a Graph"; ground Rawls/Sen in concrete edges

Rawlsian weighting → racial neighborhoods, school districts.
Sen → occupational groups (Bengal famine entitlement collapse).

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

Author: Boris Dev

docs/index.md

@@ -15,7 +15,7 @@ So AI can be safer, I evaluate its performance. One cool way to do this is to fi
 - **HealthBench EBM failure patterns** — Where do frontier models fail on evidence-based medicine, and which failures are worth fixing? I ran GPT-5.2 and Claude Opus 4.8 on an EBM-verified slice of HealthBench and clustered the errors into seven canonical recall/precision failure patterns — each with anchored examples, a root-cause hypothesis, and a distinguishing experiment. [github.com/borisdev/healthbench-ebm-verified](https://github.com/borisdev/healthbench-ebm-verified)
 - **Muni-Resilience-Bench** — How much does a specific resilience project (wildfire hardening, flood control, seismic retrofit) lower a city's borrowing cost? An open benchmark for the missing, auditable translation from a project's risk reduction to citywide fiscal impact. [github.com/borisdev/muni-resilience-bench](https://github.com/borisdev/muni-resilience-bench)
 - **Wolf Games** — What makes an AI-generated murder-mystery storyboard coherent across interpolated scenes?
-- **PhD thesis** — What makes an inequality metric capture nuanced gaps among social groups in the same city? Gini and variance silently weight every pair of places the same. I lifted that hidden assumption into an explicit spatial weights matrix — a graph of weighted edges over places — so a Rawlsian concern (unjust institutions) and a Senian one (deprivation relative to your neighbors) imply *different* metrics, and can score the same change in opposite directions. [Essay](spatial-view-is-a-graph.md) · [Full dissertation (PDF)](https://escholarship.org/content/qt8br7d5df/qt8br7d5df.pdf)
+- **Inequality as a Graph** *(PhD thesis)* — What makes an inequality metric capture nuanced gaps among social groups in the same city? Gini and variance silently weight every pair of groups the same. I lifted that hidden assumption into an explicit weights matrix — a graph whose edges say *which* gaps count, and how much — so different concerns imply *different* metrics. A Rawlsian asks whether institutions distribute justly, so the heavy edges run between racial neighborhoods and school districts. Sen asks who is deprived of capabilities, so the heavy edges run between occupational groups — the entitlement collapse that drove the Bengal famine. The same change can score in opposite directions under the two. [Essay](spatial-view-is-a-graph.md) · [Full dissertation (PDF)](https://escholarship.org/content/qt8br7d5df/qt8br7d5df.pdf)
 - **SimpleLegal** — What makes "Called the State Senator" lawyer-level work rather than an administrative task? The classification depended on the relevance of the output, not the wording of the task.
 
 ### Selected technical impact