# Phase 7 — human benchmark, welfare model, robustness, interpretability (2026-10-28)

Human-appraiser arm: NOT PERFORMED (requires a UQO research-ethics certificate and recruitment); marked pending in the paper; no human numbers anywhere. Welfare model: paper/sections/welfare.tex, scripts/40_welfare_sim.py (illustrative; propositions on rationing, lender loss, systemic correlation). Robustness: spatial holdout (A/C/D retrained without Outaouais, Abitibi-Témiscamingue, Bas-Saint-Laurent), provider committees, rounds grid, aggregation rules, small-tier models, stratified errors (results/evaluation/strata.csv), run-to-run repeat, exclusion sensitivity NOT run (WP 22 exclusion flags applied as-is). Interpretability audit: results/evaluation/faithfulness*.csv — cited ids 100 % valid; adjustments within ±40 % of raw comparable prices 96–99 %; point inside the adjusted-comparable hull ≈ 99 %; anchoring index 0.7–0.8; convergence 0.55 at round 2. Fundamental-value triangulation: scripts/50–52, paper/sections/fundamental.tex (resale-implied values for 92,089 sales; rents and user cost illustrative; LLM-arm comparison deferred for lack of resale-linked subsample properties).