# Calibration stage A (prereg §4, gates C1a-c + C4): every candidate family's base / specialist
# accuracy, specialist confidence AUC, pairwise functional conflict, gen-0 behavioural distance.
# GG reviews the printed table and fixes the 12-family set in society_v2_calib_b.yaml + the campaign.
# ~1 h on a 16 GB GPU (17 specialists at 600 x 3 epochs, cached and reused by stage B).
experiment: llm_society_v2_calib_a
kind: llm_society_calib
stage: families
base_model: Qwen/Qwen2.5-0.5B-Instruct
seed: 1
families: [lists, strings, arith, roman, binary, sortletters, setops, numtheory, mixedtoken,
           caesar, vectors, progression, charfreq, digits, liststats, alphabet, prime]
n_test: 100
n_probe: 10
spec_train: 600
spec_epochs: 3
lora: {r: 16, alpha: 32}
output: {dir: results/llm_society_v2_calib_a}