experiment: llm_epistasis
kind: llm_epistasis
seed: 1
seeds: [1, 2, 3]
n_replicates: 1

# THE DECISIVE EXPERIMENT (external review, 2026-08-11; PNAS work order Phase 3): do
# population-genetic quantities PREDICT merge success BEFORE merging, beyond existing predictors?
#
# Grid: functional conflict (conflict_fracs, add-design: private budget fixed, contradictory
# convention data added) and weight divergence (durations, zero conflict) are DECORRELATED BY
# CONSTRUCTION. Pre-merge predictors, none touching a merged model:
#   epi_conf   - operational epistasis: confidence-weighted bilateral disagreement on a broad probe
#                mix (ambiguous + both private families, drawn blind to where conflict lives). OURS.
#   dis_raw    - raw disagreement rate (the internal ablation: our theory PREDICTS this mispredicts,
#                because it counts harmless complementation - one parent ignorant - as conflict).
#   grad_cos   - gradient alignment at the shared base (the ML-literature predictor, cf. 2601.22285).
#   delta_cos / delta_l2 - LoRA-delta weight geometry (computed exactly in r-space).
#   cross_perf - performance-based predictor (cross-family accuracy).
# Outcome (PRIMARY, pre-registered): merge_penalty = parent_potential - merged_overall (the
# hybrid-load analogue: what the merge loses relative to what its parents could jointly deliver);
# secondary: merged_overall, and the soup-vs-route gap (route_private - merged_private).
#
# PRE-REGISTERED READINGS. Success for the framework: |Spearman rho(epi_conf, merge_penalty)| high,
# AND geometry/gradient predictors fail at matched divergence (their apparent correlation, if any,
# collapses within the conflict axis where divergence is near-constant), AND epi_conf > dis_raw
# (the confidence-weighting prediction). FALSIFIER: gradient/geometry/raw-disagreement match or beat
# epi_conf -> the "epistasis, not divergence, sets the cliff" claim stays analytic-only and the paper
# says so. Either outcome is reportable; do not tune toward one.

base_model: Qwen/Qwen2.5-0.5B-Instruct
family_a: strings
family_b: arith
n_train: 400
n_test: 80
epochs: 3
n_probe_each: 30
grad_k: 32
lora: {r: 16, alpha: 32}
conflict_fracs: [0.0, 0.25, 0.5, 0.75, 1.0]
durations: [1, 3, 6, 12]

output: {dir: results/llm_epistasis}