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

# The de-confounded conflict sweep (companion to configs/llm/speciation.yaml). The "replace" design
# holds TOTAL training fixed, so the merge's private-family decline with conflict_frac is confounded
# with shrinking private data (coherence is the clean readout there). Here conflict_mode: add holds
# each child's PRIVATE training fixed at n_train and ADDS conflict data on top, so any decline in the
# MERGE's private-family accuracy relative to its parents is interference from the conflicting
# convention, not a data-budget artefact. Pre-registered readings: merged private accuracy tracks the
# parents at every frac -> conflict damage is localised to the conflicted function (function-specific
# hybrid breakdown); merged private accuracy falls below the parents as frac rises -> the conflict
# corrupts shared circuitry beyond the conflicted function (global hybrid breakdown). Run at 3 seeds:
# the single-seed pilot showed one anomalous grid point (frac=0.75, a bad parent-B run), so per-seed
# replication is required before reading the curve.

base_model: Qwen/Qwen2.5-0.5B-Instruct
family_a: strings
family_b: arith
n_train: 400
n_test: 100
epochs: 3
lora: {r: 16, alpha: 32}
conflict_mode: add
conflict_fracs: [0.0, 0.25, 0.5, 0.75, 1.0]
durations: []

output: {dir: results/llm_speciation_add}