experiment: llm_speciation
kind: llm_speciation
seed: 1
n_replicates: 1

# LLM-tier model speciation (E13 in language-model weights; PNAS work order Phase 3). Two LoRA
# children from the same frozen base — which controls a major source of coordinate mismatch (no
# alignment step needed), allowing a cleaner test of conflict-associated merge failure. Two sweeps:
#   conflict_fracs — the IMPOSED cliff: each child has a private disjoint family (A: strings,
#     B: arith) plus a shared set of AMBIGUOUS sort prompts ("Sort the list [...]", no direction)
#     answered ascending by A and descending by B (each convention harmless alone, contradictory
#     jointly — the BDM structure). Prediction: the MERGED model's private-family competence degrades
#     and its convention coherence (max of asc/desc grading) collapses as conflict grows, while each
#     PARENT stays fine — hybrid breakdown in verifier units, echoing the MLP cliff.
#   durations — the EMERGENT null: pure disjoint specialists over-trained (epochs swept), zero shared
#     data. Arbitrates the MLP tier's null (no emergent isolation; the merge rescued specialists at
#     every divergence) against the empirical report that averaging prefers under-trained experts
#     (arXiv:2607.11997). Pre-registered readings: merged quality falls with duration while parents'
#     own-family quality holds -> emergent incompatibility at the LLM tier; otherwise the null
#     generalises. 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: 100
epochs: 3
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_speciation}