#!/usr/bin/env bash
# Batch 3 — decision rules and self-government, built on K=2 (best performer, cheapest).
# Config-only; no new code, so no new bug surface.
#
# Baselines (D=64, half evidence each unless noted):
#   K=2 mean/quorum ......... 10.9%   <- the configuration these vary from
#   K=4 mean/quorum .........  9.8%
#   K=4 confidence/quorum ...  4.7%   <- unequal influence halves performance
#   solo, half evidence .....  0.0%
set -uo pipefail
cd "$(dirname "$0")/.."

QUEUE=(
  # Discrete equal-weight rule: does one-unit-one-vote beat averaging logits?
  "colony-d64-k2-evihalf-vote|64|2|arch.blackboard=latent arch.standpoints=none arch.aggregate=vote arch.halt_rule=quorum arch.view_fraction=0.5"
  # Self-government: one member decides when the group stops deliberating.
  # Quorum halting already costs ~2 points; does concentrating that authority cost more?
  "colony-d64-k2-evihalf-boss|64|2|arch.blackboard=latent arch.standpoints=none arch.aggregate=mean arch.halt_rule=boss arch.view_fraction=0.5"
  # Completes the 2x2: two units, quarter evidence each (union no longer covers
  # the grid comfortably, so this is the most information-starved colony yet).
  "colony-d64-k2-evi25|64|2|arch.blackboard=latent arch.standpoints=none arch.aggregate=mean arch.halt_rule=quorum arch.view_fraction=0.25"
)

for entry in "${QUEUE[@]}"; do
  IFS='|' read -r name width k overrides <<< "$entry"
  echo "=== $(date -Is) starting ${name} ==="
  # shellcheck disable=SC2086
  PYTHONUNBUFFERED=1 PYTORCH_CUDA_ALLOC_CONF=expandable_segments:True \
  .venv/bin/python -m dsem.pretrain \
    arch=colony \
    data_paths="[data/sudoku-extreme-1k-aug-1000]" \
    data_paths_test="[data/sudoku-testsub-12k]" \
    evaluators="[]" \
    epochs=50000 eval_interval=5000 \
    global_batch_size=768 \
    lr=1e-4 puzzle_emb_lr=1e-4 weight_decay=1.0 puzzle_emb_weight_decay=1.0 \
    arch.mlp_t=True arch.pos_encodings=none \
    arch.L_layers=2 arch.H_cycles=3 arch.L_cycles=6 \
    "arch.hidden_size=${width}" "arch.num_agents=${k}" \
    ema=True "+run_name=${name}" \
    $overrides > "runs/${name}.out" 2>&1 < /dev/null
  echo "=== $(date -Is) finished ${name} ==="
done
echo "=== $(date -Is) queue3 complete ==="