{
 "tm": "1RB0LD_0RC1RA_1RD1RF_1LA0LE_0RA0LC_0RA---",
 "bucket_reason": "Parked by the stop rule: the left zone is safe in every generation computed but neither stable nor growing. A cheap way back in exists, so this is a priority call.",
 "question": "Keep #9 parked, as the stop rule says, or fund one stage to test whether its left zone settles into a 2-cycle across generations?",
 "options": [
  {
   "id": "park",
   "label": "Keep parked",
   "consequence": "Costs nothing. Everything stays in scripts/induct (the window map, validated on the real gen 1 to 2 step) for a later attempt, after the higher-confidence machines are done."
  },
  {
   "id": "cycle",
   "label": "One stage on the 2-cycle",
   "consequence": "About 2 h, 1-2 light processes. Iterate the window map to generation 10 or more with 3 window sizes. If generations g and g+2 agree on a zone that stops shrinking, write the invariant and go on to proof.md. Stop rule: if the agreement does not grow by gen 8, park for good."
  }
 ],
 "recommended": "park",
 "rationale": [
  "Stop rule hit: left-zone size went 50, 168, 96, 128, 212 cells over gens 2-6.",
  "Every zone tested is safe (0/80 nested); gens g and g-2 agree on 53, 91, 99 cells.",
  "A 2-cycle is plausible but unshown; other machines are closer to a kill."
 ],
 "evidence": [
  {
   "kind": "fact",
   "text": "Window map from the real gen-1 window reproduces all 12 real gen-2 left-zone events (6/6 runs, 11-12 blocks).",
   "href": "scripts/induct/val12seq.json"
  },
  {
   "kind": "fact",
   "text": "Predicted left zones, gens 3-6: raw prefix 168, 96, 128, 212 cells; gens g and g-2 agree on 53, 91, 99 cells.",
   "href": "scripts/induct/iter2_8_10_g7.json"
  },
  {
   "kind": "fact",
   "text": "Capacity: gen-3 zone 0/80 and gen-4 zone 0/80 nested events (real gen-2 zone: 22/200 nested DA).",
   "href": "scripts/induct/tcap_g3_R2.json"
  },
  {
   "kind": "figure",
   "text": "Fig 3: digit lines cross the reset walls without bending.",
   "href": "img/phase_1e9_left.png"
  }
 ],
 "effort_if_yes": "One stage (about 2 h). If the 2-cycle holds: proof.md, then exhaustive tile checks of both tables and a large formalization over several stages.",
 "updated": "2026-10-10",
 "answer": {
  "option": "park",
  "note": "Dennis: go with recommendations (2026-10-11)",
  "date": "2026-10-11"
 }
}