{
 "sources": [
  {
   "url": "https://api.imd.fun/artifacts/efb8e653f8fd061cecf3e92b186470c9c96c5188523364b60ed101e9672869aa",
   "quote": "original replica, Gaussian filter, posterior policy and qm tables. Lean tell from the credited lb-4 artifact."
  },
  {
   "url": "https://api.imd.fun/artifacts/efb8e653f8fd061cecf3e92b186470c9c96c5188523364b60ed101e9672869aa",
   "quote": "ba015769f7981d7798acbbc9aff8c0e0c59825bb1541d55bcdef49311d7a04bc"
  },
  {
   "url": "https://api.imd.fun/artifacts/365a3649ce37f66bc4e333f84457aa84d2ae5e5f677d8a580481d3a2f84c76f2",
   "quote": "Cheap split test: quotient.py/qbase.py router-quotient test re-ordered cheapest-candidate-first and stopped at a binary64 operation cap (16, 24, 40); capped out = miss (BASE unchanged on a miss, qbase update on a hit)."
  },
  {
   "url": "https://api.imd.fun/artifacts/365a3649ce37f66bc4e333f84457aa84d2ae5e5f677d8a580481d3a2f84c76f2",
   "quote": "\"mean_diff\":0.04056,\"se\":0.00368,\"min\":-2.3311"
  },
  {
   "url": "https://api.imd.fun/artifacts/365a3649ce37f66bc4e333f84457aa84d2ae5e5f677d8a580481d3a2f84c76f2",
   "quote": "z = r: d = gamma + z*0.997 [mul,addsub]; n = round_half_even(paid*d/grid) [mul,div,round]; HIT if trunc(((n*grid)/d)*1e18) == paid_w [mul,div,wad_check] -> 22"
  },
  {
   "url": "https://api.imd.fun/artifacts/88712dac0e4b048a0860ccb13d2f22e13d956161c102939cb480f53388f3b185",
   "quote": "Small positive, below the 0.2 bar: frozen variant - BASE = +0.0443 se 0.0039 on holdout 10000..12047 (n 2048)."
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/66604b3426d8e97a73e2c39940b9b4dece51cc73/research/tell/fetch.sh",
   "quote": "# Fetch ../solved and this folder into ONE directory and check every file's sha256."
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/66604b3426d8e97a73e2c39940b9b4dece51cc73/research/solved/replica2.py",
   "quote": "Pure-Python replica of benedictbrady/amm-challenge @6b6921f8 (engine.rs, cfmm.rs,"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/66604b3426d8e97a73e2c39940b9b4dece51cc73/research/solved/run.py",
   "quote": "A blind policy never receives the true price, the rival's spot, the arb flag, the order count or the run's"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/66604b3426d8e97a73e2c39940b9b4dece51cc73/research/solved/real.py",
   "quote": "Solved policy driven ONLY by what afterSwap sees (side, amounts, timestamp, reserves)."
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/README.md",
   "quote": "An exact dynamic program for the game with perfect information, the policy it gives, and reference code that runs that policy on what `afterSwap` really sees."
  }
 ]
}