{
 "sources": [
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/latt.py",
   "quote": "Belief = probability mass on cells of width HC around a moving centre."
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/latt.py",
   "quote": "for _ in range(min(dt - 1, 30)):"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/latt.py",
   "quote": "if abs(self.m - self.c) > 40 * HC: self.recentre(self.m); self.m, self.v = self.moments()"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/latt.py",
   "quote": "s = sig / hc; M = int(math.ceil(4.0 * s))"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/README.md",
   "quote": "`latt.py` is the same policy with the Gaussian belief replaced by probability mass on 121 cells of 2.5 bps"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/README.md",
   "quote": "10000  448.261189  443.455598  443.522608  443.663520"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/README.md",
   "quote": "Paired gaps have matched the engine so far (HA over T: 1.11 here, 1.01 to 1.15 on the engine). Nothing here has run on the Rust engine."
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/README.md",
   "quote": "The filter is wrong 16% of the time."
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/real.py",
   "quote": "for _ in range(min(dt - 1, 12)):"
  },
  {
   "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/gates.py",
   "quote": "d = R.run(seed, latt.LatticePolicy(T, {'qm': QM}))['edge']"
  },
  {
   "url": "https://api.imd.fun/artifacts/8a6e303b662e1a5ea9bb47f31acedd3988ef65b3ddb66d074517aa59ad41ca40",
   "quote": "the reference gives 443.101741 / 571.454483 / 525.908441 on seeds 10000..10002, every printed digit equal to qm-spline's values."
  },
  {
   "url": "https://api.imd.fun/artifacts/8a6e303b662e1a5ea9bb47f31acedd3988ef65b3ddb66d074517aa59ad41ca40",
   "quote": "c68887cff61180e12ba2b1ceb333edf76a830f91f63b5d775a8806fb9ec08aca"
  },
  {
   "url": "https://api.imd.fun/artifacts/8a6e303b662e1a5ea9bb47f31acedd3988ef65b3ddb66d074517aa59ad41ca40",
   "quote": "The engine peak minus the pyrevm peak is 14,724, consistent with trim-2's ~15,000. That leaves 36,225 gas of margin under the 245,000 limit."
  },
  {
   "url": "https://api.imd.fun/artifacts/8a6e303b662e1a5ea9bb47f31acedd3988ef65b3ddb66d074517aa59ad41ca40",
   "quote": "each callback evaluates two spline surfaces at about 35–43k each"
  },
  {
   "url": "https://api.imd.fun/artifacts/8a6e303b662e1a5ea9bb47f31acedd3988ef65b3ddb66d074517aa59ad41ca40",
   "quote": "The synced flag is stored in bit 255 of slot 2"
  },
  {
   "url": "https://api.imd.fun/artifacts/17d249ab0c33fc44931d9b105cf3f9e3846a560bd518b67310c2a56defacdecc",
   "quote": "0.0632, se 0.0072, n = 2048"
  },
  {
   "url": "https://api.imd.fun/artifacts/17d249ab0c33fc44931d9b105cf3f9e3846a560bd518b67310c2a56defacdecc",
   "quote": "3ac7cb8811ecfb6a17f499aa4e9b70dd55f7fb6432b3aec3b904e11a3dece38e"
  }
 ]
}