{
  "sources": [
    {
      "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/README.md",
      "quote": "What separates +4.26 from #1 is one call:** is the first trade of a step the arb or retail. The filter is wrong 16% of the time. With the true answer the same code scores +6.98, level with #1."
    },
    {
      "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/README.md",
      "quote": "Tune on replica seeds 60000 and up. Score once on 10000..12047 and report the `paired{...}` line `pair.py` gives against the nearest reference in `ref/`."
    },
    {
      "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/README.md",
      "quote": "Tried, no gain: forbidding the quote zone where the two overlap (`DP_MASK`, costs 0.6 to 2.4 with perfect information and leaves the error at 13 to 15%), buying more pins with tighter quotes (kappa above 1e-5 costs more than it returns), a quote-aware fill likelihood."
    },
    {
      "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/README.md",
      "quote": "A table classifier on the filter's own features gets 18.8% against the lattice's 16.2%, so the error is near what those features allow. Not tried: choosing quotes against the whole lattice posterior instead of its mean and sd, per-run estimates of sigma and order rate inside the classifier, the router likelihood per price hypothesis."
    },
    {
      "url": "https://raw.githubusercontent.com/gtmcknight/amm-sim/e65314f88de945f6d055bfc2aab01c482ab6570e/research/solved/run.py",
      "quote": "Any seed range, so long runs can be cut into chunks; pair.py joins and compares them."
    }
  ]
}