{"sources":[{"url":"https://api.imd.fun/artifacts/ffd2b2488b92fe51e639af36007feabbf15c3df3c119bf957d460e1be42efa34","quote":"Outcome: **PASS**. The gas rule selected **GATE = 4**. The frozen contract validates, is 22,370 runtime bytes, passes F with maximum effective-fee error `3.087157057768408e-06` bps, has engine peak 229,596 gas with 0 OOG, and scores a paired `+0.704218513630746` edge over qt1 on the required 16 fres"},{"url":"https://api.imd.fun/artifacts/a2d5a0dea7982a84bd2238f143f045b44600c35ac5638d2307fdeadc15bfc757","quote":"\"W_frozen\":[-0.026618487,-0.070207473,-0.010260029,-0.039506307,-0.031319086,-0.024026954,-0.010362795,-0.026501258,-0.092376172,0.065727168,-0.0234922,0.048898344,0.025732963,-0.003616139,-0.0396233,-0.007869716,0.004707838,0.044162589],\"W_exact\":\"state FROZEN_W.json, sha256 6aa54280e9b31560d0fb913"},{"url":"https://api.imd.fun/artifacts/70ece52dd649c2b5f1085dfca6e77046a53ab8929f0e3e11875fd33a9fe0c2e4","quote":"{\"GATE\":4,\"label\":\"4\",\"vs_qt1_ref\":{\"n\":2048,\"mean_diff\":0.601755886,\"se\":0.013533815,\"worst5\":[[10146,-3.646769299],[11062,-2.324024168],[11808,-1.86874264],[10519,-1.839589919],[11376,-1.784058107]]},\"vs_TwoComp\":{\"n\":2048,\"mean_diff\":0.176953002,\"se\":0.010784215,\"worst5\":[[11695,-1.721534604],[10"},{"url":"https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/contracts/Candidate.sol","quote":"// Two-component posterior port; credit Taylor (gtmcknight) for policy, filter and tables.\n// Policy: Taylor's (gtmcknight) solved game, amm-sim 4812a638, research/solved: Gaussian filter (real.py) + qm tables\n// (qm_k1e-5.json, +3.77 vs HA on Taylor's replica). Filter, state and timing from trim-1 "},{"url":"https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/reference/qt1/Strategy.sol","quote":"// Solved AMM policy by Taylor (gtmcknight), amm-sim 4812a638 research/solved: Gaussian filter + qm tables (qm_k1e-5.json),\n// fee rule of real.py's qm variant (sd level, phase, synced flag). All credit for the policy, filter and tables: Taylor.\n// Tables compressed by qm-spline (cubic B-splines, QM"},{"url":"https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/reference/qt1/qmref.py","quote":"\"\"\"qt1 reference: Taylor's (gtmcknight) Gaussian filter (as port-3's standalone.Coarse / trim-2) + real.py's qm fee\nrule over the DECODED qm-spline tables (QMS1 blob, sha256 3ac7cb88...). Standard library only.\nusage: from qmref import QMRef; QMRef('blob.bin') is a replica2 policy (wants_j).\nInit fe"},{"url":"https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/reference/qt1/blob.bin","quote":"QMS1"},{"url":"https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/reference/twocomp/twocomp.py","quote":"# Two-component lattice substitute, adapted from qt1 and Taylor (gtmcknight).\n\"\"\"qt1 reference: Taylor's (gtmcknight) Gaussian filter (as port-3's standalone.Coarse / trim-2) + real.py's qm fee\nrule over the DECODED qm-spline tables (QMS1 blob, sha256 3ac7cb88...). Standard library only.\nusage: from"},{"url":"https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/tools/check.py","quote":"\"\"\"Gate F effective-fee replay, adapted from SP replay.py.\nCredit: Taylor (gtmcknight), Gaussian filter, qm tables and replica.\nSeed ranges are half-open. Run from a prepared amm-challenge checkout.\n\"\"\"\nimport argparse\nimport hashlib\nimport importlib\nimport json\nfrom pathlib import Path\nimport sys\ni"},{"url":"https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/tools/engine.py","quote":"def configs(start,end):\n    # _build_configs seeds parameter variability with np.default_rng(i).\n    # Build through end, then select assigned fresh seeds, so the config\n    # for seed i is exactly the one MatchRunner would build for i.\n    # Equivalent direct transcription avoids allocating 9.5M co"},{"url":"https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/README.md","quote":"Replica levels do not convert to board scores. 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.\n\nThis replaces the reading in `../filter-brief.md`: the perfect-price table there was a search result, not a ceiling."},{"url":"https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/gates.py","quote":"for seed in (10000, 10001, 10002):\n    a = R.run(seed, DPPolicy(T))['edge']\n    b = R.run(seed, real.RealPolicy(T, {'soft': 1.0}))['edge']\n    c = R.run(seed, real.RealPolicy(T, {'soft': 1.0, 'qm': QM}))['edge']\n    d = R.run(seed, latt.LatticePolicy(T, {'qm': QM}))['edge']\n    print(f'{seed}  {a:.6"},{"url":"https://raw.githubusercontent.com/gtmcknight/amm-sim/4812a6382311624e1506aca131ca35c378f930d9/research/solved/replica2.py","quote":"def run(seed, policy, n_steps=10000, cfg=None, qcap=None):\n    cr = random.Random(10_000_000 + seed)\n    size_mean = cr.uniform(19.0, 21.0)\n    lam = cr.uniform(0.6, 1.0)\n    sigma = cr.uniform(0.000882, 0.001008)\n    if cfg:\n        size_mean, lam, sigma = cfg\n    pr = random.Random(seed)\n    rr = "},{"url":"https://raw.githubusercontent.com/benedictbrady/amm-challenge/6b6921f8d463314aa7c96234e1be25a25245f704/amm_competition/competition/match.py","quote":"    def _build_configs(self) -> list[amm_sim_rs.SimulationConfig]:\n        \"\"\"Build simulation configs with optional variance.\"\"\"\n        import numpy as np\n\n        configs = []\n        for i in range(self.n_simulations):\n            rng = np.random.default_rng(seed=i)\n\n            retail_mean_size"},{"url":"https://raw.githubusercontent.com/benedictbrady/amm-challenge/6b6921f8d463314aa7c96234e1be25a25245f704/amm_competition/evm/compiler.py","quote":"    SOLC_VERSION = \"0.8.24\"\n\n    # Path to the contracts directory with base contracts\n    CONTRACTS_DIR = Path(__file__).parent.parent.parent / \"contracts\"\n    CONTRACTS_SRC_DIR = CONTRACTS_DIR / \"src\"\n\n    # Opcodes we never allow in user runtime bytecode.\n    FORBIDDEN_OPCODES = {\n        0x31: \""},{"url":"https://raw.githubusercontent.com/benedictbrady/amm-challenge/6b6921f8d463314aa7c96234e1be25a25245f704/contracts/src/VanillaStrategy.sol","quote":"contract VanillaStrategy is AMMStrategyBase {\n    /// @notice Fixed fee in WAD (30 bps = 0.30% = 30e14)\n    uint256 public constant FEE = 30 * BPS;\n\n    /// @inheritdoc IAMMStrategy\n    function afterInitialize(uint256, uint256) external pure override returns (uint256 bidFee, uint256 askFee) {\n     "},{"url":"https://api.imd.fun/artifacts/d360bea6c8c982717b7b43a8069a87013169c89ee3e4da25622db4d880b936d4","quote":"# combo-offsets: two-component filter + weighted-average offset quoting (COMBO)\n\nCredit: the replica (`replica2.py`), the Gaussian filter, the fee rule and the qm tables are by Taylor (gtmcknight), [amm-sim `research/solved` @4812a638](https://github.com/gtmcknight/amm-sim/tree/4812a6382311624e1506a"}]}