{"sources":[{"url":"https://api.imdnotdead.fun/artifacts/2333ecf28d4356bd232b85c1e55842e94e1ada05e1cd067830b5625dfdbc5336","quote":"\"search_settings\":{\"method\":\"CMA-ES (pycma 4.x) over 219 = 178 head weights + 41 constants\",\"start\":\"CG's frozen weights and T's constants (fe2320 params.constants start values)\",\"weights\":\"w = w0 + 0.03 * rms(block) * z, blocks W1,b1,W2,b2\",\"constants\":\"c = c0 * 2^(0.02 z), exponent clipped to [-1,1]; decays d = 1-(1-d0)*2^(0.02 z); ELAPSED_CAP, DIR_IMPACT_MULT, STEP_COUNT_CAP, ANCHOR_COUNT_CAP r"},{"url":"https://api.imdnotdead.fun/artifacts/ebbd90c663c396598965b23341aea97a4501b4c971db183a8fe94a880f399979","quote":"\"port_sha256\":\"b29cd2a078b4c3fc57945a79e927624dd346c44d8cc149dae43f4929aa6d736b\",\"params\":{\"architecture\":\"19-8-2, ReLU clipped [0,4], inputs clipped [-4,4], output in bps added to T-path fees then clamped [0,MAX_FEE]; weights rounded to 1e-6, Solidity signed 1e6 fixed point\",\"feature_order\":[\"sigmaHat\",\"lambdaHat\",\"sizeHat\",\"toxEma\",\"actEma\",\"direction\",\"(spot-staleHat)/staleHat\",\"signed_trade_ra"},{"url":"https://api.imdnotdead.fun/artifacts/e8a7a2af9039c24b8bb2d3b5fa1c9113606cbf5a480ac07d02ca26750f1752ea","quote":"\"replica_source_sha256\": \"1e4c44b4bffbdeed65872ee15d46dbde209bf5aa11014329d13d100507b4040c\",\n  \"th_names\": [\n    \"ELAPSED_CAP\",\n    \"SIGNAL_THRESHOLD\",\n    \"DIR_DECAY\",\n    \"ACT_DECAY\",\n    \"SIZE_DECAY\",\n    \"TOX_DECAY\",\n    \"SIGMA_DECAY\",\n    \"LAMBDA_DECAY\",\n    \"SIZE_BLEND_DECAY\",\n    \"TOX_BLEND_DECAY\",\n    \"ACT_BLEND_DECAY\",\n    \"PHAT_ALPHA\",\n    \"PHAT_ALPHA_RETAIL\",\n    \"DIR_IMPACT_MULT\",\n    "},{"url":"https://api.imdnotdead.fun/artifacts/2801efc8190e86318dd922d4a7179f63684d77a226047fc2f3c78232963eb690","quote":"\"sha256\":\"99e3a2eceae0e5543d27473859e10b005d0ce0aa7067f2e1a24d1e0e4a7390fe\",\"real\":{\"chunks\":[{\"start\":6020000,\"n\":64,\"mean_diff\":1.1425077821720162},{\"start\":6020064,\"n\":64,\"mean_diff\":1.2991317911389402},{\"start\":6020128,\"n\":64,\"mean_diff\":1.540802036087534},{\"start\":6020192,\"n\":64,\"mean_diff\":0.9597960607904676},{\"start\":6020256,\"n\":64,\"mean_diff\":1.213708554548524},{\"start\":6020320,\"n\":64,\"mea"},{"url":"https://api.imdnotdead.fun/artifacts/6ac5e013b7b1fb4c5e7bdcdfec0aba28b16824e18ccf39500f258533879faffe","quote":"\"sha256\":\"ebd9de9bf6af6e55d5e308fd15dbb88edec11fd684891d02a30aec185acd19b3\",\"params\":{\"target\":\"toxEma\",\"TOX_DECAY\":\"910000000000000000\",\"k_linear\":0.7126960148076509,\"k_quadratic\":1.2952407538263107,\"N\":674,\"cma_seed\":45},\"log\":[{\"params\":[0.7606817830040726,0.8554320462623013,612],\"n\":64,\"mean_diff\":-0.36271454600530095,\"se\":0.054248159843225174,\"fitness\":-0.36271454600530095,\"valid\":true,\"seed_"},{"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 = (\n                rng.uniform(self.variance.retail_mean_size_min, self.variance.retail_mean_size_"},{"url":"https://raw.githubusercontent.com/benedictbrady/amm-challenge/6b6921f8d463314aa7c96234e1be25a25245f704/amm_competition/competition/config.py","quote":"BASELINE_VARIANCE = HyperparameterVariance(\n    retail_mean_size_min=19.0,\n    retail_mean_size_max=21.0,\n    vary_retail_mean_size=True,\n    retail_arrival_rate_min=0.6,\n    retail_arrival_rate_max=1.0,\n    vary_retail_arrival_rate=True,\n    gbm_sigma_min=0.000882,\n    gbm_sigma_max=0.001008,\n    vary_gbm_sigma=True,\n)\n\ndef _midpoint(min_val: float, max_val: float) -> float:\n    return (min_val +"},{"url":"https://raw.githubusercontent.com/benedictbrady/amm-challenge/6b6921f8d463314aa7c96234e1be25a25245f704/amm_sim_rs/src/types/result.rs","quote":"    /// Edge by strategy name (sum over trades)\n    #[pyo3(get)]\n    pub edges: HashMap<String, f64>,\n\n    /// Initial fair price\n    #[pyo3(get)]\n    pub initial_fair_price: f64,\n\n    /// Initial reserves by strategy name: (reserve_x, reserve_y)\n    #[pyo3(get)]\n    pub initial_reserves: HashMap<String, (f64, f64)>,\n\n    /// Step results for charting\n    #[pyo3(get)]\n    pub steps: Vec<Lightweigh"},{"url":"https://raw.githubusercontent.com/benedictbrady/amm-challenge/6b6921f8d463314aa7c96234e1be25a25245f704/amm_sim_rs/src/simulation/engine.rs","quote":"            // 2. Arbitrageur extracts profit from each AMM\n            for amm in amms.iter_mut() {\n                if let Some(arb_result) = arbitrageur.execute_arb(amm, fair_price, t as u64) {\n                    *arb_volume_y.get_mut(&arb_result.amm_name).unwrap() += arb_result.amount_y;\n                    let entry = edges.entry(arb_result.amm_name).or_insert(0.0);\n                    // AMM"}]}