{
 "approach": "Kalman-filter variance on YQ's fair-price estimate, used as an innovation gate. slot11 v (relative variance of pHat) grows by sigmaHat^2 on each new step and shrinks by (1-0.26) after an accepted first-in-step print. A print is rejected when ret^2 > 4*(v + r*sigmaHat^2), with r=11 for the first print in a step and r=25 for later prints. This replaces YQ's gate, max(10*sigmaHat, 3%). Making the gain adaptive (gain = v/(v+r)) lost 1.5 to 11 edge in every grid point, and so did the c*sqrt(v) widening term. YQ's fee coefficients appear tuned to a constant-gain pHat, so only the gate was kept.",
 "tried": [
  {
   "variant": "full Kalman gain, r=R*sigmaHat^2, R1=11,R2=200, gate 16, uncapped elapsed",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -5.222,
   "se": 0.043
  },
  {
   "variant": "full Kalman R1=11,R2=100",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -4.776,
   "se": 0.041
  },
  {
   "variant": "full Kalman R1=5,R2=200",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -10.86,
   "se": 0.06
  },
  {
   "variant": "full Kalman R1=20,R2=200",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -3.914,
   "se": 0.036
  },
  {
   "variant": "full Kalman R1=11,R2=1000",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -5.787,
   "se": 0.045
  },
  {
   "variant": "full Kalman R1=40,R2=100",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -5.49,
   "se": 0.039
  },
  {
   "variant": "full Kalman R1=80,R2=100",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -10.573,
   "se": 0.052
  },
  {
   "variant": "full Kalman R1=40,R2=40",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -9.247,
   "se": 0.049
  },
  {
   "variant": "full Kalman R1=20,R2=100, v grows by at most 1 step per print (VCAP=1)",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -2.621,
   "se": 0.029
  },
  {
   "variant": "full Kalman R1=11,R2=200,VCAP=1",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -2.178,
   "se": 0.027
  },
  {
   "variant": "full Kalman R1=11,R2=55,VCAP=1 (YQ-equivalent steady-state gains)",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -1.563,
   "se": 0.024
  },
  {
   "variant": "same, gate off",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -2.779,
   "se": 0.038
  },
  {
   "variant": "same, VCAP=2",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -2.736,
   "se": 0.029
  },
  {
   "variant": "full Kalman R1=8,R2=40,VCAP=1",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -1.708,
   "se": 0.024
  },
  {
   "variant": "full Kalman R1=15,R2=80,VCAP=1",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -1.9,
   "se": 0.026
  },
  {
   "variant": "Kalman gain, later prints do not shrink v, R1=11,R2=55,VCAP=1",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -1.723,
   "se": 0.025
  },
  {
   "variant": "same, VCAP=4",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -4.19,
   "se": 0.036
  },
  {
   "variant": "same, VCAP=64",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -4.735,
   "se": 0.041
  },
  {
   "variant": "fixed r (units 1e-6 rel var) R1=11,R2=55",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -39.687,
   "se": 0.195
  },
  {
   "variant": "fixed r R1=100,R2=500",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -3.556,
   "se": 0.053
  },
  {
   "variant": "fixed r R1=250,R2=1250",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -1.491,
   "se": 0.043
  },
  {
   "variant": "fixed r R1=600,R2=3000",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -3.531,
   "se": 0.033
  },
  {
   "variant": "widening c*sqrt(v)/pHat, c=0.1 (Kalman R1=11,R2=55,VCAP=1)",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -6.76,
   "se": 0.049
  },
  {
   "variant": "widening c=0.3",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -74.36,
   "se": 0.314
  },
  {
   "variant": "widening c=0.2 on gate-only variant",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -22.555,
   "se": 0.105
  },
  {
   "variant": "YQ fixed alphas 0.26/0.05 + Kalman innovation gate only, R1=11,R2=55, gate off (sanity: removing YQ gate)",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -1.498,
   "se": 0.029
  },
  {
   "variant": "gate-only GATE=64",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -1.349,
   "se": 0.026
  },
  {
   "variant": "gate-only GATE=16",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -0.644,
   "se": 0.017
  },
  {
   "variant": "gate-only GATE=9",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -0.24,
   "se": 0.011
  },
  {
   "variant": "gate-only GATE=6",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": 0.004,
   "se": 0.011
  },
  {
   "variant": "gate-only GATE=4",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": 0.144,
   "se": 0.015
  },
  {
   "variant": "gate-only GATE=3",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": 0.129,
   "se": 0.018
  },
  {
   "variant": "gate-only GATE=2",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": -0.054,
   "se": 0.022
  },
  {
   "variant": "gate-only GATE=4,R2=120",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": 0.103,
   "se": 0.015
  },
  {
   "variant": "gate-only GATE=4,VCAP=2",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": 0.139,
   "se": 0.014
  },
  {
   "variant": "FINAL gate-only GATE=4,R1=11,R2=25,VCAP=1",
   "tuning_seeds": "0..1999",
   "n": 2000,
   "mean_diff": 0.154,
   "se": 0.014
  }
 ],
 "next": [
  "Retune YQ fee coefficients (tox/stale) jointly with a true adaptive Kalman gain; the gain alone loses because fees were fit to constant-alpha pHat.",
  "Use the no-arb-in-gap signal as a censored observation (fair price inside band) to shrink v without moving pHat.",
  "Fine-grid KF_GATE in 3..5 and R1 with a separate gate multiplier for first vs later prints; replicate on another fresh block."
 ],
 "code": "// SPDX-License-Identifier: MIT\npragma solidity ^0.8.24;\n\nimport {AMMStrategyBase} from \"./AMMStrategyBase.sol\";\nimport {TradeInfo} from \"./IAMMStrategy.sol\";\n\ncontract Strategy is AMMStrategyBase {\n    // --- decay / update constants ---\n    uint256 constant ELAPSED_CAP = 8;\n    uint256 constant SIGNAL_THRESHOLD = WAD / 500; // ~20 bps of reserve\n    uint256 constant DIR_DECAY = 800000000000000000; // 0.80\n    uint256 constant ACT_DECAY = 700000000000000000; // 0.70\n    uint256 constant SIZE_DECAY = 700000000000000000; // 0.70\n    uint256 constant TOX_DECAY = 910000000000000000; // 0.91\n    uint256 constant SIGMA_DECAY = 824000000000000000; // 0.824\n    uint256 constant LAMBDA_DECAY = 990000000000000000; // 0.99\n    uint256 constant SIZE_BLEND_DECAY = 818000000000000000; // 0.818\n    uint256 constant TOX_BLEND_DECAY = 51000000000000000; // 0.051\n    uint256 constant ACT_BLEND_DECAY = 985000000000000000; // 0.985\n    uint256 constant PHAT_ALPHA = 260000000000000000; // 0.26\n    uint256 constant PHAT_ALPHA_RETAIL = 50000000000000000; // 0.05\n    uint256 constant KF_R1 = 11; // first-in-step obs noise, in sigmaHat^2 units\n    uint256 constant KF_R2 = 25; // later-in-step obs noise, in sigmaHat^2 units\n    uint256 constant KF_GATE = 4; // reject if innov^2 > GATE*(v+r)\n    uint256 constant DIR_IMPACT_MULT = 2;\n\n    // --- Cubic Toxicity ---\n    uint256 constant TOX_CUBIC_COEF = 15000 * BPS;\n\n    // --- Trade-Tox Boost ---\n    uint256 constant TRADE_TOX_BOOST = 2500 * BPS;\n\n    // --- Asymmetric Stale Dir ---\n    uint256 constant STALE_ATTRACT_FRAC = 1124000000000000000; // 1.124\n\n    // --- state caps ---\n    uint256 constant RET_CAP = WAD / 10; // 10%\n    uint256 constant TOX_CAP = WAD / 5; // 20%\n    uint256 constant TRADE_RATIO_CAP = WAD / 5; // 20%\n    uint256 constant LAMBDA_CAP = 5 * WAD; // max 5 trades/step estimate\n    uint256 constant STEP_COUNT_CAP = 64; // guardrail\n\n    // --- fee model constants ---\n    uint256 constant BASE_FEE = 3 * BPS;\n    uint256 constant SIGMA_COEF = 200000000000000000; // 0.20\n    uint256 constant LAMBDA_COEF = 12 * BPS;\n    uint256 constant FLOW_SIZE_COEF = 4842 * BPS;\n    uint256 constant TOX_COEF = 250 * BPS;\n    uint256 constant TOX_QUAD_COEF = 11700 * BPS;\n    uint256 constant ACT_COEF = 91843 * BPS;\n    uint256 constant DIR_COEF = 20 * BPS;\n    uint256 constant DIR_TOX_COEF = 100 * BPS;\n    uint256 constant STALE_DIR_COEF = 6850 * BPS;\n    uint256 constant SIGMA_TOX_COEF = 500 * BPS;\n    uint256 constant TAIL_KNEE = 500 * BPS;\n    uint256 constant TAIL_SLOPE_PROTECT = 930000000000000000; // 0.93\n    uint256 constant TAIL_SLOPE_ATTRACT = 955000000000000000; // 0.955\n\n    // slots[0] = bid fee\n    // slots[1] = ask fee\n    // slots[2] = last timestamp\n    // slots[3] = dirState (centered at WAD, [0, 2*WAD])\n    // slots[4] = actEma\n    // slots[5] = pHat\n    // slots[6] = sigmaHat\n    // slots[7] = lambdaHat\n    // slots[8] = sizeHat\n    // slots[9] = toxEma\n    // slots[10] = stepTradeCount (raw integer)\n    // slots[11] = kfVar (relative variance of pHat, WAD)\n\n    function afterInitialize(uint256 initialX, uint256 initialY) external override returns (uint256, uint256) {\n        slots[0] = BASE_FEE;\n        slots[1] = BASE_FEE;\n        slots[2] = 0;\n        slots[3] = WAD; // neutral direction\n        slots[4] = 0;\n        slots[5] = initialX > 0 ? wdiv(initialY, initialX) : 100 * WAD;\n        slots[6] = 950000000000000; // 0.095% initial sigma guess\n        slots[7] = 800000000000000000; // 0.8 initial arrival-rate guess\n        slots[8] = 2000000000000000; // 0.2% reserve-size ratio guess\n        slots[9] = 0;\n        slots[10] = 0;\n        slots[11] = 10 * wmul(slots[6], slots[6]);\n        return (BASE_FEE, BASE_FEE);\n    }\n\n    function afterSwap(TradeInfo calldata trade) external override returns (uint256, uint256) {\n        uint256 prevBidFee = slots[0];\n        uint256 prevAskFee = slots[1];\n        uint256 lastTs = slots[2];\n        uint256 dirState = slots[3];\n        uint256 actEma = slots[4];\n        uint256 pHat = slots[5];\n        uint256 sigmaHat = slots[6];\n        uint256 lambdaHat = slots[7];\n        uint256 sizeHat = slots[8];\n        uint256 toxEma = slots[9];\n        uint256 stepTradeCount = slots[10];\n        uint256 kfVar = slots[11];\n\n        bool isNewStep = trade.timestamp > lastTs;\n        if (isNewStep) {\n            uint256 elapsedRaw = trade.timestamp - lastTs;\n            uint256 elapsed = elapsedRaw > ELAPSED_CAP ? ELAPSED_CAP : elapsedRaw;\n\n            dirState = _decayCentered(dirState, DIR_DECAY, elapsed);\n            actEma = wmul(actEma, _powWad(ACT_DECAY, elapsed));\n            sizeHat = wmul(sizeHat, _powWad(SIZE_DECAY, elapsed));\n            toxEma = wmul(toxEma, _powWad(TOX_DECAY, elapsed));\n\n            if (stepTradeCount > 0 && elapsedRaw > 0) {\n                uint256 lambdaInst = (stepTradeCount * WAD) / elapsedRaw;\n                if (lambdaInst > LAMBDA_CAP) lambdaInst = LAMBDA_CAP;\n                lambdaHat = wmul(lambdaHat, LAMBDA_DECAY) + wmul(lambdaInst, WAD - LAMBDA_DECAY);\n            }\n\n            stepTradeCount = 0;\n            kfVar = kfVar + wmul(sigmaHat, sigmaHat);\n        }\n\n        bool firstInStep = stepTradeCount == 0;\n\n        uint256 spot = trade.reserveX > 0 ? wdiv(trade.reserveY, trade.reserveX) : pHat;\n        if (pHat == 0) pHat = spot;\n\n        uint256 feeUsed = trade.isBuy ? prevBidFee : prevAskFee;\n        uint256 gamma = feeUsed < WAD ? WAD - feeUsed : 0;\n        uint256 pImplied;\n        if (gamma == 0) {\n            pImplied = spot;\n        } else {\n            pImplied = trade.isBuy ? wmul(spot, gamma) : wdiv(spot, gamma);\n        }\n\n        {\n            uint256 ret = pHat > 0 ? wdiv(absDiff(pImplied, pHat), pHat) : 0;\n            uint256 kfR = (firstInStep ? KF_R1 : KF_R2) * wmul(sigmaHat, sigmaHat);\n            uint256 kfS = kfVar + kfR;\n            if (kfS > 0 && wmul(ret, ret) <= KF_GATE * kfS) {\n                uint256 gain = firstInStep ? PHAT_ALPHA : PHAT_ALPHA_RETAIL;\n                pHat = wmul(pHat, WAD - gain) + wmul(pImplied, gain);\n                if (firstInStep) kfVar = wmul(kfVar, WAD - gain);\n            }\n            if (firstInStep) {\n                if (ret > RET_CAP) ret = RET_CAP;\n                sigmaHat = wmul(sigmaHat, SIGMA_DECAY) + wmul(ret, WAD - SIGMA_DECAY);\n            }\n        }\n\n        uint256 tradeRatio = trade.reserveY > 0 ? wdiv(trade.amountY, trade.reserveY) : 0;\n        if (tradeRatio > TRADE_RATIO_CAP) tradeRatio = TRADE_RATIO_CAP;\n\n        if (tradeRatio > SIGNAL_THRESHOLD) {\n            uint256 push = tradeRatio * DIR_IMPACT_MULT;\n            if (push > WAD / 4) push = WAD / 4;\n\n            if (trade.isBuy) {\n                dirState = dirState + push;\n                if (dirState > 2 * WAD) dirState = 2 * WAD;\n            } else {\n                dirState = dirState > push ? dirState - push : 0;\n            }\n\n            actEma = wmul(actEma, ACT_BLEND_DECAY) + wmul(tradeRatio, WAD - ACT_BLEND_DECAY);\n\n            sizeHat = wmul(sizeHat, SIZE_BLEND_DECAY) + wmul(tradeRatio, WAD - SIZE_BLEND_DECAY);\n            if (sizeHat > WAD) sizeHat = WAD;\n        }\n\n        uint256 tox = pHat > 0 ? wdiv(absDiff(spot, pHat), pHat) : 0;\n        if (tox > TOX_CAP) tox = TOX_CAP;\n        toxEma = wmul(toxEma, TOX_BLEND_DECAY) + wmul(tox, WAD - TOX_BLEND_DECAY);\n        uint256 toxSignal = toxEma;\n\n        stepTradeCount = stepTradeCount + 1;\n        if (stepTradeCount > STEP_COUNT_CAP) stepTradeCount = STEP_COUNT_CAP;\n\n        uint256 flowSize = wmul(lambdaHat, sizeHat);\n        uint256 fBase = BASE_FEE + wmul(SIGMA_COEF, sigmaHat) + wmul(LAMBDA_COEF, lambdaHat) + wmul(FLOW_SIZE_COEF, flowSize);\n        uint256 fMid = fBase + wmul(TOX_COEF, toxSignal) + wmul(TOX_QUAD_COEF, wmul(toxSignal, toxSignal)) + wmul(ACT_COEF, actEma);\n\n        fMid = fMid + wmul(SIGMA_TOX_COEF, wmul(sigmaHat, toxSignal));\n\n        // Cubic toxicity\n        {\n            uint256 toxCubed = wmul(toxSignal, wmul(toxSignal, toxSignal));\n            fMid = fMid + wmul(TOX_CUBIC_COEF, toxCubed);\n        }\n\n        uint256 dirDev;\n        bool sellPressure;\n        if (dirState >= WAD) {\n            dirDev = dirState - WAD;\n            sellPressure = true;\n        } else {\n            dirDev = WAD - dirState;\n            sellPressure = false;\n        }\n\n        uint256 skew = wmul(DIR_COEF, dirDev) + wmul(DIR_TOX_COEF, wmul(dirDev, toxSignal));\n\n        uint256 bidFee;\n        uint256 askFee;\n        if (sellPressure) {\n            bidFee = fMid + skew;\n            askFee = fMid > skew ? fMid - skew : 0;\n        } else {\n            askFee = fMid + skew;\n            bidFee = fMid > skew ? fMid - skew : 0;\n        }\n\n        // Directional protection using stale-price sign\n        {\n            uint256 staleShift = wmul(STALE_DIR_COEF, toxSignal);\n            uint256 attractShift = wmul(staleShift, STALE_ATTRACT_FRAC);\n            if (spot >= pHat) {\n                bidFee = bidFee + staleShift;\n                askFee = askFee > attractShift ? askFee - attractShift : 0;\n            } else {\n                askFee = askFee + staleShift;\n                bidFee = bidFee > attractShift ? bidFee - attractShift : 0;\n            }\n        }\n\n        // Trade-aligned toxicity boost\n        {\n            bool tradeAligned = (trade.isBuy && spot >= pHat) || (!trade.isBuy && spot < pHat);\n            if (tradeAligned) {\n                uint256 tradeBoost = wmul(TRADE_TOX_BOOST, tradeRatio);\n                if (trade.isBuy) {\n                    bidFee = bidFee + tradeBoost;\n                } else {\n                    askFee = askFee + tradeBoost;\n                }\n            }\n        }\n\n        // Asymmetric tail compression\n        if (sellPressure) {\n            bidFee = clampFee(_compressTailWithSlope(bidFee, TAIL_SLOPE_PROTECT));\n            askFee = clampFee(_compressTailWithSlope(askFee, TAIL_SLOPE_ATTRACT));\n        } else {\n            askFee = clampFee(_compressTailWithSlope(askFee, TAIL_SLOPE_PROTECT));\n            bidFee = clampFee(_compressTailWithSlope(bidFee, TAIL_SLOPE_ATTRACT));\n        }\n\n        slots[0] = bidFee;\n        slots[1] = askFee;\n        slots[2] = trade.timestamp;\n        slots[3] = dirState;\n        slots[4] = actEma;\n        slots[5] = pHat;\n        slots[6] = sigmaHat;\n        slots[7] = lambdaHat;\n        slots[8] = sizeHat;\n        slots[9] = toxEma;\n        slots[10] = stepTradeCount;\n        slots[11] = kfVar;\n\n        return (bidFee, askFee);\n    }\n\n    function _compressTailWithSlope(uint256 fee, uint256 slope) internal pure returns (uint256) {\n        if (fee <= TAIL_KNEE) return fee;\n        return TAIL_KNEE + wmul(fee - TAIL_KNEE, slope);\n    }\n\n    function _powWad(uint256 factor, uint256 exp) internal pure returns (uint256 result) {\n        result = WAD;\n        while (exp > 0) {\n            if (exp & 1 == 1) result = wmul(result, factor);\n            factor = wmul(factor, factor);\n            exp >>= 1;\n        }\n    }\n\n    function _decayCentered(uint256 centered, uint256 decayFactor, uint256 elapsed) internal pure returns (uint256) {\n        uint256 mul = _powWad(decayFactor, elapsed);\n        if (centered >= WAD) {\n            return WAD + wmul(centered - WAD, mul);\n        }\n        uint256 below = wmul(WAD - centered, mul);\n        return below < WAD ? WAD - below : 0;\n    }\n\n    function getName() external pure override returns (string memory) {\n        return \"yq-kalman\";\n    }\n}\n",
 "code_sha256": "30703dfda680d18a05b9a6b903c46efcd3734fae5571aa51a88829065c4b391b",
 "delta": "From YQ: (1) delete GATE_SIGMA_MULT and MIN_GATE; add constants KF_R1=11, KF_R2=25, KF_GATE=4. (2) afterInitialize: slots[11]=10*wmul(slots[6],slots[6]). (3) afterSwap: load kfVar=slots[11]; in the isNewStep block after stepTradeCount=0 add kfVar=kfVar+wmul(sigmaHat,sigmaHat). (4) Replace the alpha/adaptiveGate/if(ret<=adaptiveGate) block with: kfR=(firstInStep?KF_R1:KF_R2)*wmul(sigmaHat,sigmaHat); kfS=kfVar+kfR; if(kfS>0 && wmul(ret,ret)<=KF_GATE*kfS){gain=firstInStep?PHAT_ALPHA:PHAT_ALPHA_RETAIL; pHat=wmul(pHat,WAD-gain)+wmul(pImplied,gain); if(firstInStep) kfVar=wmul(kfVar,WAD-gain);} (5) store slots[11]=kfVar; getName returns \"yq-kalman\".",
 "score": {
  "n": 1000,
  "mean_edge": 524.7803,
  "se": 2.7851,
  "seed_start": 0,
  "paired_vs_YQ_same_seeds": {
   "mean_diff": 0.1532,
   "se": 0.0189
  }
 },
 "paired": {
  "reference": "YQ 00fae418",
  "seed_start": 400000,
  "n": 2000,
  "mean_diff": 0.1961,
  "se": 0.0142,
  "mean_candidate": 523.2713,
  "mean_reference": 523.0752,
  "worst": [
   {
    "seed": 401973,
    "diff": -3.775
   },
   {
    "seed": 401718,
    "diff": -3.1707
   },
   {
    "seed": 400497,
    "diff": -2.6674
   },
   {
    "seed": 401501,
    "diff": -2.3564
   },
   {
    "seed": 400034,
    "diff": -2.3544
   }
  ]
 },
 "seconds_per_simulation": {
  "wall_with_24_workers": 0.0149,
  "approx_single_core": 0.36
 },
 "validate_ok": true,
 "blocked": null,
 "notes": "Reproduced YQ = 524.6271 on seeds 0..999 with amm_sim_rs.run_batch using MatchRunner._build_configs seeding. All tuning used seeds 0..1999. Seeds 900000..909999 were never run. Gas per call was not measured separately; amm-match validate passed and the code adds no loops.",
 "citations": [
  "https://github.com/benedictbrady/amm-challenge/tree/6b6921f8d463314aa7c96234e1be25a25245f704",
  "https://raw.githubusercontent.com/jiayaoqijia/amm-challenge-yq/3e9dc7d5a6192c88b562a0f8d9c172ca566ec94d/contracts/src/Strategy.sol"
 ]
}