{"variant": "gated-a", "blocked": null, "gates": {"A": {"passed": true, "number": 7.60422131512728e-05, "unit": "max |fee diff| bps, HA code vs port", "threshold_bps": 0.01, "sequences": 50, "swap_callbacks": 100000, "seeds": [310000, 310049]}, "B": {"passed": true, "number": 1.127066774560329, "unit": "replica gain of HA over T", "n": 4096, "seeds": [31000000, 31004095], "gain": 1.127066774560329, "se": 0.016115612191653444, "required_interval": [1.107, 1.407], "retail_delta": 4.069987917211661, "arb_delta": -2.942921142651332, "markets_per_s": 583.6811412999953, "speed_scope": "4096 10000-step markets, 6 processes, warmed Numba, one arm timed"}, "C": {"passed": true, "number": 3.791724180389976e-05, "unit": "max |fee diff| bps, frozen Solidity vs frozen port", "threshold_bps": 0.1, "sequences": 20, "swap_callbacks": 40000, "seeds": [310000, 310019]}}, "sim_markets_per_s": 583.6811412999953, "search_minutes": 46.13, "curve": [[0.12, 1.1507702061123384, 0.02115449032164739], [5.23, 1.2137877432841755, 0.02192840243656811], [10.34, 1.2266127395136424, 0.02210376473226844], [15.39, 1.2266127395136424, 0.02210376473226844], [20.42, 1.2699756826053807, 0.024591945918986592], [25.5, 1.2699756826053807, 0.024591945918986592], [30.62, 1.2719382174762823, 0.021848476743728553], [35.63, 1.3046737785212352, 0.024579340126283742], [40.68, 1.3046737785212352, 0.024579340126283742], [45.71, 1.3309685788040397, 0.022073748962300698]], "curve_format": "[search minutes, best monitor gain over T so far, se]; monitor seeds 30000000-30002047, 2048 markets", "holdout": {"n": 8192, "seeds": [40000000, 40008191], "gain_over_T": 1.2977019552806421, "se": 0.01040397764491074, "gain_over_HA": 0.18086989278069254, "se_HA": 0.004820672287836844}, "real": {"seeds": [7002000, 7002511], "vs_T": {"n": 512, "mean_diff": 1.2688378908379983, "se": 0.03959383579523053, "worst5": [{"seed": 7002110, "d": -5.280316534670874}, {"seed": 7002371, "d": -2.1386819263968846}, {"seed": 7002421, "d": -1.984126345093273}, {"seed": 7002288, "d": -1.3721133626794426}, {"seed": 7002177, "d": -0.8197947605269746}]}, "vs_HA": {"n": 512, "mean_diff": 0.19194006446164824, "se": 0.018697629820778872, "worst5": [{"seed": 7002498, "d": -0.9901540596365521}, {"seed": 7002027, "d": -0.9535844091751642}, {"seed": 7002465, "d": -0.9346442383512112}, {"seed": 7002110, "d": -0.8670023419190329}, {"seed": 7002363, "d": -0.8589186777983286}]}, "retail_delta": {"mean": 0.2782333078988777, "se": 0.0188293626025413}, "arb_delta": {"mean": -0.0862932434372306, "se": 0.007552060790023716}, "HA_vs_T": {"n": 512, "mean_diff": 1.07689782637635, "se": 0.03836073568449277}, "arm_means": {"frozen": 522.7103489835293, "HA": 522.5184089190677, "T": 521.4415110926914}, "engine": "amm_sim_rs.run_batch(strategy, VanillaStrategy, configs, 8), each arm alone, configs per MatchRunner._build_configs with seed=s"}, "gas": {"afterSwap_max_ok": 232419, "init_max_ok": 243128, "oog": 0, "other_failures": 0, "probe_16_markets_before_training": {"seeds": [7100000, 7100015], "afterSwap_max_ok": 232308, "init_max_ok": 243128, "oog": 0}, "HA_afterSwap_max_ok_same_seeds": 231560, "T_afterSwap_max_ok_same_seeds": 223336}, "valid": true, "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    uint256 constant ELAPSED_CAP = 8;\n    uint256 constant SIGNAL_THRESHOLD = WAD / 650;\n    uint256 constant DIR_DECAY = 750000000000000000;\n    uint256 constant ACT_DECAY = 530000000000000000;\n    uint256 constant SIZE_DECAY = 530000000000000000;\n    uint256 constant TOX_DECAY = 910000000000000000;\n    uint256 constant SIGMA_DECAY = 690000000000000000;\n    uint256 constant LAMBDA_DECAY = 990000000000000000;\n    uint256 constant SIZE_BLEND_DECAY = 828000000000000000;\n    uint256 constant TOX_BLEND_DECAY = 51000000000000000;\n    uint256 constant ACT_BLEND_DECAY = 985000000000000000;\n    uint256 constant PHAT_ALPHA = 270000000000000000;\n    uint256 constant PHAT_ALPHA_RETAIL = 60000000000000000;\n    uint256 constant PHAT_ALPHA_SAME = 120000000000000000;\n    uint256 constant REVERT_U = 0;\n    uint256 constant DIR_IMPACT_MULT = 4;\n    uint256 constant GATE_SIGMA_MULT = 7200000000000000000;\n    uint256 constant MIN_GATE = 30000000000000000;\n    uint256 constant TRADE_TOX_BOOST = 3500 * BPS;\n    uint256 constant STALE_ATTRACT_FRAC = 1050000000000000000;\n    uint256 constant RET_CAP = WAD / 35;\n    uint256 constant TOX_CAP = WAD / 5;\n    uint256 constant TRADE_RATIO_CAP = WAD / 5;\n    uint256 constant LAMBDA_CAP = 1820000000000000000;\n    uint256 constant STEP_COUNT_CAP = 64;\n    uint256 constant BASE_FEE = 4 * BPS;\n    uint256 constant SIGMA_COEF = 200000000000000000;\n    uint256 constant LAMBDA_COEF = 12 * BPS;\n    uint256 constant FLOW_SIZE_COEF = 4842 * BPS;\n    uint256 constant TOX_COEF = 300 * BPS;\n    uint256 constant TOX_QUAD_COEF = 15000 * 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 = 600 * BPS;\n    uint256 constant TAIL_SLOPE_PROTECT = 930000000000000000;\n    uint256 constant TAIL_SLOPE_ATTRACT = 850000000000000000;\n\n    function afterInitialize(uint256 initialX, uint256 initialY) external override returns (uint256, uint256) {\n        slots[0] = BASE_FEE; slots[1] = BASE_FEE; slots[3] = WAD; \n        slots[5] = initialX > 0 ? wdiv(initialY, initialX) : 100 * WAD;\n        slots[6] = 950000000000000; slots[7] = 800000000000000000; slots[8] = 2000000000000000;\n        slots[15] = 400000000000000000 | (uint256(2000000000000000) << 160); slots[13] = 902500000000; slots[14] = slots[5]; \n        return (BASE_FEE, BASE_FEE);\n    }\n\n    function afterSwap(TradeInfo calldata trade) external override returns (uint256, uint256) {\n        uint256 prevBidFee = slots[0]; uint256 prevAskFee = slots[1]; uint256 lastTs = uint64(slots[2]);\n        uint256 dirState = slots[3]; uint256 actEma = slots[4]; uint256 pHat = slots[5];\n        uint256 sigmaHat = slots[6]; uint256 lambdaHat = slots[7]; uint256 sizeHat = slots[8];\n        uint256 toxEma = slots[9]; uint256 stepTradeCount = slots[10];\n\n        uint256 sigmaForFast = sigmaHat;\n        uint256 fastHat = slots[14];\n        uint256 uncertainty = slots[13];\n        uint256 silent = trade.timestamp > lastTs ? trade.timestamp - lastTs : 0;\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            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            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            // Process variance is propagated inside the censored update.\n            if (uncertainty > 100000000000000) uncertainty = 100000000000000;\n            stepTradeCount = 0;\n        }\n\n        bool firstInStep = stepTradeCount == 0;\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) { pImplied = spot; }\n        else { pImplied = trade.isBuy ? wmul(spot, gamma) : wdiv(spot, gamma); }\n\n        // S: infer a no-trade interval center from the last post-trade spot.\n        uint256 silenceScale = WAD;\n        if (firstInStep && silent > 1) {\n            uint256 g = silent - 1;\n            if (g > 1) g = 1;\n            uint256 w = WAD - _powWad(800000000000000000, g);\n            uint256 s = slots[2] >> 64;\n            if (s == 0) s = pHat;\n            uint256 c = (wmul(s, WAD - prevBidFee) + wdiv(s, WAD - prevAskFee)) / 2;\n            if (c >= pHat) pHat += wmul(w, c - pHat);\n            else pHat -= wmul(w, pHat - c);\n            silenceScale = WAD - wmul(300000000000000000, w);\n        }\n\n        {\n            uint256 ret = pHat > 0 ? wdiv(absDiff(pImplied, pHat), pHat) : 0;\n            uint256 alpha = firstInStep ? PHAT_ALPHA : PHAT_ALPHA_RETAIL;\n            uint256 prePhat = pHat;\n            bool secondPrint = !firstInStep && stepTradeCount == 1;\n            bool sameDir = false; bool oppDir = false;\n            if (secondPrint) {\n                bool up2 = pImplied >= pHat;\n                uint256 d1 = slots[12];\n                if (d1 != 0) { sameDir = (d1 == 1) == up2; oppDir = !sameDir; }\n                if (sameDir) alpha = PHAT_ALPHA_SAME;\n            }\n            if (firstInStep) { slots[12] = pImplied >= pHat ? 1 : 2; }\n            uint256 adaptiveGate = wmul(sigmaHat, GATE_SIGMA_MULT);\n            if (adaptiveGate < MIN_GATE) adaptiveGate = MIN_GATE;\n            alpha = wmul(alpha, silenceScale);\n            adaptiveGate = wmul(adaptiveGate, silenceScale);\n            if (ret <= adaptiveGate) { pHat = wmul(pHat, WAD - alpha) + wmul(pImplied, alpha); }\n            if (oppDir && REVERT_U > 0) {\n                uint256 pre = slots[11];\n                if (pre > pHat) pHat = pHat + wmul(pre - pHat, REVERT_U);\n                else pHat = pHat - wmul(pHat - pre, REVERT_U);\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        // Interior retail routing equalizes fee-adjusted marginal prices.\n        // Subsequent trades in a step cannot be the initial arbitrage trade.\n        if (!firstInStep && feeUsed > 30 * BPS && gamma > 0) {\n            uint256 normalSpot = trade.isBuy\n                ? wdiv(wmul(spot, gamma), WAD - 30 * BPS)\n                : wdiv(wmul(spot, WAD - 30 * BPS), gamma);\n            pHat = wmul(pHat, 90 * WAD / 100) + wmul(normalSpot, 10 * WAD / 100);\n        }\n\n        // Censored assumed-density posterior. No external or future inputs.\n        uint256 arbProbability;\n        (fastHat, uncertainty, arbProbability) = _posterior(PosteriorInput(\n            fastHat, uncertainty, pImplied, spot, slots[2] >> 64,\n            prevBidFee, prevAskFee, firstInStep, silent, trade.isBuy,\n            trade.reserveY > 0 ? wdiv(trade.amountY, trade.reserveY) : 0\n        ));\n        slots[13] = uncertainty;\n        slots[14] = fastHat;\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            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            actEma = wmul(actEma, ACT_BLEND_DECAY) + wmul(tradeRatio, WAD - ACT_BLEND_DECAY);\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        uint256 toxLinear;\n        uint256 toxQuadratic;\n        {\n            uint256 packedAnchor = slots[16];\n            uint256 runMean = uint64(packedAnchor);\n            uint256 sampleCount = packedAnchor >> 64;\n            if (sampleCount < 674) sampleCount++;\n            if (toxEma >= runMean) runMean += (toxEma-runMean)/sampleCount;\n            else runMean -= (runMean-toxEma)/sampleCount;\n            slots[16] = runMean | (sampleCount << 64);\n            toxLinear = _anchorBlend(runMean, toxEma, 712696014807650816);\n            toxQuadratic = _anchorBlend(runMean, toxEma, 1295240753826310656);\n        }\n\n\n        stepTradeCount = stepTradeCount + 1;\n        if (stepTradeCount > STEP_COUNT_CAP) stepTradeCount = STEP_COUNT_CAP;\n\n        uint256 originalLambda = lambdaHat; uint256 originalSize = sizeHat;\n\n        if (342406799193418304 > 0) {\n            uint256 packedFlow = slots[15];\n            uint256 rate = uint80(packedFlow);\n            uint256 count = uint80(packedFlow >> 80);\n            uint256 meanSize = uint80(packedFlow >> 160);\n            if (rate == 0) rate = 400000000000000000;\n            if (meanSize == 0) meanSize = 2000000000000000;\n            if (isNewStep) {\n                uint256 inst = count / silent;\n                if (inst > 3 * WAD) inst = 3 * WAD;\n                uint256 retention = _powWad(999000000000000000, silent > 64 ? 64 : silent);\n                rate = wmul(rate, retention) + wmul(inst, WAD-retention);\n                count = 0;\n            }\n            uint256 weight = firstInStep ? WAD-arbProbability : WAD;\n            uint256 correctedWeight = weight;\n            if (2 == 2) {\n                uint256 missing = wmul(feeUsed, 196030880396139429888);\n                if (missing > 333333333333333376) missing = 333333333333333376;\n                correctedWeight = wdiv(weight, WAD-missing);\n            }\n            count += correctedWeight;\n            uint256 learning = wmul(WAD-999000000000000000, weight);\n            meanSize = _blend(meanSize, tradeRatio, learning);\n            slots[15]=rate | (count << 80) | (meanSize << 160);\n            uint256 retailRate = wmul(rate, 366383424913407168);\n            uint256 retailSize = 2 == 0 ? sizeHat : wmul(meanSize,1883296158119298304);\n            lambdaHat = _blend(lambdaHat,retailRate,342406799193418304);\n            sizeHat = _blend(sizeHat,retailSize,342406799193418304);\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, toxLinear) + wmul(TOX_QUAD_COEF, wmul(toxQuadratic, toxQuadratic)) + wmul(ACT_COEF, actEma);\n        fMid = fMid + wmul(SIGMA_TOX_COEF, wmul(sigmaHat, toxLinear));\n\n        lambdaHat = originalLambda; sizeHat = originalSize;\n        uint256 dirDev; bool sellPressure;\n        if (dirState >= WAD) { dirDev = dirState - WAD; sellPressure = true; }\n        else { dirDev = WAD - dirState; sellPressure = false; }\n\n        uint256 skew = wmul(DIR_COEF, dirDev) + wmul(DIR_TOX_COEF, wmul(dirDev, toxSignal));\n        uint256 bidFee; 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        {\n            uint256 staleHat = wmul(pHat, 700000000000000000) + wmul(fastHat, 300000000000000000);\n            uint256 staleTox = wdiv(absDiff(spot, staleHat), staleHat);\n            if (staleTox > TOX_CAP) staleTox = TOX_CAP;\n            uint256 staleShift = wmul(STALE_DIR_COEF, staleTox);\n            uint256 attractShift = wmul(staleShift, STALE_ATTRACT_FRAC);\n            if (spot >= staleHat) {\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        {\n            bool tradeAligned = (trade.isBuy && spot >= pHat) || (!trade.isBuy && spot < pHat);\n            if (tradeAligned) {\n                uint256 tradeBoost = wmul(TRADE_TOX_BOOST, tradeRatio);\n                if (!firstInStep && tradeBoost > 16 * BPS) tradeBoost = 16 * BPS;\n                if (trade.isBuy) { bidFee = bidFee + tradeBoost; }\n                else { askFee = askFee + tradeBoost; }\n            }\n        }\n\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        if (firstInStep) {\n            if (askFee > bidFee && bidFee > 30 * BPS) bidFee = 30 * BPS;\n            else if (bidFee > askFee && askFee > 30 * BPS) askFee = 30 * BPS;\n        }\n\n        if (bidFee > askFee && askFee > 36 * BPS) askFee = 36 * BPS;\n        else if (askFee > bidFee && bidFee > 36 * BPS) bidFee = 36 * BPS;\n\n        {\n            int256[13] memory nx;\n            unchecked {\n                nx[0] = int256(sigmaHat)*1000/1e12-1000000;\n                nx[1] = int256(lambdaHat)*2/1e12-1000000;\n                nx[2] = int256(sizeHat)*500/1e12-1000000;\n                nx[3] = int256(toxEma)*500/1e12-1000000;\n                nx[4] = int256(actEma)*500/1e12-1000000;\n                nx[5] = int256(dirState)/1e12-1000000;\n                uint256 nh = wmul(pHat,700000000000000000)+wmul(fastHat,300000000000000000);\n                nx[6] = (int256(spot)-int256(nh))*500000000/int256(nh);\n                nx[7] = int256(tradeRatio)*500/1e12;\n                if (!trade.isBuy) nx[7] = -nx[7];\n                nx[8] = int256(arbProbability)*2/1e12-1000000;\n                nx[9] = firstInStep ? int256(1000000) : -int256(1000000);\n                nx[10] = int256(uncertainty)/1e6-1000000;\n                nx[11] = int256(silent>8 ? 8 : silent)*1000000/8;\n                nx[12] = int256(uint256(uint64(slots[16])))*500/1e12-1000000;\n                for (uint256 ni=0;ni<13;ni++) {\n                    if(nx[ni]>4000000) nx[ni]=4000000;\n                    if(nx[ni]<-4000000) nx[ni]=-4000000;\n                }\n                (int256 hb,int256 ha) = _gate(nx, firstInStep);\n                int256 nb = int256(bidFee)+hb*100000000;\n                int256 na = int256(askFee)+ha*100000000;\n                bidFee = nb<0 ? 0 : (nb>int256(MAX_FEE) ? MAX_FEE : uint256(nb));\n                askFee = na<0 ? 0 : (na>int256(MAX_FEE) ? MAX_FEE : uint256(na));\n            }\n        }\n\n        slots[0] = bidFee; slots[1] = askFee; slots[2] = (spot << 64) | trade.timestamp;\n        slots[3] = dirState; slots[4] = actEma; slots[5] = pHat;\n        slots[6] = sigmaHat; slots[7] = lambdaHat; slots[8] = sizeHat;\n        slots[9] = toxEma; slots[10] = stepTradeCount;\n\n        return (bidFee, askFee);\n    }\n\n\n\n    function _head0(int256[13] memory x) internal pure returns (int256, int256) {\n        unchecked {\n            int256[3] memory r;\n            r[0] = 765686000000; r[1] = 2148677000000;\n            r[2] = 1699511 + ((-123607 * x[0]) + (1751671 * x[1]) + (-189172 * x[2]) + (1917151 * x[3]) + (-2206228 * x[4]) + (-42175 * x[5]) + (-2097012 * x[6]) + (784709 * x[7]) + (-3928716 * x[8]) + (-435477 * x[9]) + (135972 * x[10]) + (26073 * x[11]) + (410041 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (464798 * r[2]); r[1] += (95531 * r[2]);\n            r[2] = -3021932 + ((649928 * x[0]) + (1353543 * x[1]) + (1696432 * x[2]) + (4255552 * x[3]) + (1708696 * x[4]) + (929033 * x[5]) + (17676 * x[6]) + (-418967 * x[7]) + (-290855 * x[8]) + (247959 * x[9]) + (-216565 * x[10]) + (-402406 * x[11]) + (748756 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-1482327 * r[2]); r[1] += (-1356794 * r[2]);\n            r[2] = -2762384 + ((1994799 * x[0]) + (1990494 * x[1]) + (-585689 * x[2]) + (333713 * x[3]) + (2295166 * x[4]) + (3195923 * x[5]) + (-390090 * x[6]) + (2125562 * x[7]) + (1986086 * x[8]) + (-860946 * x[9]) + (-92073 * x[10]) + (-1516708 * x[11]) + (-1112267 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-64896 * r[2]); r[1] += (-1089820 * r[2]);\n            r[2] = -142320 + ((-1331142 * x[0]) + (-615502 * x[1]) + (-179423 * x[2]) + (543338 * x[3]) + (-496422 * x[4]) + (1142562 * x[5]) + (-526944 * x[6]) + (1055614 * x[7]) + (-1740150 * x[8]) + (1129874 * x[9]) + (1398808 * x[10]) + (-2257774 * x[11]) + (-1370205 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-60809 * r[2]); r[1] += (294964 * r[2]);\n            r[2] = -1235829 + ((885776 * x[0]) + (-1120615 * x[1]) + (4182243 * x[2]) + (-714465 * x[3]) + (-2003070 * x[4]) + (-892853 * x[5]) + (-1337976 * x[6]) + (-1667800 * x[7]) + (922480 * x[8]) + (28835 * x[9]) + (136801 * x[10]) + (-3257614 * x[11]) + (482131 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-3988532 * r[2]); r[1] += (946654 * r[2]);\n            r[2] = -1553111 + ((1759358 * x[0]) + (-1075746 * x[1]) + (1818733 * x[2]) + (-1859320 * x[3]) + (2931904 * x[4]) + (1046379 * x[5]) + (660837 * x[6]) + (-18645 * x[7]) + (-2227607 * x[8]) + (432369 * x[9]) + (725750 * x[10]) + (3835298 * x[11]) + (524186 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-424927 * r[2]); r[1] += (-465618 * r[2]);\n            r[2] = -2421926 + ((-3167801 * x[0]) + (851522 * x[1]) + (-341077 * x[2]) + (-2420777 * x[3]) + (1923013 * x[4]) + (1076878 * x[5]) + (-122366 * x[6]) + (133156 * x[7]) + (1058729 * x[8]) + (-439722 * x[9]) + (577951 * x[10]) + (1388093 * x[11]) + (-368778 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-1130945 * r[2]); r[1] += (-491933 * r[2]);\n            r[2] = -67929 + ((-3044813 * x[0]) + (-2057395 * x[1]) + (2219022 * x[2]) + (3433820 * x[3]) + (-1511106 * x[4]) + (-2304163 * x[5]) + (-506732 * x[6]) + (1895093 * x[7]) + (738237 * x[8]) + (-262661 * x[9]) + (2042285 * x[10]) + (-2449764 * x[11]) + (253953 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (835538 * r[2]); r[1] += (786723 * r[2]);\n            return (r[0] / 1000000, r[1] / 1000000);\n        }\n    }\n\n    function _head1(int256[13] memory x) internal pure returns (int256, int256) {\n        unchecked {\n            int256[3] memory r;\n            r[0] = 498328000000; r[1] = 1957840000000;\n            r[2] = 1261684 + ((-65102 * x[0]) + (706840 * x[1]) + (-15422 * x[2]) + (1905138 * x[3]) + (-3146612 * x[4]) + (59887 * x[5]) + (-1608804 * x[6]) + (979138 * x[7]) + (-3837041 * x[8]) + (-455981 * x[9]) + (-254171 * x[10]) + (87575 * x[11]) + (458929 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (667247 * r[2]); r[1] += (318473 * r[2]);\n            r[2] = -3679368 + ((994961 * x[0]) + (1156312 * x[1]) + (1688007 * x[2]) + (3739343 * x[3]) + (1220439 * x[4]) + (1122835 * x[5]) + (216053 * x[6]) + (13102 * x[7]) + (-706560 * x[8]) + (171949 * x[9]) + (-455369 * x[10]) + (-215487 * x[11]) + (369147 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-2052446 * r[2]); r[1] += (-1682751 * r[2]);\n            r[2] = -2812473 + ((2162364 * x[0]) + (1971084 * x[1]) + (-1572065 * x[2]) + (976510 * x[3]) + (2322256 * x[4]) + (2203722 * x[5]) + (-546818 * x[6]) + (1960652 * x[7]) + (2158180 * x[8]) + (-1627234 * x[9]) + (-293668 * x[10]) + (-1390956 * x[11]) + (-1025761 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (309783 * r[2]); r[1] += (-1286575 * r[2]);\n            r[2] = -681010 + ((-1028777 * x[0]) + (-441221 * x[1]) + (1215359 * x[2]) + (1130125 * x[3]) + (-593537 * x[4]) + (594127 * x[5]) + (-206154 * x[6]) + (1620993 * x[7]) + (-2198264 * x[8]) + (451787 * x[9]) + (734669 * x[10]) + (-1377181 * x[11]) + (-1807138 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-203866 * r[2]); r[1] += (855937 * r[2]);\n            r[2] = -547846 + ((903385 * x[0]) + (-411824 * x[1]) + (3729599 * x[2]) + (-872077 * x[3]) + (-2087040 * x[4]) + (-744290 * x[5]) + (-1673259 * x[6]) + (-1787198 * x[7]) + (276010 * x[8]) + (-93134 * x[9]) + (-219684 * x[10]) + (-3682551 * x[11]) + (90303 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-3620654 * r[2]); r[1] += (930943 * r[2]);\n            r[2] = -1879259 + ((1017350 * x[0]) + (-543841 * x[1]) + (865266 * x[2]) + (-1530515 * x[3]) + (2122386 * x[4]) + (1342735 * x[5]) + (1383951 * x[6]) + (33526 * x[7]) + (-2696569 * x[8]) + (-330813 * x[9]) + (611889 * x[10]) + (3843156 * x[11]) + (172710 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-553005 * r[2]); r[1] += (-251116 * r[2]);\n            r[2] = -2147129 + ((-2180886 * x[0]) + (703844 * x[1]) + (-834722 * x[2]) + (-3204275 * x[3]) + (1731177 * x[4]) + (851517 * x[5]) + (-493024 * x[6]) + (108655 * x[7]) + (1882154 * x[8]) + (-834476 * x[9]) + (792353 * x[10]) + (1281555 * x[11]) + (-305286 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (-2086453 * r[2]); r[1] += (-73830 * r[2]);\n            r[2] = -393936 + ((-2745381 * x[0]) + (-1646265 * x[1]) + (3102349 * x[2]) + (3484882 * x[3]) + (-1022903 * x[4]) + (-1878162 * x[5]) + (-403622 * x[6]) + (1790547 * x[7]) + (1068680 * x[8]) + (-1303799 * x[9]) + (2435548 * x[10]) + (-2226062 * x[11]) + (1484720 * x[12]))/1000000;\n            if(r[2]<0) r[2]=0; else if(r[2]>4000000) r[2]=4000000;\n            r[0] += (1017331 * r[2]); r[1] += (846915 * r[2]);\n            return (r[0] / 1000000, r[1] / 1000000);\n        }\n    }\n\n    function _gate(int256[13] memory x, bool f) internal pure returns (int256, int256) {\n        if (f) return _head0(x);\n        return _head1(x);\n    }\n\n    function _anchorBlend(uint256 mean, uint256 value, uint256 k) internal pure returns (uint256) {\n        if (k == WAD) return value;\n        if (value >= mean) return mean + wmul(value-mean,k);\n        uint256 delta = wmul(mean-value,k);\n        return delta < mean ? mean-delta : 0;\n    }\n\n    struct PosteriorInput {\n        uint256 mu; uint256 v; uint256 obs; uint256 spot; uint256 preSpot;\n        uint256 bid; uint256 ask; bool first; uint256 silent; bool buy; uint256 size;\n    }\n    function _posterior(PosteriorInput memory x) internal pure returns (uint256, uint256, uint256) {\n        if (x.mu == 0) x.mu = x.spot;\n        if (x.v < 10000000000) x.v = 10000000000;\n        uint256 lo = wmul(x.preSpot, WAD-x.bid);\n        uint256 hi = wdiv(x.preSpot, WAD-x.ask);\n        if (x.first) {\n            if (x.silent>1 && x.preSpot>0) {\n                uint256 elapsed=x.silent>8?8:x.silent;\n                x.v += 902500000000*(elapsed-1);\n                (x.mu,x.v)=_band(x.mu,x.v,lo,hi);\n            }\n            x.v+=902500000000;\n        }\n        uint256 mRetail = x.mu;\n        uint256 vRetail = x.v;\n        // A missing own-pool trade is a censored price observation.\n        if (x.first && x.preSpot > 0) {\n            (mRetail, vRetail) = _band(x.mu, x.v, lo, hi);\n        }\n        if (!x.first) {\n            // A later print is retail. Only an interior route is an observation\n            // of the other pool, with explicit observation uncertainty.\n            uint256 fee = x.buy ? x.bid : x.ask;\n            if (fee > 30 * BPS) {\n                uint256 normal = x.buy ? wdiv(wmul(x.spot, WAD-fee), WAD-30*BPS)\n                    : wdiv(wmul(x.spot, WAD-30*BPS), WAD-fee);\n                uint256 residual = wdiv(absDiff(normal, x.mu),x.mu);\n                uint256 noise = 9000000000000 + wmul(residual,residual);\n                uint256 k = wdiv(x.v,x.v+noise);\n                return (_blend(x.mu,normal,k),wmul(x.v,WAD-k),0);\n            }\n            return (x.mu,x.v,0);\n        }\n        uint256 e = wdiv(absDiff(x.obs,x.mu),x.mu);\n        uint256 totalV = x.v + 22500000000;\n        uint256 z = wdiv(wmul(e,e),totalV);\n        uint256 density = _powWad(wdiv(WAD,WAD+z/8),4);\n        uint256 odds = wmul(density,wdiv(4000000000000000,_isqrt(totalV*WAD)));\n        if (x.size > 3000000000000000) odds = wmul(odds,4*WAD/10);\n        if (x.silent > 1) odds = wmul(odds,8*WAD/10);\n        uint256 sd = _isqrt(x.v*WAD);\n        uint256 width = wdiv(hi-lo,x.mu);\n        uint256 distance = x.mu<lo?lo-x.mu:(x.mu>hi?x.mu-hi:0);\n        uint256 zBand = wdiv(wdiv(distance,x.mu),sd);\n        uint256 mass = wmul(wdiv(width,width+2*sd),wdiv(WAD,WAD+wmul(zBand,zBand)));\n        if (mass < WAD/100) mass = WAD/100;\n        odds = wdiv(odds,mass);\n        uint256 prob = wdiv(odds,WAD+odds);\n        uint256 kArb = wdiv(x.v,totalV);\n        uint256 mArb = _blend(x.mu,x.obs,kArb);\n        uint256 mean = _blend(mRetail,mArb,prob);\n        uint256 between = wdiv(absDiff(mArb,mRetail),x.mu);\n        uint256 variance = wmul(prob,wmul(x.v,WAD-kArb)) + wmul(WAD-prob,vRetail)\n            + wmul(wmul(prob,WAD-prob),wmul(between,between));\n        if (variance > 100000000000000) variance = 100000000000000;\n        return (mean,variance,prob);\n    }\n    function _blend(uint256 a,uint256 b,uint256 w) internal pure returns(uint256) {\n        return b>=a ? a+wmul(b-a,w) : a-wmul(a-b,w);\n    }\n    function _band(uint256 mu,uint256 v,uint256 lo,uint256 hi) internal pure returns(uint256,uint256) {\n        // Soft interval likelihood avoids discontinuities at quadrature nodes.\n        uint256 sd=wmul(mu,_isqrt(v*WAD));\n        uint256[3] memory acc;\n        for(uint256 j=0;j<7;j++) {\n            uint256 p=j<3 ? (mu>(3-j)*sd?mu-(3-j)*sd:1) : mu+(j-3)*sd;\n            uint256 w=j==3?72:(j==2||j==4?45:(j==1||j==5?10:1));\n            uint256 distance=p<lo?lo-p:(p>hi?p-hi:0);\n            uint256 z=sd>0?wdiv(distance,sd):0;\n            uint256 likelihood=wdiv(WAD,WAD+4*wmul(z,z));\n            w=wmul(w*WAD,likelihood);\n            acc[0]+=w;acc[1]+=wmul(w,p);\n            uint256 d=wdiv(absDiff(p,mu),mu);\n            acc[2]+=wmul(w,wmul(d,d));\n        }\n        uint256 m=wdiv(acc[1],acc[0]);\n        uint256 d=wdiv(absDiff(m,mu),mu);\n        uint256 second=wdiv(acc[2],acc[0]);\n        return(m,second>wmul(d,d)?second-wmul(d,d):10000000000);\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) { return WAD + wmul(centered - WAD, mul); }\n        uint256 below = wmul(WAD - centered, mul);\n        return below < WAD ? WAD - below : 0;\n    }\n\n    // Floor square root: bit-length seed and seven Newton steps (all uint256).\n    function _isqrt(uint256 x) internal pure returns (uint256 r) {\n        if (x == 0) return 0;\n        unchecked {\n            uint256 y = x;\n            r = 1;\n            if (y >> 128 != 0) { y >>= 128; r <<= 64; }\n            if (y >> 64 != 0) { y >>= 64; r <<= 32; }\n            if (y >> 32 != 0) { y >>= 32; r <<= 16; }\n            if (y >> 16 != 0) { y >>= 16; r <<= 8; }\n            if (y >> 8 != 0) { y >>= 8; r <<= 4; }\n            if (y >> 4 != 0) { y >>= 4; r <<= 2; }\n            if (y >> 2 != 0) { r <<= 1; }\n            r = (r + x / r) >> 1;\n            r = (r + x / r) >> 1;\n            r = (r + x / r) >> 1;\n            r = (r + x / r) >> 1;\n            r = (r + x / r) >> 1;\n            r = (r + x / r) >> 1;\n            r = (r + x / r) >> 1;\n            uint256 t = x / r;\n            return r < t ? r : t;\n        }\n    }\n\n    function getName() external pure override returns (string memory) { return \"gated_a\"; }\n}\n", "sha256": "50087729ef5e0a6ae4714a100fcdbe6f1757c6902e106e875cafa1e96e037f0f", "params": {"structure": "two copies of the HA 13-8-2 head: net_first runs when firstInStep, net_later otherwise; one copy evaluated per call", "net_first": {"W1": [[-0.123607, 1.751671, -0.189172, 1.917151, -2.206228, -0.042175, -2.097012, 0.784709, -3.928716, -0.435477, 0.135972, 0.026073, 0.410041], [0.649928, 1.353543, 1.696432, 4.255552, 1.708696, 0.929033, 0.017676, -0.418967, -0.290855, 0.247959, -0.216565, -0.402406, 0.748756], [1.994799, 1.990494, -0.585689, 0.333713, 2.295166, 3.195923, -0.39009, 2.125562, 1.986086, -0.860946, -0.092073, -1.516708, -1.112267], [-1.331142, -0.615502, -0.179423, 0.543338, -0.496422, 1.142562, -0.526944, 1.055614, -1.74015, 1.129874, 1.398808, -2.257774, -1.370205], [0.885776, -1.120615, 4.182243, -0.714465, -2.00307, -0.892853, -1.337976, -1.6678, 0.92248, 0.028835, 0.136801, -3.257614, 0.482131], [1.759358, -1.075746, 1.818733, -1.85932, 2.931904, 1.046379, 0.660837, -0.018645, -2.227607, 0.432369, 0.72575, 3.835298, 0.524186], [-3.167801, 0.851522, -0.341077, -2.420777, 1.923013, 1.076878, -0.122366, 0.133156, 1.058729, -0.439722, 0.577951, 1.388093, -0.368778], [-3.044813, -2.057395, 2.219022, 3.43382, -1.511106, -2.304163, -0.506732, 1.895093, 0.738237, -0.262661, 2.042285, -2.449764, 0.253953]], "b1": [1.699511, -3.021932, -2.762384, -0.14232, -1.235829, -1.553111, -2.421926, -0.067929], "W2": [[0.464798, -1.482327, -0.064896, -0.060809, -3.988532, -0.424927, -1.130945, 0.835538], [0.095531, -1.356794, -1.08982, 0.294964, 0.946654, -0.465618, -0.491933, 0.786723]], "b2": [0.765686, 2.148677]}, "net_later": {"W1": [[-0.065102, 0.70684, -0.015422, 1.905138, -3.146612, 0.059887, -1.608804, 0.979138, -3.837041, -0.455981, -0.254171, 0.087575, 0.458929], [0.994961, 1.156312, 1.688007, 3.739343, 1.220439, 1.122835, 0.216053, 0.013102, -0.70656, 0.171949, -0.455369, -0.215487, 0.369147], [2.162364, 1.971084, -1.572065, 0.97651, 2.322256, 2.203722, -0.546818, 1.960652, 2.15818, -1.627234, -0.293668, -1.390956, -1.025761], [-1.028777, -0.441221, 1.215359, 1.130125, -0.593537, 0.594127, -0.206154, 1.620993, -2.198264, 0.451787, 0.734669, -1.377181, -1.807138], [0.903385, -0.411824, 3.729599, -0.872077, -2.08704, -0.74429, -1.673259, -1.787198, 0.27601, -0.093134, -0.219684, -3.682551, 0.090303], [1.01735, -0.543841, 0.865266, -1.530515, 2.122386, 1.342735, 1.383951, 0.033526, -2.696569, -0.330813, 0.611889, 3.843156, 0.17271], [-2.180886, 0.703844, -0.834722, -3.204275, 1.731177, 0.851517, -0.493024, 0.108655, 1.882154, -0.834476, 0.792353, 1.281555, -0.305286], [-2.745381, -1.646265, 3.102349, 3.484882, -1.022903, -1.878162, -0.403622, 1.790547, 1.06868, -1.303799, 2.435548, -2.226062, 1.48472]], "b1": [1.261684, -3.679368, -2.812473, -0.68101, -0.547846, -1.879259, -2.147129, -0.393936], "W2": [[0.667247, -2.052446, 0.309783, -0.203866, -3.620654, -0.553005, -2.086453, 1.017331], [0.318473, -1.682751, -1.286575, 0.855937, 0.930943, -0.251116, -0.07383, 0.846915]], "b2": [0.498328, 1.95784]}, "shapes": {"W1": [8, 13], "b1": [8], "W2": [2, 8], "b2": [2]}, "weight_fixed_point_scale": 1000000, "feature_fixed_point_scale": 1000000, "output_unit_fee": 0.0001, "feature_order": ["sigmaHat", "lambdaHat", "sizeHat", "toxEma", "actEma", "direction", "(spot-staleHat)/staleHat", "signed_trade_ratio", "arb_probability", "first_in_step", "uncertainty", "min(silent,8)/8", "anchor_mean"], "feature_multipliers": [1000, 2, 500, 500, 500, 1, 500, 500, 2, 2, 1000000, 1, 500], "feature_offsets": [-1, -1, -1, -1, -1, -1, 0, 0, -1, -1, -1, 0, -1], "feature_clip": [-4, 4], "hidden_relu_clip": [0, 4], "toxicity_anchor": {"count_cap": 674, "linear_k_wad": 712696014807650816, "quadratic_k_wad": 1295240753826310656}, "training": {"optimizer": "cma (CMA_diagonal=True)", "seed": 103, "popsize": 16, "initial_sigma": 0.05, "dimension": 260, "start": "both copies = HA weights (exact HA fees)", "generations": 370, "train_seeds": [120000000, 120094719], "markets_per_generation": 256, "objective": "mean edge minus T edge on shared replica seeds", "proposals_rounded": 1e-06, "monitor_seeds": [30000000, 30002047], "selection": "max monitor gain among CMA mean and best training-block proposal, checked about every 5 search minutes", "selected_at_search_minute": 45.713273020585376}}, "port_zb64": "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", "port_sha256": "7a63e119816cdadb240482c2aed3c9df6f24e3f1eb8e1ceb39fd44897fc7f627", "notes": ["All input sha256 verified: HA 2801efc8..., T 6ac5e013..., RS2 port d845a4b9..., replica e8a7a2af...; HA input_sha256 field hashes (T code ebd9de9b..., port_source 9eac3553..., replica_source 1e4c44b4...) match the extracted fields.", "Port: RS2 float port + T toxicity anchor (run mean of toxEma, count cap 674, k 0.712696/1.295241 on linear/quadratic tox terms; skew keeps raw toxEma) + HA 13-8-2 head applied after the 30/36 bps caps, clamped to [0, MAX_FEE]; embedded in the replica sim (verbatim). Gate A run against HA code; T and HA real arms use the unmodified downloaded code.", "Gate B passed narrowly: replica HA-over-T 1.127 se 0.016 vs real 1.257 (interval 1.107-1.407). On real seeds 7002000-7002511 HA-over-T was 1.077 se 0.038, so real gains on this block are lower than on 6020000+.", "Solidity: a straight two-head copy failed to compile (stack too deep under viaIR); fixed by evaluating each head with an int256[3] memory accumulator and a _gate(nx, firstInStep) dispatcher. Same arithmetic as HA (1e6 fixed point, truncating division). The start contract from HA weights matched HA fees (3 sequences, 6000 callbacks, max 3.2e-5 bps) and gas probe passed (232,308 afterSwap, 0 OOG) before training; no shrinking was needed.", "Training: CMA-ES diagonal, sigma 0.05, pop 16, 260 params, 256 fresh replica markets per generation from 120000000, paired against T on the same seeds; 370 generations in 46.1 search minutes over 7 segments, saved under scratch. The monitor curve was still rising at the stop (1.151 -> 1.331), so longer training from these weights should help further.", "Result: replica holdout +0.181 se 0.005 over HA; real +0.192 se 0.019 over HA and +1.269 se 0.040 over T (512 fresh seeds), 0 OOG, afterSwap peak 232,419. The replica predicted the real gain over HA within 0.011. This is far from the ~+3.1 over HA needed for top 10.", "Next: resume from these weights (port_zb64, make_th(2, net_first, net_later)) with longer runs and larger blocks per generation; consider gating on more regimes (e.g. silent>1, arb-probability high) or a wider hidden layer, while staying under the 245k gas cap (peak now 232k)."]}