{
  "approach": "Tune only inferred competitor spread 1. Require 0.3 ticks of estimated margin for ordinary bids and asks (dmin, formerly 0); lower the probability floor below tick one from 0.0005 to 0.000001 (pfl). The margin filter removes thin-edge ordinary quotes while preserving the separate tick-one stock bid; the lower probability floor permits more retail quoting in deeply NO-valued states. Retain the original inventory-purchase and queue rules. Each retained sequential increment gained on both disjoint tuning groups. Selection used the simpler policy because additional procurement cuts had a negative incremental first-group effect, despite a higher pooled score. Full-stock removal, large quote cuts, large risk increases, and stock-netting rules were rejected. Selection measurements before freeze: {\"4000\":{\"versus_base\":{\"n\":265,\"diff\":1.0253177588486784,\"se\":0.3167770064025856,\"retail_diff\":-0.18745014679358438,\"arb_diff\":1.2127679056456604,\"failures\":0},\"probability_floor_increment\":{\"n\":265,\"diff\":0.18690118047245297,\"se\":0.06636825523240238,\"retail_diff\":0.18147378065320735,\"arb_diff\":0.0054273998199999805,\"failures\":0},\"excluded_procurement_increment\":{\"n\":265,\"diff\":-0.032903233021509166,\"se\":0.2427263072499907,\"retail_diff\":-0.06343098143584922,\"arb_diff\":0.03052774841169812,\"failures\":0}},\"6000\":{\"versus_base\":{\"n\":246,\"diff\":0.5160933987105686,\"se\":0.31919303602318017,\"retail_diff\":-0.4518373908711373,\"arb_diff\":0.9679307895825204,\"failures\":0},\"probability_floor_increment\":{\"n\":246,\"diff\":0.1248399093288616,\"se\":0.06238645424896486,\"retail_diff\":0.1290872028146341,\"arb_diff\":-0.0042472934869918705,\"failures\":0},\"excluded_procurement_increment\":{\"n\":246,\"diff\":0.21650722974878078,\"se\":0.11150322296215051,\"retail_diff\":-0.08384122339512216,\"arb_diff\":0.3003484531487804,\"failures\":0}}}. Simulator commit b244530ee2a6247b5f930830eeca9dd950da0e7e. Scorer reproduced on seeds 1000-1599. Exact equality of every SimulationResult field for all 456 non-spread-1 reference runs, and all non-target runs in both 4000-run batches. Other-spread constants copied unchanged into per-instance dictionaries. Spread-1 tuning used only seeds 4000-4999 and 6000-6999 unless explicitly listed otherwise; all reported paired SEs use sample standard deviation / sqrt(n). Code frozen before holdout scoring at 2026-11-06T02:46:33.034419+00:00; no holdout-based retuning. arb_edge is signed negative edge, not positive loss. All measurements are local simulator results, not claims about Paradigm deployment. All required measurements are present and nothing was fabricated. Deliberately canceled exploratory workloads are marked in tried; no partial scores were reported.",
  "blocked": null,
  "python_version": "3.12.3",
  "base_mean_edge": 109.27254289017199,
  "base_holdout_mean_edge": 98.28063388702982,
  "score": {
    "mean_edge": 98.9689746680761,
    "retail_edge": 124.29013580906907,
    "arb_edge": -25.321161141007252,
    "simulations": 4000,
    "seed_start": 4000,
    "failures": 0
  },
  "holdout": {
    "mean_edge": 98.52619137752235,
    "retail_edge": 125.95607618418198,
    "arb_edge": -27.4298848066588,
    "simulations": 4000,
    "seed_start": 50000,
    "failures": 0
  },
  "by_spread": [
    {
      "spread": 1,
      "runs": 1016,
      "base": 35.099921878704336,
      "yours": 36.06668365229695,
      "diff": 0.9667617735926181,
      "standard_error": 0.24996913452108194
    },
    {
      "spread": 2,
      "runs": 998,
      "base": 83.51205221971222,
      "yours": 83.51205221971222,
      "diff": 0.0,
      "standard_error": 0.0
    },
    {
      "spread": 3,
      "runs": 1017,
      "base": 122.97345583671554,
      "yours": 122.97345583671554,
      "diff": 0.0,
      "standard_error": 0.0
    },
    {
      "spread": 4,
      "runs": 969,
      "base": 153.82041508580312,
      "yours": 153.82041508580312,
      "diff": 0.0,
      "standard_error": 0.0
    }
  ],
  "constants": {
    "P.dmin": 0.3,
    "P.pfl": 1e-06
  },
  "code": "\"\"\"Stale-quote defence with tick probes, a sub-tick belief and cheap YES stock.\n\nEvery step the arbitrageur removes any order on the wrong side of p, so tiny\ntwo-sided probes around the estimate locate p to a tick; a grid filter narrows\nthat further.  Quotes sit one tick inside the competitor and are sized by the\nmarginal rule: one more share is worth quoting while the chance a retail order\nreaches it, times its edge, exceeds the expected arbitrage loss.  Near p=0 a\nretail buy pays almost its whole notional as edge, so YES is held to cover low\nasks.  That YES is bought when it is cheap: a large bid rests at tick 1 while p\nis above it, so the arbitrageur fills it on the crossing for about 0.1 tick a\nshare instead of nearly a full tick once p is near zero, and smaller bids sit on\nwhichever tick p is within 0.15 of.  Below tick 1 the estimate of p decays with\nthe time spent there, since no probe can see it.\n\"\"\"\nimport math\nfrom orderbook_pm_challenge.strategy import BaseStrategy\nfrom orderbook_pm_challenge.types import CancelOrder, PlaceOrder, Side\n\nP = dict(lam_r=0.25, m=5.0, sig_n=1.2, lam_j=0.0019, sig_j=0.35, sig=0.02,\n         qmax=3000.0, rmin=2, kA=0.7, kL=0.15, pL=0.05,\n         ammo=1.0, ydem=0.4, W=200.0, fy=0.6, ammo_q=60.0, ammo_pmax=0.05, ammo_maxpay=0.02,\n         fb=0.9, fu=0.7, xu=0.1, sticky=1.0, min_ahead=2.0, keep_hi=1.5, keep_lo=0.7, Hu=300.0, bins=8.0, filt=1.0, uni=0.01, jumpinfo=1.0, dmin=0.0, kLb=0.08, kLf=0.08, pinf=1.0, pre=0.0, H1=100.0,\n         ydf=0.6, Wf=2000.0, g_hi=0.15, g_lo=0.15, qf=400.0, pmaxf=0.05, pre_gap=1.0,\n         ydf1=0.6, g1=5.0, f1=0.6, a1=100.0, nb1=0.0, gs=1.0, p1t=1.0, m1=1.0, zd=1.0, pfl=0.0005)\nP.update({'W': 50, 'ammo_pmax': 0.02, 'fy': 0.7, 'fu': 0.25, 'Hu': 500})\nC = {'W': 50, 'ammo_pmax': 0.02, 'fy': 0.7, 'reserve': 200, 'scar': 0.0025, 'fu': 0.25, 'Hu': 500}\nSQ2 = math.sqrt(2.0)\nSQ2PI = math.sqrt(2.0 * math.pi)\ndef cdf(x): return 0.5 * (1.0 + math.erf(x / SQ2))\ndef pdf(x): return math.exp(-0.5 * x * x) / SQ2PI\ndef inv(p):\n    p = min(max(p, 1e-9), 1 - 1e-9)\n    t = math.sqrt(-2.0 * math.log(min(p, 1 - p)))\n    x = t - (2.515517 + 0.802853 * t + 0.010328 * t * t) / (1 + 1.432788 * t + 0.189269 * t * t + 0.001308 * t ** 3)\n    x = -x if p < 0.5 else x\n    for _ in range(2):\n        d = pdf(x)\n        if d < 1e-12:\n            break\n        x -= (cdf(x) - p) / d\n    return x\ndef lpm(k):\n    return pdf(k) + k * cdf(k)\ndef fl(q):\n    return math.floor(q * 100 + 1e-9) / 100\n\nNODES = [(-2.2, .06), (-1.3, .17), (-0.6, .27), (0.6, .27), (1.3, .17), (2.2, .06)]\nPROBE = 0.01\n\n\nclass Strategy(BaseStrategy):\n    def __init__(self):\n        self.n = 0\n        self.ahead = set()     # main orders placed strictly ahead of any competitor order at their tick\n        self.res = {}          # order id -> uncovered quantity at placement\n        self.bc = None         # belief: sub-tick grid centres (ticks)\n        self.bw = None         # belief: weights\n        self.st = 0.5          # last one-step sd in ticks\n        self.pcb = self.pca = None\n        self.pb = set()\n        self.pa = set()\n        self.tb = 0\n        self.params = P.copy()\n        self.controls = C.copy()\n        self.s = None          # competitor spread parameter\n\n    def _oid(self, tag):\n        self.n += 1\n        return tag + str(self.n)\n\n    def on_step(self, state):\n        H = max(1, state.steps_remaining)\n        cb = state.competitor_best_bid_ticks or 0\n        ca = state.competitor_best_ask_ticks or 100\n        if self.s is None:\n            self.s = max(1, (ca - cb + 1) // 2)\n            if self.s == 1:\n                self.params.update({'dmin': 0.3, 'pfl': 1e-06})\n                self.controls.update({})\n        P = self.params\n        C = self.controls\n        lo, hi = cb, ca\n        for o in state.own_orders:\n            if o.side is Side.BUY:\n                lo = max(lo, o.price_ticks)\n            else:\n                hi = min(hi, o.price_ticks)\n        if P['pinf'] > 0:\n            sb = {o.price_ticks for o in state.own_orders if o.side is Side.BUY and o.remaining_quantity <= PROBE + 1e-9}\n            sa = {o.price_ticks for o in state.own_orders if o.side is Side.SELL and o.remaining_quantity <= PROBE + 1e-9}\n            ea = self.pa - sa\n            eb = self.pb - sb\n            if sa and ea:\n                lo = max(lo, min(max(ea), hi))\n            if eb and (sb or min(eb) <= P['p1t']):\n                hi = min(hi, max(min(eb), lo))\n        if P['jumpinfo'] > 0 and self.pcb is not None:\n            if ca > self.pca + 1:\n                lo = max(lo, ca - 1)\n            if cb < self.pcb - 1:\n                hi = min(hi, cb + 1)\n        self.pcb, self.pca = cb, ca\n        if lo > hi:\n            lo, hi = hi, lo\n        # sub-tick belief over p_(t-1): predict with one-step noise, truncate to [lo, hi]\n        wid = max(hi - lo, 1e-6)\n        nb = max(2, min(48, int(round(wid * P['bins']))))\n        cs = [lo + (i + 0.5) * wid / nb for i in range(nb)]\n        if self.bc is None or P['filt'] <= 0:\n            ws = [1.0 / nb] * nb\n        else:\n            sg = max(self.st, 0.6 * wid / nb)\n            k = -0.5 / (sg * sg)\n            ws = []\n            uni = P['uni'] * sg\n            for c in cs:\n                t = uni\n                for ci, wi in zip(self.bc, self.bw):\n                    d = c - ci\n                    d2 = d * d * k\n                    if d2 > -12.5:\n                        t += wi * math.exp(d2)\n                ws.append(t)\n            tot = sum(ws)\n            ws = [w / tot for w in ws]\n        self.bc, self.bw = cs, ws\n        mean_t = sum(c * w for c, w in zip(cs, ws))\n        var_t = max(sum(c * c * w for c, w in zip(cs, ws)) - mean_t * mean_t, 0.0)\n        phat = min(max(mean_t / 100.0, 0.002), 0.998)\n        var = P['sig'] ** 2 + P['lam_j'] * P['sig_j'] ** 2\n        sd = math.sqrt(H * var)\n        self.tb = self.tb + 1 if hi <= 1 else 0\n        if self.tb > 0 and P['zd'] > 0:\n            # below the last tick there is no probe: the score keeps walking away from it\n            phat = min(phat, max(P['pfl'], cdf(inv(0.01) - P['zd'] * 0.02 * math.sqrt(self.tb) / sd)))\n        z = inv(phat)\n        Z = z * sd\n        sp = pdf(z) / sd * P['sig']\n        self.st = sp * 100.0\n        s = math.sqrt(sp * sp + var_t / 1e4 + 1e-8)\n        sd1 = math.sqrt(max(1.0, H - 1.0) * var)\n        jp = [(cdf((Z + n * P['sig_j']) / sd1), w) for n, w in NODES]\n        lj = P['lam_j']\n\n        def AB(x):\n            k = (x - phat) / s\n            a = s * lpm(k)\n            b = a - (x - phat)\n            ja = sum(w * max(0.0, x - p) for p, w in jp)\n            jb = sum(w * max(0.0, p - x) for p, w in jp)\n            return (1 - lj) * a + lj * ja, (1 - lj) * b + lj * jb\n\n        if H == 1:\n            def AB(x):\n                return (1 - phat) * x, phat * (1 - x)\n        rho = P['lam_r'] * 0.5\n        mu = math.log(P['m']) - 0.5 * P['sig_n'] ** 2\n        kA = P['kL'] if phat < P['pL'] else P['kA']\n\n        def qsize(loss, gain, px):\n            loss *= kA\n            if gain <= 0:\n                return 0.0\n            tail = loss / (rho * gain)\n            if tail >= 1.0:\n                return 0.0\n            return min(P['qmax'], math.exp(mu + P['sig_n'] * inv(1 - max(tail, 1e-6))) / px)\n\n        ptk = phat * 100\n        def qbid(t):\n            if not 1 <= t <= 99:\n                return 0.0\n            a, b = AB(t / 100.0)\n            if phat * 100 - t < P['dmin']:\n                return 0.0\n            if P['nb1'] > 0 and self.s == 1 and t == 1 and ptk < 1.0:\n                return 0.0\n            if phat < P['pL']:\n                ytg = P['ydem'] * min(H, P['W']) / max(ca - 1, ptk + 1) * 100.0\n                a *= (P['kLb'] if state.yes_inventory < ytg else P['kLf']) / P['kL']\n            return qsize(a, b, max(phat, 0.05))\n\n        def qask(t):\n            if not 1 <= t <= 99:\n                return 0.0\n            a, b = AB(t / 100.0)\n            if t - phat * 100 < P['dmin']:\n                return 0.0\n            if phat < C.get('scar_p', .1):\n                a = max(0.0, a - C.get('scar', 0.0) * (1 - min(1.0, state.yes_inventory / C.get('stock', 3000.0))))\n            return min(C.get('askcap', P['qmax']), qsize(b, a, t / 100.0))\n\n        bids = [o for o in state.own_orders if o.side is Side.BUY and o.remaining_quantity > PROBE + 1e-9]\n        asks = [o for o in state.own_orders if o.side is Side.SELL and o.remaining_quantity > PROBE + 1e-9]\n        sticky = P['sticky'] > 0\n        def top(orders, comp, step):\n            if sticky and sum(o.remaining_quantity for o in orders if o.price_ticks == comp and o.order_id in self.ahead) >= P['min_ahead']:\n                return comp\n            return comp + step\n        bid_t = top(bids, cb, 1)\n        ask_t = top(asks, ca, -1)\n        qb = min(C.get('bidcap', 3000.0), qbid(bid_t))\n        qa = qask(ask_t)\n\n        Y = state.yes_inventory\n        if ask_t == 1 and H > P['H1'] and P['pre'] > 0:\n            qa = qa if Y >= P['a1'] > 0 else 0.0          # let the competitor's 2-tick ask erode instead of fronting it for nothing\n        # ammunition: hold YES so that low asks are covered\n        ptick = phat * 100\n        amt = 0\n        qam = 0.0\n        if P['ammo'] > 0 and ask_t >= 2 and phat < max(P['ammo_pmax'], P['pmaxf']):\n            wealth = state.cash + Y * phat\n            x = max(ask_t, ptick + 1) / 100.0\n            capw = P['fy'] * wealth / max(phat, 0.005)\n            target = min(P['ydem'] * min(H, P['W']) / x, capw)\n            full = min(P['ydf'] * min(H, P['Wf']) / x, capw) if phat < P['pmaxf'] else 0.0\n            t = max(1, min(99, int(math.ceil(ptick + 1e-9))))\n            g = t - ptick\n            if Y < full and g <= P['g_hi'] and bid_t <= t < ask_t:\n                amt, qam = t, min(P['qf'], full - Y)     # a tick p has just crossed: nearly free\n            elif Y < target and phat < P['ammo_pmax'] and bid_t <= t < ask_t and t / 100.0 - phat < P['ammo_maxpay']:\n                amt, qam = t, min(P['ammo_q'], target - Y)\n            elif Y < full and t >= 2 and 1.0 - g <= P['g_lo']:\n                amt, qam = t - 1, min(P['qf'], full - Y)  # rest just under p: filled only on the crossing, or by retail\n\n        if P['pre'] > 0 and ca == 2 and phat < 0.01 and H > P['H1'] and Y < P['pre'] and not qam and 1.0 - ptick < P['pre_gap']:\n            amt, qam = 1, min(P['ammo_q'], P['pre'] - Y)\n        q1 = 0.0\n        if P['ydf1'] > 0 and P['m1'] < ptick < P['g1'] + 1.0 and amt != 1:\n            q1 = max(0.0, P['ydf1'] * min(H, P['Wf']) / (self.s / 100.0) - Y)\n        # order management\n        actions = []\n        free = state.free_cash - 2.0\n        keep_ask = 0.0\n        new_b = []\n        new_a = []\n        def cancel(o):\n            nonlocal free\n            actions.append(CancelOrder(o.order_id))\n            x = o.price_ticks / 100.0\n            if o.side is Side.BUY:\n                free += x * o.remaining_quantity\n            else:\n                free += (1 - x) * min(self.res.get(o.order_id, 0.0), o.remaining_quantity)\n            self.ahead.discard(o.order_id)\n            self.res.pop(o.order_id, None)\n        for o in state.own_orders:\n            if o.remaining_quantity <= PROBE + 1e-9:\n                cancel(o)\n        kept_ids = set()\n        def manage(orders, t, q, comp):\n            kept = 0.0\n            for o in orders:\n                if not (C.get('recover', 0) and o.side is Side.SELL and t < comp and self.res.get(o.order_id, 0.0) > 1 and state.yes_inventory > C.get('recover_yes', 1) and state.free_cash < C.get('recover_cash', 200)) and o.price_ticks == t and q > 0 and kept + o.remaining_quantity <= max(q * P['keep_hi'], 1.0):\n                    kept += o.remaining_quantity\n                    kept_ids.add(o.order_id)\n                else:\n                    cancel(o)\n            return kept\n        kb = manage(bids, bid_t, qb, cb)\n        ka = manage(asks, ask_t, qa, ca)\n        add_b = (qb - kb) if (kb < qb * P['keep_lo'] and bid_t != cb) else 0.0\n        add_a = (qa - ka) if (ka < qa * P['keep_lo'] and ask_t != ca) else 0.0\n\n        budget = P['fb'] * max(free, 0.0)\n        cost = add_b * bid_t / 100.0 + qam * amt / 100.0\n        if cost > budget:\n            f = budget / cost\n            add_b *= f\n            qam *= f\n            cost = budget\n        out = []\n        q1 = min(q1, P['f1'] * max(budget - cost, 0.0) * 100.0)\n        if q1 >= 0.01:\n            out.append(PlaceOrder(side=Side.BUY, price_ticks=1, quantity=fl(q1)))\n            free -= fl(q1) / 100.0 + 1e-6\n        if amt and qam >= 0.01:\n            q = fl(qam)\n            out.append(PlaceOrder(side=Side.BUY, price_ticks=amt, quantity=q))\n            free -= q * amt / 100.0 + 1e-6\n        if bid_t >= 1 and add_b >= 0.01:\n            q = fl(add_b)\n            oid = self._oid('b')\n            out.append(PlaceOrder(side=Side.BUY, price_ticks=bid_t, quantity=q, client_order_id=oid))\n            free -= q * bid_t / 100.0 + 1e-6\n            if bid_t > cb:\n                self.ahead.add(oid)\n        if ask_t <= 99 and add_a >= 0.01:\n            x = ask_t / 100.0\n            covk = sum(o.remaining_quantity - min(self.res.get(o.order_id, 0.0), o.remaining_quantity)\n                       for o in asks if o.order_id in kept_ids)\n            cov = max(0.0, Y - covk - 0.1)\n            unc = max(0.0, add_a - cov)\n            if unc > 0:\n                ub = max(0.0, free - (1 - P['fu']) * max(state.cash, 0.0)) if x >= P['xu'] else 0.0\n                if H < P['Hu'] and phat < 0.05:\n                    ub = max(0.0, free * (1 - H / P['Hu']))\n                ub = min(ub, max(0.0, free - C.get('reserve', 0.0) * min(1.0, H / C.get('release', 50.0))))\n                unc = min(unc, ub / (1 - x))\n            q = fl(min(add_a, cov + unc))\n            if q >= 0.01:\n                oid = self._oid('a')\n                out.append(PlaceOrder(side=Side.SELL, price_ticks=ask_t, quantity=q, client_order_id=oid))\n                r = max(0.0, q - cov)\n                self.res[oid] = r\n                free -= r * (1 - x) + 1e-6\n                if ask_t < ca:\n                    self.ahead.add(oid)\n\n        # probes: tiny orders that the arbitrageur removes when p crosses them\n        f = int(math.floor(ptick + 1e-9))\n        r = max(int(P['rmin']), int(math.ceil(2.0 * s * 100)))\n        self.pb = set()\n        self.pa = set()\n        if free > 1.0:\n            for t in range(f, f + r + 1):\n                if cb < t < ca and 1 <= t <= 99:\n                    out.append(PlaceOrder(side=Side.BUY, price_ticks=t, quantity=PROBE))\n                    self.pb.add(t)\n            for t in range(f + 1 - r, f + 2):\n                if cb < t < ca and 1 <= t <= 99:\n                    out.append(PlaceOrder(side=Side.SELL, price_ticks=t, quantity=PROBE))\n                    self.pa.add(t)\n        return actions + out\n",
  "code_sha256": "3ce03e13efedc1b452938b7dfb1d0abd62b7d13dd1eb67a12afa57d9fe2d6a41",
  "tried": [
    "ammo_low {'P.pmaxf': 0.02, 'P.ammo_pmax': 0.01}; spread-1 seeds 4000-4999; mean=28.68510897618453; paired {\"n\":265,\"diff\":0.5176134810015093,\"se\":0.3558551296871196,\"retail_diff\":-0.3242451680981131,\"arb_diff\":0.8418586490928303,\"failures\":0}",
    "ammo_low {'P.pmaxf': 0.02, 'P.ammo_pmax': 0.01}; spread-1 seeds 6000-6999; mean=44.43331818324878; paired {\"n\":246,\"diff\":0.1213771886792682,\"se\":0.23666937141843558,\"retail_diff\":-0.3837828925654471,\"arb_diff\":0.5051600812398375,\"failures\":0}",
    "ammo_q1000 {'P.qf': 1000}; spread-1 seeds 4000-4999; mean=28.322729252314716; paired {\"n\":265,\"diff\":0.15523375713169787,\"se\":0.31743222507277474,\"retail_diff\":0.3680013445366039,\"arb_diff\":-0.21276758739207557,\"failures\":0}",
    "ammo_q100 {'P.qf': 100, 'P.ammo_q': 20}; spread-1 seeds 4000-4999; mean=28.41790736812566; paired {\"n\":265,\"diff\":0.2504118729426409,\"se\":0.1963549661343005,\"retail_diff\":-0.3328916523215086,\"arb_diff\":0.5833035252566038,\"failures\":0}",
    "ammoq0 {'P.ammo_q': 0}; spread-1 seeds 4000-4999; mean=28.197928941938113; paired {\"n\":265,\"diff\":0.03043344675509428,\"se\":0.013295774611614677,\"retail_diff\":-0.013180276536981185,\"arb_diff\":0.04361372329245297,\"failures\":0}",
    "ammoq0 {'P.ammo_q': 0}; spread-1 seeds 6000-6999; mean=44.331683317041055; paired {\"n\":246,\"diff\":0.019742322471544626,\"se\":0.008877346758723864,\"retail_diff\":-0.016336090323983588,\"arb_diff\":0.036078412794308894,\"failures\":0}",
    "ask0 {'P.ask_risk': 1000}; spread-1 seeds 4000-4999; mean=-7.3188314249796225; paired {\"n\":265,\"diff\":-35.48632692016264,\"se\":5.471071875150244,\"retail_diff\":-44.133685329319626,\"arb_diff\":8.647358409181887,\"failures\":0}",
    "ask2 {'P.ask_risk': 2}; spread-1 seeds 4000-4999; mean=29.07045187168; paired {\"n\":265,\"diff\":0.9029563764969805,\"se\":0.7861190935888522,\"retail_diff\":-2.3063857199018867,\"arb_diff\":3.2093420964049058,\"failures\":0}",
    "ask2 {'P.ask_risk': 2}; spread-1 seeds 6000-6999; mean=44.23058841356789; paired {\"n\":246,\"diff\":-0.08135258100162653,\"se\":0.6075263600357094,\"retail_diff\":-2.7657346789865853,\"arb_diff\":2.6843820979772355,\"failures\":0}",
    "ask4 {'P.ask_risk': 4}; spread-1 seeds 4000-4999; mean=27.363254282279247; paired {\"n\":265,\"diff\":-0.8042412129037745,\"se\":1.2334949844065843,\"retail_diff\":-6.024811867452829,\"arb_diff\":5.220570654577358,\"failures\":0}",
    "bid0 {'P.bid_risk': 1000}; spread-1 seeds 4000-4999; mean=23.37391963165585; paired {\"n\":265,\"diff\":-4.79357586352717,\"se\":0.9659878482774296,\"retail_diff\":-7.377087271260754,\"arb_diff\":2.5835114077090564,\"failures\":0}",
    "bid2 {'P.bid_risk': 2}; spread-1 seeds 4000-4999; mean=27.35925146303283; paired {\"n\":265,\"diff\":-0.8082440321501895,\"se\":0.4420631528875718,\"retail_diff\":-2.451874140612453,\"arb_diff\":1.6436301084166038,\"failures\":0}",
    "bid4 {'P.bid_risk': 4}; spread-1 seeds 4000-4999; mean=27.290438495416225; paired {\"n\":265,\"diff\":-0.8770569997667927,\"se\":0.584177319160883,\"retail_diff\":-3.5926021514524527,\"arb_diff\":2.715545151635849,\"failures\":0}",
    "cap1000 {'C.askcap': 1000}; spread-1 seeds 4000-4999; mean=25.474168927290943; paired {\"n\":265,\"diff\":-2.693326567892076,\"se\":1.2798071781568088,\"retail_diff\":-6.227996507601132,\"arb_diff\":3.5346699397241506,\"failures\":0}",
    "cap500 {'C.askcap': 500}; spread-1 seeds 4000-4999; mean=19.035228625821887; paired {\"n\":265,\"diff\":-9.132266869361132,\"se\":2.1302415701808926,\"retail_diff\":-13.628827117109056,\"arb_diff\":4.496560247755848,\"failures\":0}",
    "cheapceil05 {'P.ammo_maxpay': 0, 'P.g_hi': 0.05}; spread-1 seeds 4000-4999; mean=28.53299179928113; paired {\"n\":265,\"diff\":0.36549630409811285,\"se\":0.23714951927354094,\"retail_diff\":-0.01311976147358514,\"arb_diff\":0.37861606556905686,\"failures\":0}",
    "cheapceil {'P.ammo_maxpay': 0, 'P.g_hi': 0.03}; spread-1 seeds 4000-4999; mean=28.53299179928113; paired {\"n\":265,\"diff\":0.36549630409811285,\"se\":0.23714951927354094,\"retail_diff\":-0.01311976147358514,\"arb_diff\":0.37861606556905686,\"failures\":0}",
    "dmin03 {'P.dmin': 0.3}; spread-1 seeds 4000-4999; mean=29.005912073559244; paired {\"n\":265,\"diff\":0.8384165783762255,\"se\":0.2997582244971853,\"retail_diff\":-0.36892392744679176,\"arb_diff\":1.2073405058256603,\"failures\":0}",
    "dmin03 {'P.dmin': 0.3}; spread-1 seeds 6000-6999; mean=44.70319448395122; paired {\"n\":246,\"diff\":0.39125348938170695,\"se\":0.30175137587514234,\"retail_diff\":-0.5809245936857713,\"arb_diff\":0.9721780830695124,\"failures\":0}",
    "dmin06 {'P.dmin': 0.6}; spread-1 seeds 4000-4999; mean=25.57767465749019; paired {\"n\":265,\"diff\":-2.5898208376928302,\"se\":0.888234401215598,\"retail_diff\":-11.525582296306037,\"arb_diff\":8.935761458587548,\"failures\":0}",
    "fastdecay {'P.zd': 2}; spread-1 seeds 4000-4999; mean=27.39195813042566; paired {\"n\":265,\"diff\":-0.7755373647573592,\"se\":0.21346024795143234,\"retail_diff\":-0.08427669360528314,\"arb_diff\":-0.6912606711490565,\"failures\":0}",
    "floor_kl02 {'P.ammo_q': 0, 'P.g_hi': 0, 'P.kL': 0.2}; spread-1 seeds 4000-4999; mean=28.975134835332074; paired {\"n\":265,\"diff\":0.8076393401490558,\"se\":0.39076873272490126,\"retail_diff\":-0.674651822326037,\"arb_diff\":1.4822911624947173,\"failures\":0}",
    "floor_margin {'P.g_hi': 0, 'P.ammo_q': 0, 'P.dmin': 0.3}; spread-1 seeds 4000-4999; mean=28.971915254367925; paired {\"n\":265,\"diff\":0.8044197591849047,\"se\":0.22898414952198778,\"retail_diff\":-0.43344849505245225,\"arb_diff\":1.2378682542373585,\"failures\":0}",
    "floor_margin {'P.g_hi': 0, 'P.ammo_q': 0, 'P.dmin': 0.3}; spread-1 seeds 6000-6999; mean=44.9197017137; paired {\"n\":246,\"diff\":0.6077607191304878,\"se\":0.29533721903000426,\"retail_diff\":-0.6647658170808936,\"arb_diff\":1.2725265362182927,\"failures\":0}",
    "floor_margin_pfl {'P.g_hi': 0, 'P.ammo_q': 0, 'P.dmin': 0.3, 'P.pfl': 1e-06}; spread-1 seeds 4000-4999; mean=29.159910021010187; paired {\"n\":265,\"diff\":0.9924145258271693,\"se\":0.24355716852645742,\"retail_diff\":-0.2508811282294336,\"arb_diff\":1.2432956540573585,\"failures\":0}",
    "floor_margin_pfl {'P.g_hi': 0, 'P.ammo_q': 0, 'P.dmin': 0.3, 'P.pfl': 1e-06}; spread-1 seeds 6000-6999; mean=45.04454162302886; paired {\"n\":246,\"diff\":0.7326006284593494,\"se\":0.31264895481724214,\"retail_diff\":-0.5356786142662594,\"arb_diff\":1.2682792427313008,\"failures\":0}",
    "floorbig {'P.ammo_q': 0, 'P.g_hi': 0, 'P.qf': 1000}; spread-1 seeds 4000-4999; mean=28.31995656057434; paired {\"n\":265,\"diff\":0.15246106539132073,\"se\":0.21262234942205294,\"retail_diff\":0.2673954277022646,\"arb_diff\":-0.11493436230452823,\"failures\":0}",
    "floorlow {'P.ammo_q': 0, 'P.g_hi': 0, 'P.pmaxf': 0.02}; spread-1 seeds 4000-4999; mean=28.519525762084527; paired {\"n\":265,\"diff\":0.3520302669015092,\"se\":0.22755108579554695,\"retail_diff\":-0.41583848086943365,\"arb_diff\":0.7678687477671698,\"failures\":0}",
    "floornarrow {'P.ammo_q': 0, 'P.g_hi': 0, 'P.g_lo': 0.05}; spread-1 seeds 4000-4999; mean=28.466008326784152; paired {\"n\":265,\"diff\":0.29851283160113185,\"se\":0.2167820964639374,\"retail_diff\":-0.41470349375433935,\"arb_diff\":0.7132163253513207,\"failures\":0}",
    "floornarrow {'P.ammo_q': 0, 'P.g_hi': 0, 'P.g_lo': 0.05}; spread-1 seeds 6000-6999; mean=44.49794458798293; paired {\"n\":246,\"diff\":0.1860035934134145,\"se\":0.2487919843596939,\"retail_diff\":-0.46229628172561005,\"arb_diff\":0.6482998751337399,\"failures\":0}",
    "flooronly {'P.ammo_maxpay': 0, 'P.g_hi': 0}; spread-1 seeds 4000-4999; mean=28.53299179928113; paired {\"n\":265,\"diff\":0.36549630409811285,\"se\":0.23714951927354094,\"retail_diff\":-0.01311976147358514,\"arb_diff\":0.37861606556905686,\"failures\":0}",
    "flooronly_big {'P.ammo_maxpay': 0, 'P.g_hi': 0, 'P.qf': 1000}; spread-1 seeds 4000-4999; mean=28.31995656057434; paired {\"n\":265,\"diff\":0.15246106539132073,\"se\":0.21262234942205294,\"retail_diff\":0.2673954277022646,\"arb_diff\":-0.11493436230452823,\"failures\":0}",
    "flooronly_big {'P.ammo_maxpay': 0, 'P.g_hi': 0, 'P.qf': 1000}; spread-1 seeds 6000-6999; mean=44.25432247839106; paired {\"n\":246,\"diff\":-0.057618516178455564,\"se\":0.19328326135608592,\"retail_diff\":0.23182251492195163,\"arb_diff\":-0.28944103110040653,\"failures\":0}",
    "floorstock {'P.ammo_q': 0, 'P.g_hi': 0, 'P.f1': 1}; spread-1 seeds 4000-4999; mean=28.70830788349019; paired {\"n\":265,\"diff\":0.5408123883071697,\"se\":0.39140153617661005,\"retail_diff\":-0.009599938240000213,\"arb_diff\":0.5504123265433964,\"failures\":0}",
    "floorwide {'P.ammo_q': 0, 'P.g_hi': 0, 'P.g_lo': 0.5}; spread-1 seeds 4000-4999; mean=27.310009332292076; paired {\"n\":265,\"diff\":-0.8574861628909439,\"se\":0.653067098647097,\"retail_diff\":0.5489787958075479,\"arb_diff\":-1.4064649586901887,\"failures\":0}",
    "freeammo {'P.ammo_q': 0, 'P.g_hi': 0}; spread-1 seeds 4000-4999; mean=28.53299179928113; paired {\"n\":265,\"diff\":0.36549630409811285,\"se\":0.23714951927354094,\"retail_diff\":-0.01311976147358514,\"arb_diff\":0.37861606556905686,\"failures\":0}",
    "freeammo {'P.ammo_q': 0, 'P.g_hi': 0}; spread-1 seeds 6000-6999; mean=44.47854104722155; paired {\"n\":246,\"diff\":0.1666000526520323,\"se\":0.12670415711223112,\"retail_diff\":0.035218575316260686,\"arb_diff\":0.13138147733414632,\"failures\":0}",
    "kl02 {'P.kL': 0.2}; spread-1 seeds 4000-4999; mean=29.045611764584905; paired {\"n\":265,\"diff\":0.8781162694018864,\"se\":0.4266238248917203,\"retail_diff\":-0.5693046265332065,\"arb_diff\":1.44742089595283,\"failures\":0}",
    "kl02 {'P.kL': 0.2}; spread-1 seeds 6000-6999; mean=44.32306713299228; paired {\"n\":246,\"diff\":0.011126138422763932,\"se\":0.2565072591352963,\"retail_diff\":-0.7455699193069107,\"arb_diff\":0.7566960577191058,\"failures\":0}",
    "kl03 {'P.kL': 0.3}; spread-1 seeds 4000-4999; mean=28.8940503025317; paired {\"n\":265,\"diff\":0.7265548073486785,\"se\":0.78728483629224,\"retail_diff\":-1.8654394132271697,\"arb_diff\":2.5919942205762263,\"failures\":0}",
    "kl03 {'P.kL': 0.3}; spread-1 seeds 6000-6999; mean=43.85343885920935; paired {\"n\":246,\"diff\":-0.4585021353601622,\"se\":0.4533277866115457,\"retail_diff\":-2.477841668376423,\"arb_diff\":2.0193395330101627,\"failures\":0}",
    "kl03_freeammo {'P.kL': 0.3, 'P.ammo_q': 0, 'P.g_hi': 0}; spread-1 seeds 4000-4999; mean=28.902873097115847; paired {\"n\":265,\"diff\":0.7353776019328295,\"se\":0.7777582075465522,\"retail_diff\":-1.949732429460755,\"arb_diff\":2.6851100313913205,\"failures\":0}",
    "kl03_noammo {'P.kL': 0.3, 'P.ammo': 0}; spread-1 seeds 4000-4999; mean=29.047869037716982; paired {\"n\":265,\"diff\":0.880373542533962,\"se\":0.8035149906699545,\"retail_diff\":-2.2178451008588675,\"arb_diff\":3.0982186433890564,\"failures\":0}",
    "kl03_noammo {'P.kL': 0.3, 'P.ammo': 0}; spread-1 seeds 6000-6999; mean=43.890968856232114; paired {\"n\":246,\"diff\":-0.4209721383373984,\"se\":0.48036832294301185,\"retail_diff\":-2.61358684338374,\"arb_diff\":2.19261470504065,\"failures\":0}",
    "kl04 {'P.kL': 0.4}; spread-1 seeds 4000-4999; mean=28.07422063808868; paired {\"n\":265,\"diff\":-0.0932748570943403,\"se\":1.0464174511531297,\"retail_diff\":-3.192057328775849,\"arb_diff\":3.0987824716811323,\"failures\":0}",
    "kl06 {'P.kL': 0.6}; spread-1 seeds 4000-4999; mean=27.182675142894716; paired {\"n\":265,\"diff\":-0.9848203522883024,\"se\":1.2308608769306835,\"retail_diff\":-5.358633059315848,\"arb_diff\":4.373812707043774,\"failures\":0}",
    "kl1 {'P.kL': 1}; spread-1 seeds 4000-4999; mean=24.68938846697283; paired {\"n\":265,\"diff\":-3.4781070282101894,\"se\":1.3555535502464382,\"retail_diff\":-8.702859030282264,\"arb_diff\":5.224752002075849,\"failures\":0}",
    "klf03 {'P.kLf': 0.3}; spread-1 seeds 4000-4999; mean=28.31206989706604; paired {\"n\":265,\"diff\":0.1445744018830183,\"se\":0.33547321152237636,\"retail_diff\":-1.2015192110615092,\"arb_diff\":1.3460936129486794,\"failures\":0}",
    "klf1 {'P.kLf': 1}; spread-1 seeds 4000-4999; mean=27.64322545994566; paired {\"n\":265,\"diff\":-0.5242700352373588,\"se\":0.3943582167982855,\"retail_diff\":-1.857190976009056,\"arb_diff\":1.332920940766415,\"failures\":0}",
    "lowrisk {'P.kLf': 0.3, 'P.kLb': 0.3}; spread-1 seeds 4000-4999; mean=28.297291142306037; paired {\"n\":265,\"diff\":0.12979564712301836,\"se\":0.37574037389218207,\"retail_diff\":-1.7214434475599998,\"arb_diff\":1.8512390946901887,\"failures\":0}",
    "margin_pfl {'P.dmin': 0.3, 'P.pfl': 1e-06}; spread-1 seeds 4000-4999; mean=29.192813254031698; paired {\"n\":265,\"diff\":1.0253177588486784,\"se\":0.3167770064025856,\"retail_diff\":-0.18745014679358438,\"arb_diff\":1.2127679056456604,\"failures\":0}",
    "margin_pfl {'P.dmin': 0.3, 'P.pfl': 1e-06}; spread-1 seeds 6000-6999; mean=44.82803439328008; paired {\"n\":246,\"diff\":0.5160933987105686,\"se\":0.31919303602318017,\"retail_diff\":-0.4518373908711373,\"arb_diff\":0.9679307895825204,\"failures\":0}",
    "netall {'P.net_all_stock': 1}; spread-1 seeds 4000-4999; mean=28.134635989525663; paired {\"n\":265,\"diff\":-0.032859505657358484,\"se\":0.039038432028108846,\"retail_diff\":-0.05032508952981147,\"arb_diff\":0.017465583871698127,\"failures\":0}",
    "netallfloor {'P.net_all_stock': 1, 'P.g_hi': 0, 'P.ammo_q': 0}; spread-1 seeds 4000-4999; mean=28.504273152810566; paired {\"n\":265,\"diff\":0.3367776576275473,\"se\":0.24111011946932134,\"retail_diff\":-0.054557095197358504,\"arb_diff\":0.3913347528230189,\"failures\":0}",
    "netfloor {'P.net_stock': 1, 'P.g_hi': 0, 'P.ammo_q': 0}; spread-1 seeds 4000-4999; mean=28.50392793267887; paired {\"n\":265,\"diff\":0.3364324374958492,\"se\":0.24111138927890577,\"retail_diff\":-0.054542586032075464,\"arb_diff\":0.39097502352603775,\"failures\":0}",
    "netfloor_f1 {'P.net_stock': 1, 'P.g_hi': 0, 'P.ammo_q': 0, 'P.f1': 1}; spread-1 seeds 4000-4999; mean=28.65894464704264; paired {\"n\":265,\"diff\":0.4914491518596225,\"se\":0.39328202348758723,\"retail_diff\":-0.05499179841207542,\"arb_diff\":0.546440950269434,\"failures\":0}",
    "netstock {'P.net_stock': 1}; spread-1 seeds 4000-4999; mean=28.13390435185849; paired {\"n\":265,\"diff\":-0.033591143324528304,\"se\":0.039018603245951744,\"retail_diff\":-0.05023411522037748,\"arb_diff\":0.016642971895094394,\"failures\":0}",
    "noammo {'P.ammo': 0}; spread-1 seeds 4000-4999; mean=28.437077349316226; paired {\"n\":265,\"diff\":0.2695818541332072,\"se\":0.23401089240717945,\"retail_diff\":-0.38278430000603747,\"arb_diff\":0.6523661541358491,\"failures\":0}",
    "noammo {'P.ammo': 0}; spread-1 seeds 6000-6999; mean=44.43191497952195; paired {\"n\":246,\"diff\":0.11997398495243895,\"se\":0.23918404077209066,\"retail_diff\":-0.4345588829414637,\"arb_diff\":0.5545328678890245,\"failures\":0}",
    "noammo_risk14 {'P.ammo': 0, 'P.kA': 1.4, 'P.kLf': 0.3}; spread-1 seeds 4000-4999; mean=27.965480944066414; paired {\"n\":265,\"diff\":-0.20201455111660455,\"se\":0.3971057875006576,\"retail_diff\":-2.816088200750943,\"arb_diff\":2.6140736496056607,\"failures\":0}",
    "nodecay {'P.zd': 0}; spread-1 seeds 4000-4999; mean=27.366475012684905; paired {\"n\":265,\"diff\":-0.8010204824981138,\"se\":0.9050657464083458,\"retail_diff\":-1.9820708634275472,\"arb_diff\":1.1810503809286792,\"failures\":0}",
    "noq1 {'P.ydf1': 0}; spread-1 seeds 4000-4999; mean=7.543537875523019; paired {\"n\":265,\"diff\":-20.62395761966,\"se\":4.472549581397331,\"retail_diff\":-30.112798060750567,\"arb_diff\":9.488840441115471,\"failures\":0}",
    "pfl002 {'P.pfl': 0.002}; spread-1 seeds 4000-4999; mean=28.031234660236226; paired {\"n\":265,\"diff\":-0.13626083494679295,\"se\":0.20700683786995575,\"retail_diff\":-0.3393640634132076,\"arb_diff\":0.2031032284664152,\"failures\":0}",
    "pfl0 {'P.pfl': 1e-06}; spread-1 seeds 4000-4999; mean=28.32952364772302; paired {\"n\":265,\"diff\":0.16202815253999986,\"se\":0.057602191616682036,\"retail_diff\":0.16921436383622632,\"arb_diff\":-0.007186211294339622,\"failures\":0}",
    "pfl0 {'P.pfl': 1e-06}; spread-1 seeds 6000-6999; mean=44.36236063240203; paired {\"n\":246,\"diff\":0.05041963783252023,\"se\":0.031764707714135254,\"retail_diff\":0.05877387094349579,\"arb_diff\":-0.008354233110569102,\"failures\":0}",
    "q1_f10 {'P.f1': 1}; spread-1 seeds 4000-4999; mean=28.32180648273849; paired {\"n\":265,\"diff\":0.15431098755547196,\"se\":0.14757968627341783,\"retail_diff\":-0.0004525920222641093,\"arb_diff\":0.1547635795766038,\"failures\":0}",
    "q1_f10 {'P.f1': 1}; spread-1 seeds 6000-6999; mean=44.90676480913171; paired {\"n\":246,\"diff\":0.5948238145621949,\"se\":0.5319566229014691,\"retail_diff\":0.19634353839227645,\"arb_diff\":0.39848027616869913,\"failures\":0}",
    "q1_g2 {'P.g1': 2}; spread-1 seeds 4000-4999; mean=27.835768291356604; paired {\"n\":265,\"diff\":-0.3317272038264153,\"se\":0.3332222986936544,\"retail_diff\":-0.4508691542392452,\"arb_diff\":0.11914195041283018,\"failures\":0}",
    "q1_yd01 {'P.ydf1': 0.1}; spread-1 seeds 4000-4999; mean=11.427125820325283; paired {\"n\":265,\"diff\":-16.740369674857735,\"se\":3.8337492811946863,\"retail_diff\":-18.77058257188189,\"arb_diff\":2.030212897041132,\"failures\":0}",
    "q1_yd15 {'P.ydf1': 1.5}; spread-1 seeds 4000-4999; mean=21.296231833426038; paired {\"n\":265,\"diff\":-6.8712636617569816,\"se\":1.5534367883806857,\"retail_diff\":0.9703759290611321,\"arb_diff\":-7.841639590814717,\"failures\":0}",
    "q1_yd1 {'P.ydf1': 1}; spread-1 seeds 4000-4999; mean=25.55223642465019; paired {\"n\":265,\"diff\":-2.615259070532831,\"se\":0.8032028143665738,\"retail_diff\":0.9424822590535851,\"arb_diff\":-3.557741329585283,\"failures\":0}",
    "qmax10000 {'P.qmax': 10000}; spread-1 seeds 4000-4999; mean=27.796280233066415; paired {\"n\":265,\"diff\":-0.37121526211660416,\"se\":0.2772699205327375,\"retail_diff\":0.1476660300958491,\"arb_diff\":-0.5188812922090565,\"failures\":0}",
    "qmax1000 {'P.qmax': 1000}; spread-1 seeds 4000-4999; mean=25.518480057060376; paired {\"n\":265,\"diff\":-2.6490154381226425,\"se\":1.2779263462733934,\"retail_diff\":-6.21272294926566,\"arb_diff\":3.5637075111577357,\"failures\":0}",
    "qmax6000 {'P.qmax': 6000}; spread-1 seeds 4000-4999; mean=27.86857505666453; paired {\"n\":265,\"diff\":-0.29892043851849126,\"se\":0.2722296964077629,\"retail_diff\":0.18051606273320744,\"arb_diff\":-0.4794365012486792,\"failures\":0}",
    "risk04 {'P.kA': 0.4}; spread-1 seeds 4000-4999; mean=27.322324977321887; paired {\"n\":265,\"diff\":-0.8451705178611324,\"se\":0.3926842661960433,\"retail_diff\":3.117793601129057,\"arb_diff\":-3.962964118935849,\"failures\":0}",
    "risk14 {'P.kA': 1.4}; spread-1 seeds 4000-4999; mean=27.920912464894716; paired {\"n\":265,\"diff\":-0.24658303028830247,\"se\":0.19891444100425867,\"retail_diff\":-1.38515111936,\"arb_diff\":1.1385680890350944,\"failures\":0}",
    "risk28 {'P.kA': 2.8}; spread-1 seeds 4000-4999; mean=27.691510377241887; paired {\"n\":265,\"diff\":-0.47598511794113263,\"se\":0.24087042301523273,\"retail_diff\":-1.7533789817245284,\"arb_diff\":1.2773938637460378,\"failures\":0}",
    "scar001 {'C.scar': 0.001}; spread-1 seeds 4000-4999; mean=28.368859015302263; paired {\"n\":265,\"diff\":0.2013635201192451,\"se\":0.2880602091922806,\"retail_diff\":0.44313678389169814,\"arb_diff\":-0.24177326377056585,\"failures\":0}",
    "scar005 {'C.scar': 0.005}; spread-1 seeds 4000-4999; mean=28.584644104586037; paired {\"n\":265,\"diff\":0.4171486094030181,\"se\":0.35687267117733046,\"retail_diff\":-0.596207656276981,\"arb_diff\":1.0133562656788677,\"failures\":0}",
    "scar0 {'C.scar': 0}; spread-1 seeds 4000-4999; mean=27.44158455848; paired {\"n\":265,\"diff\":-0.7259109367030191,\"se\":0.4913614337846424,\"retail_diff\":0.3018749400645285,\"arb_diff\":-1.0277858767573584,\"failures\":0}",
    "slowdecay {'P.zd': 0.5}; spread-1 seeds 4000-4999; mean=28.54392130087283; paired {\"n\":265,\"diff\":0.3764258056898111,\"se\":0.5913278863918111,\"retail_diff\":-0.4170670402969809,\"arb_diff\":0.7934928459875474,\"failures\":0}",
    "slowdecay {'P.zd': 0.5}; spread-1 seeds 6000-6999; mean=44.32914808262398; paired {\"n\":246,\"diff\":0.01720708805447112,\"se\":0.12005071274141098,\"retail_diff\":-0.16847863375691005,\"arb_diff\":0.18568572180934942,\"failures\":0}",
    "smallq1 {'P.ydf1': 0.2, 'P.f1': 0.25}; spread-1 seeds 4000-4999; mean=16.89526434001585; paired {\"n\":265,\"diff\":-11.272231155167171,\"se\":3.183301157329583,\"retail_diff\":-12.456010355734717,\"arb_diff\":1.183779200563019,\"failures\":0}",
    "sticky0 {'P.sticky': 0}; spread-1 seeds 4000-4999; mean=21.729183185270568; paired {\"n\":265,\"diff\":-6.438312309912454,\"se\":1.032400810849649,\"retail_diff\":-4.545381115149812,\"arb_diff\":-1.892931194775472,\"failures\":0}",
    "stock_near15 {'P.g1': 2, 'P.ydf1': 1.5, 'P.f1': 1}; spread-1 seeds 4000-4999; mean=20.38222280714; paired {\"n\":265,\"diff\":-7.78527268804302,\"se\":1.7357841279696755,\"retail_diff\":0.593706521920755,\"arb_diff\":-8.378979209955094,\"failures\":0}",
    "stock_near_big {'P.g1': 2, 'P.ydf1': 1, 'P.f1': 1}; spread-1 seeds 4000-4999; mean=25.317590703596604; paired {\"n\":265,\"diff\":-2.849904791586416,\"se\":0.8453968432219969,\"retail_diff\":0.6657945837694343,\"arb_diff\":-3.5156993753516983,\"failures\":0}",
    "stock_nearer_big {'P.g1': 1, 'P.ydf1': 1, 'P.f1': 1}; spread-1 seeds 4000-4999; mean=25.69758489547132; paired {\"n\":265,\"diff\":-2.469910599711699,\"se\":0.8953655662963999,\"retail_diff\":0.5014164357283021,\"arb_diff\":-2.9713270354373584,\"failures\":0}",
    "stockbig {'P.ydf1': 1, 'P.f1': 1}; spread-1 seeds 4000-4999; mean=25.51244854458604; paired {\"n\":265,\"diff\":-2.6550469505969816,\"se\":0.7994664801616264,\"retail_diff\":0.896119586095472,\"arb_diff\":-3.551166536687547,\"failures\":0}",
    "stockearly {'P.g1': 10}; spread-1 seeds 4000-4999; mean=27.927318870379622; paired {\"n\":265,\"diff\":-0.2401766248033964,\"se\":0.30864021844675943,\"retail_diff\":-0.001128181289811511,\"arb_diff\":-0.23904844351471696,\"failures\":0}",
    "Selection before holdout: {\"4000\":{\"versus_base\":{\"n\":265,\"diff\":1.0253177588486784,\"se\":0.3167770064025856,\"retail_diff\":-0.18745014679358438,\"arb_diff\":1.2127679056456604,\"failures\":0},\"probability_floor_increment\":{\"n\":265,\"diff\":0.18690118047245297,\"se\":0.06636825523240238,\"retail_diff\":0.18147378065320735,\"arb_diff\":0.0054273998199999805,\"failures\":0},\"excluded_procurement_increment\":{\"n\":265,\"diff\":-0.032903233021509166,\"se\":0.2427263072499907,\"retail_diff\":-0.06343098143584922,\"arb_diff\":0.03052774841169812,\"failures\":0}},\"6000\":{\"versus_base\":{\"n\":246,\"diff\":0.5160933987105686,\"se\":0.31919303602318017,\"retail_diff\":-0.4518373908711373,\"arb_diff\":0.9679307895825204,\"failures\":0},\"probability_floor_increment\":{\"n\":246,\"diff\":0.1248399093288616,\"se\":0.06238645424896486,\"retail_diff\":0.1290872028146341,\"arb_diff\":-0.0042472934869918705,\"failures\":0},\"excluded_procurement_increment\":{\"n\":246,\"diff\":0.21650722974878078,\"se\":0.11150322296215051,\"retail_diff\":-0.08384122339512216,\"arb_diff\":0.3003484531487804,\"failures\":0}}}; retained increments positive in both groups; additional procurement cuts failed the incremental first-group check.",
    "At freeze, unfinished reserve/uncovered sweeps and redundant full noammo training scoring were canceled to reserve compute for the required evaluations. No partial simulation scores were used or reported. Completed subset trial records above remain valid; candidate source copies were preserved.",
    "Exact non-target full-result equality reference 1000-1599: 456 paired runs; base and selected strategy share canonical result-vector SHA256 d653d62b153f9b3147f3ea9d68ca28c7b47da812f00b53f89b8c1115855e96c2",
    "Exact non-target full-result equality training 4000-7999: 3001 paired runs; base and selected strategy share canonical result-vector SHA256 cc25940bb3b0617577780793852172c9d01381a921d23d279fb1b3e133e92b3c",
    "Exact non-target full-result equality unseen 50000-53999: 2984 paired runs; base and selected strategy share canonical result-vector SHA256 8d78359f464935ba9560bdf309f0ecd24ab7b6e0a03a9c1dac424a14ff845bb8",
    "Reference full training baseline, seeds 4000-7999: {\"mean_edge\":98.74404012314791,\"retail_edge\":124.32965738115115,\"arb_edge\":-25.585617258018875,\"simulations\":4000,\"seed_start\":4000,\"failures\":0}",
    "Frozen selected margin_pfl; training all spreads {\"mean_edge\": 98.9689746680761, \"retail_edge\": 124.29013580906907, \"arb_edge\": -25.321161141007252, \"simulations\": 4000, \"seed_start\": 4000, \"failures\": 0}; unseen all spreads {\"mean_edge\": 98.52619137752235, \"retail_edge\": 125.95607618418198, \"arb_edge\": -27.4298848066588, \"simulations\": 4000, \"seed_start\": 50000, \"failures\": 0}; unseen paired all spreads {\"n\": 4000, \"diff\": 0.24555749049252498, \"se\": 0.06381676155994687, \"retail_diff\": -0.06299609210224989, \"arb_diff\": 0.3085535825935501, \"failures\": 0}; unseen paired spread 1 {\"n\": 1016, \"diff\": 0.9667617735926181, \"se\": 0.24996913452108194, \"retail_diff\": -0.24801611063877912, \"arb_diff\": 1.2147778842265753, \"failures\": 0}"
  ],
  "next": "The held-out spread-1 gain is positive and exceeds twice its paired standard error. Use the four seats' all-spread paired holdout gains to assess additivity, weighting conditional spread gains by run frequency. Merge only the frozen per-spread settings, verify exact preservation of unaffected spreads, and evaluate the merged strategy on new shared seeds before spending a wider goal. These trials support checking selective quote margins and boundary belief calibration; blanket quote or stock cuts sacrificed too much retail. All-spread holdout paired evidence: {\"n\":4000,\"diff\":0.24555749049252498,\"se\":0.06381676155994687,\"retail_diff\":-0.06299609210224989,\"arb_diff\":0.3085535825935501,\"failures\":0}"
}