{"approach":"No change retained. Returned the supplied base code byte for byte: no purchase-control idea improved both the 1024-run discovery set and the independent 1012-run tuning validation set. The strongest screen gains were dominated by rare large losses and did not generalize. Tested near-crossing reserve gates, volatility gates, partial distant-bid caps, stock horizons/rates, FIFO-ask guards, and accounting for already-resting bids. All changes were gated to spread 1. Only tuning traces and scores informed those choices; no experimental candidate was promoted to unseen scoring. The unchanged baseline was separately frozen before its repeat unseen and other-spread evaluations. Baseline scorer: from the simulator clone, python3 -m orderbook_pm_challenge run ../base.py --simulations 4000 --seed-start 4000 --workers 4 --json, no sandbox; exactly 98.4694596619638, zero failures. Python standard library only; simulator commit b244530ee2a6247b5f930830eeca9dd950da0e7e, default 2000 steps. Spread seeds were enumerated with sample_config(ChallengeConfig(), ParameterVariance(), seed=N).competitor.spread_ticks over 8000..15999 and 60000..67999. Full SimulationResult dictionaries match on all 1969 spread-1 unseen runs and on 300 seeds of each other spread starting from 60000. The reported holdout scores come from a separate repeat of the frozen unchanged file, not copied aggregates. Traces recorded actual fill price/probability for every YES purchase at <=5 cents and matched later covered sales FIFO; unsold purchase cost is not treated as scored edge loss. Instrumentation reproduced every full plain-engine result on all tuning and unseen seeds. Timing is a single-process 200-pair test with one warmup each and alternating execution order, timing engine construction plus run; sampling and module loading excluded. An initial test overlapped other simulation batches, so it is recorded separately and one quiet repeat is reported in seconds. The returned strategy is byte-identical to the base; timing differences are measurements of the same code. Trace audit: {\"method\":\"Actual true probability at fill; FIFO attribution across all YES lots; only actual covered sales consume stock; no sales inferred from uncovered asks. Every <=5-cent purchase traced, including probes. Instrumented full SimulationResult checked against plain engine run by run.\",\"base_tuning\":{\"runs\":2036,\"purchase_fills\":422438,\"purchased_quantity_per_run\":11424.344037387405,\"sold_quantity_per_run\":8158.327652244295,\"sold_fraction\":0.7141178194166145,\"purchase_cost_per_run\":164.13108978466283,\"unsold_cost_per_run\":36.71504332019958,\"purchase_edge_per_run\":-12.241291622233412,\"overpay_above_half_tick_quantity_per_run\":827.5010756395928,\"overpay_above_half_tick_edge_per_run\":-6.3796860152920125,\"tick1_purchased_per_run\":8909.054754414205,\"tick1_sold_per_run\":5869.45569744208,\"all_results_match_plain\":true},\"base_unseen\":{\"runs\":1969,\"purchase_fills\":451908,\"purchased_quantity_per_run\":12317.834992461114,\"sold_quantity_per_run\":9144.036079221696,\"sold_fraction\":0.742341173170295,\"purchase_cost_per_run\":177.68027927968674,\"unsold_cost_per_run\":35.01830858296402,\"purchase_edge_per_run\":-13.452570756891408,\"overpay_above_half_tick_quantity_per_run\":1020.6176587111969,\"overpay_above_half_tick_edge_per_run\":-7.577232678045233,\"tick1_purchased_per_run\":9620.535896396363,\"tick1_sold_per_run\":6637.174377852305,\"all_results_match_plain\":true},\"fifo_checks\":{\"runs\":4005,\"purchase_lots\":874346,\"lot_bounds_valid\":true,\"chronological\":true,\"remaining_cheap_yes_never_exceeds_final_yes\":true}}","blocked":null,"python_version":"3.12.3","spread":1,"base_mean_edge":98.4694596619638,"runs":{"tuning":2036,"unseen":1969},"base_unseen":{"mean_edge":41.78494849744236,"retail_edge":65.91107840022042,"arb_edge":-24.1261299027871},"holdout":{"mean_edge":41.78494849744236,"retail_edge":65.91107840022042,"arb_edge":-24.1261299027871,"failures":0},"diff":{"mean":0.0,"standard_error":0.0,"retail":0.0,"arb":0.0},"others_identical":{"runs":900,"identical":true},"seconds":{"base":92.833317338489,"yours":92.71133088413626},"code":"\"\"\"Crossing-cover base with isolated, untuned spread overrides.\"\"\"\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)\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.s = None          # competitor spread parameter\n        self.flow_notional = 0.0\n        self.flow_exposure = 0\n        self.last_ask_tick = None\n        self.last_quote_exposed = False\n        self.last_flow_ca = None\n        self.last_flow_cap = 0.0\n        self.last_flow_correction = 1.0\n        self.params = P.copy()\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            if self.s == 3:\n                self.params.update({'flow_prior': 200, 'flow_level': 0.6, 'flow_strength': 1.0, 'flow_safety': 2.0, 'flow_exposure_min': 5.0})\n        P = self.params\n        if self.s == 3 and self.last_quote_exposed and ca <= self.last_flow_ca + 1:\n            self.flow_exposure += 1\n            self.flow_notional += min(self.last_flow_cap, state.sell_filled_quantity * self.last_ask_tick / 100.0) * self.last_flow_correction\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            return 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 = 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            stock_rate = P['ydf1']\n            if self.s == 3:\n                flow = (self.flow_notional + P['flow_prior'] * P['flow_level']) / (P['flow_prior'] + self.flow_exposure)\n                scale = max(0.5, min(2.0, flow / P['flow_level']))\n                stock_rate *= 1.0 + P['flow_strength'] * (scale - 1.0)\n            q1 = max(0.0, stock_rate * min(H, P['Wf']) / (self.s / 100.0) - Y)\n\n        # Bridge expected retail demand until another tick crossing is available.\n        if 0.02 < phat < 0.1:\n            ct = max(2, min(99, int(math.floor(ptick))))\n            wealth = state.cash + Y * phat\n            goal = min(1 * qa, 0.3 * max(wealth, 0.0) / phat)\n            if Y < goal and ct < ask_t:\n                amt, qam = ct, min(3000.0, goal - 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 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                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        if self.s == 3:\n            self.last_ask_tick = ask_t\n            self.last_flow_ca = ca\n            exposed_qty = ka + sum(o.quantity for o in out if o.side is Side.SELL and o.price_ticks == ask_t and o.quantity > PROBE)\n            self.last_flow_cap = exposed_qty * ask_t / 100.0\n            self.last_quote_exposed = ask_t / 100.0 > phat + max(0.005, P['flow_safety'] * self.st / 100.0) and self.last_flow_cap >= P['flow_exposure_min']\n            if self.last_quote_exposed:\n                logcap = math.log(self.last_flow_cap)\n                mu_flow = math.log(P['m']) - 0.5 * P['sig_n'] ** 2\n                clipped = P['m'] * cdf((logcap - mu_flow - P['sig_n'] ** 2) / P['sig_n']) + self.last_flow_cap * (1.0 - cdf((logcap - mu_flow) / P['sig_n']))\n                self.last_flow_correction = min(3.0, P['m'] / max(clipped, 0.01))\n        return actions + out\n","code_sha256":"dcf68e0c9a7b06f90cf70a833357b60e2208b5b3e2971e7dddf02986d4747076","tried":["Reserve bid only if competitor best ask<=3; {\"discovery_256\":{\"diff\":{\"mean\":5.502981058923829,\"standard_error\":4.598841557651251,\"retail\":-1.2012682563496095,\"arb\":6.704249315273828},\"failures\":0}}","Reserve bid only if competitor best bid<=1; {\"discovery_256\":{\"diff\":{\"mean\":5.502981058923829,\"standard_error\":4.598841557651251,\"retail\":-1.2012682563496095,\"arb\":6.704249315273828},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":1.5937033072092774,\"standard_error\":1.2376895502203507,\"retail\":-0.6609939924786135,\"arb\":2.254697299687793},\"failures\":0}}","Reserve bid only if competitor best bid<=1 and ask<=3; {\"discovery_256\":{\"diff\":{\"mean\":5.502981058923829,\"standard_error\":4.598841557651251,\"retail\":-1.2012682563496095,\"arb\":6.704249315273828},\"failures\":0}}","Cap distant (phat>1.5 cents) reserve order at 12000 shares; {\"discovery_256\":{\"diff\":{\"mean\":1.2329008195398434,\"standard_error\":1.228361542187227,\"retail\":-1.1258971494390628,\"arb\":2.3587979689804683},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":0.25569031289501964,\"standard_error\":0.6195030198176336,\"retail\":-0.5547024591416019,\"arb\":0.8103927720357421},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-1.970396171736166,\"standard_error\":0.48873045488573263,\"retail\":-1.2082494805820154,\"arb\":-0.7621466911534583},\"failures\":0}}","Cap distant (phat>1.5 cents) reserve order at 24000 shares; {\"discovery_256\":{\"diff\":{\"mean\":0.28080497182539055,\"standard_error\":0.6677380909642461,\"retail\":-0.4758758171214843,\"arb\":0.7566807889492185},\"failures\":0}}","Cap distant (phat>1.5 cents) reserve order at 3000 shares; {\"discovery_256\":{\"diff\":{\"mean\":3.4074686453757805,\"standard_error\":3.8350462280159996,\"retail\":-2.106617259521094,\"arb\":5.51408590489961},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":0.06573703599150355,\"standard_error\":1.1251874197244074,\"retail\":-1.2214415312364262,\"arb\":1.2871785672285154},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-2.159072334115612,\"standard_error\":2.125825987008374,\"retail\":-1.3539953627242092,\"arb\":-0.8050769713914032},\"failures\":0}}","Cap distant (phat>1.5 cents) reserve order at 6000 shares; {\"discovery_256\":{\"diff\":{\"mean\":1.0007667885578126,\"standard_error\":1.1478671756183607,\"retail\":-2.8831322276843747,\"arb\":3.883899016245703},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":-0.1998622118508788,\"standard_error\":0.6619927035798023,\"retail\":-1.2001908022936525,\"arb\":1.0003285904439452},\"failures\":0}}","Stock horizon Wf=100; {\"discovery_256\":{\"diff\":{\"mean\":-20.30890912561875,\"standard_error\":4.861753624861362,\"retail\":-25.106764552466014,\"arb\":4.797855426848047},\"failures\":0}}","Stock horizon Wf=200; {\"discovery_256\":{\"diff\":{\"mean\":-13.119153454116017,\"standard_error\":4.054671884517979,\"retail\":-14.328163518857814,\"arb\":1.2090100647496085},\"failures\":0}}","Stock horizon Wf=400; {\"discovery_256\":{\"diff\":{\"mean\":-4.732507219766406,\"standard_error\":3.1614682993167094,\"retail\":-3.7974981687300784,\"arb\":-0.9350090510371096},\"failures\":0}}","Stock horizon Wf=50; {\"discovery_256\":{\"diff\":{\"mean\":-20.997255619233595,\"standard_error\":6.539362142527422,\"retail\":-33.36312770863398,\"arb\":12.365872089403906},\"failures\":0}}","Stock horizon Wf=800; {\"discovery_256\":{\"diff\":{\"mean\":-1.3496965133546872,\"standard_error\":1.6072050493517251,\"retail\":-0.368735457613672,\"arb\":-0.9809610557429689},\"failures\":0}}","Tick-1 reserve only below 1.15 estimated cents (g1=0.15); {\"discovery_256\":{\"diff\":{\"mean\":-12.22532240564922,\"standard_error\":6.327153617087603,\"retail\":-13.327337641341407,\"arb\":1.1020152356874995},\"failures\":0}}","Tick-1 reserve only below 1.3 estimated cents (g1=0.3); {\"discovery_256\":{\"diff\":{\"mean\":-5.4652415762671875,\"standard_error\":5.8163390929199,\"retail\":-10.373985973151171,\"arb\":4.908744396882422},\"failures\":0}}","Tick-1 reserve only below 1.5 estimated cents (g1=0.5); {\"discovery_256\":{\"diff\":{\"mean\":3.7073669516550782,\"standard_error\":4.69354203435746,\"retail\":-3.4635658348820315,\"arb\":7.170932786545703},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":-1.356734356118164,\"standard_error\":1.4245514281400078,\"retail\":-1.9770139453183597,\"arb\":0.620279589201367},\"failures\":0}}","Tick-1 reserve only below 1.75 estimated cents (g1=0.75); {\"discovery_256\":{\"diff\":{\"mean\":5.806491094846485,\"standard_error\":4.60892689635426,\"retail\":-1.3873531283476561,\"arb\":7.19384422319414},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":1.8382040145594727,\"standard_error\":1.252188864539989,\"retail\":-0.7266780532954102,\"arb\":2.5648820678543944},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-1.3511127019596838,\"standard_error\":0.7100126106061005,\"retail\":-1.13379036468498,\"arb\":-0.2173223372740119},\"failures\":0}}","Tick-1 reserve only below 2.0 estimated cents (g1=1.0); {\"discovery_256\":{\"diff\":{\"mean\":5.833144574905078,\"standard_error\":4.611359552333837,\"retail\":-1.2170541156882813,\"arb\":7.050198690593359},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":1.7683318455369141,\"standard_error\":1.2539982304376485,\"retail\":-0.6836019960752932,\"arb\":2.4519338416118166},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-1.1705988219660082,\"standard_error\":0.49092163675179157,\"retail\":-0.9347016620737153,\"arb\":-0.23589715989160082},\"failures\":0}}","Tick-1 reserve only below 2.5 estimated cents (g1=1.5); {\"discovery_256\":{\"diff\":{\"mean\":5.502170614484766,\"standard_error\":4.5988452887334335,\"retail\":-1.2013056915421876,\"arb\":6.703476306026953},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":1.593436248112793,\"standard_error\":1.2376898680581707,\"retail\":-0.6610677992634767,\"arb\":2.254504047376074},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-0.8250906641083005,\"standard_error\":0.3884475507825908,\"retail\":-0.8992539918592884,\"arb\":0.07416332775108692},\"failures\":0}}","Tick-1 reserve only below 3.0 estimated cents (g1=2.0); {\"discovery_256\":{\"diff\":{\"mean\":4.800716351551172,\"standard_error\":4.556854555998397,\"retail\":-0.8747088604460937,\"arb\":5.675425211997266},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":1.1742233337112304,\"standard_error\":1.2026560352259241,\"retail\":-0.4928360076500001,\"arb\":1.667059341361621},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-0.48582354925503957,\"standard_error\":0.26866779040547634,\"retail\":-0.3558044558678852,\"arb\":-0.1300190933865612},\"failures\":0}}","Tick-1 reserve only below 4.0 estimated cents (g1=3.0); {\"discovery_256\":{\"diff\":{\"mean\":0.4161666268753902,\"standard_error\":0.3139614082252183,\"retail\":-0.5578647898789063,\"arb\":0.9740314167539059},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":0.25265195109941396,\"standard_error\":0.1424419304838317,\"retail\":-0.35598281564902345,\"arb\":0.6086347667487304},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-0.16357911316363638,\"standard_error\":0.11306761495459733,\"retail\":-0.28680023725592874,\"arb\":0.1232211240923913},\"failures\":0}}","Subtract same-tick pending main bids from ammo; {\"discovery_256\":{\"diff\":{\"mean\":0.5705590823265618,\"standard_error\":0.6188952993897167,\"retail\":-0.005624717353906329,\"arb\":0.5761837996804685},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":0.16949323083994128,\"standard_error\":0.15704439921523738,\"retail\":-0.0911920085025391,\"arb\":0.26068523934228505},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-0.056153547509090726,\"standard_error\":0.061794585004293724,\"retail\":-0.06399496960553355,\"arb\":0.007841422095751173},\"failures\":0}}","Subtract all pending main bids and ammo from tick-1 stock target; {\"discovery_256\":{\"diff\":{\"mean\":0.02531858632460937,\"standard_error\":0.08048114350040869,\"retail\":-0.03218215672265615,\"arb\":0.05750074304882806},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":-0.01244163483281242,\"standard_error\":0.02975888801992225,\"retail\":-0.04282469042207031,\"arb\":0.03038305558955059},\"failures\":0}}","Subtract pending tick-1 main bids and ammo from tick-1 stock target; {\"discovery_256\":{\"diff\":{\"mean\":0.01517750707968743,\"standard_error\":0.07963909290623364,\"retail\":-0.01827580154609365,\"arb\":0.033453308626171685},\"failures\":0}}","Maximum tick-1 ammo premium 0.0 ticks; {\"discovery_256\":{\"diff\":{\"mean\":-0.0001656385425781448,\"standard_error\":0.0001656385425781448,\"retail\":-0.009356004932031259,\"arb\":0.009190366389453086},\"failures\":0}}","Maximum tick-1 ammo premium 0.15 ticks; {\"discovery_256\":{\"diff\":{\"mean\":-0.0001656385425781448,\"standard_error\":0.0001656385425781448,\"retail\":-0.009356004932031259,\"arb\":0.009190366389453086},\"failures\":0}}","Maximum tick-1 ammo premium 0.3 ticks; {\"discovery_256\":{\"diff\":{\"mean\":-0.0001656385425781448,\"standard_error\":0.0001656385425781448,\"retail\":-0.009356004932031259,\"arb\":0.009190366389453086},\"failures\":0}}","Maximum tick-1 ammo premium 0.5 ticks; {\"discovery_256\":{\"diff\":{\"mean\":-2.8590226171881783e-05,\"standard_error\":2.8590226171881783e-05,\"retail\":-0.002326307318750054,\"arb\":0.0022977170925780888},\"failures\":0}}","Maximum tick-1 ammo premium 0.7 ticks; {\"discovery_256\":{\"diff\":{\"mean\":0.0,\"standard_error\":0.0,\"retail\":0.0,\"arb\":0.0},\"failures\":0}}","Reserve bid only with profitable tick-2 ask; {\"discovery_256\":{\"diff\":{\"mean\":3.9029050906765614,\"standard_error\":4.808771100641369,\"retail\":-9.156361136207032,\"arb\":13.059266226880078},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":-2.684701821284473,\"standard_error\":1.613401853606841,\"retail\":-8.923404816984082,\"arb\":6.238702995697656},\"failures\":0}}","Reserve bid with profitable tick-2 ask or phat<1.5 cents; {\"discovery_256\":{\"diff\":{\"mean\":5.503244997122656,\"standard_error\":4.624150039162029,\"retail\":-2.129920773979297,\"arb\":7.633165771102344},\"failures\":0}}","Reserve bid only with profitable ask at tick 2 or lower; {\"discovery_256\":{\"diff\":{\"mean\":3.9029050906765614,\"standard_error\":4.808771100641369,\"retail\":-9.156361136207032,\"arb\":13.059266226880078},\"failures\":0}}","Low-probability tick-1 ammo target 0.1 times ask quantity; {\"discovery_256\":{\"diff\":{\"mean\":-0.0001656385425781448,\"standard_error\":0.0001656385425781448,\"retail\":-0.009356004932031259,\"arb\":0.009190366389453086},\"failures\":0}}","Low-probability tick-1 ammo target 0.25 times ask quantity; {\"discovery_256\":{\"diff\":{\"mean\":-0.0001656385425781448,\"standard_error\":0.0001656385425781448,\"retail\":-0.009356004932031259,\"arb\":0.009190366389453086},\"failures\":0}}","Low-probability tick-1 ammo target 0.5 times ask quantity; {\"discovery_256\":{\"diff\":{\"mean\":-2.4022898828135464e-05,\"standard_error\":2.4022898828135464e-05,\"retail\":-0.0018615145535156308,\"arb\":0.0018374916546874953},\"failures\":0}}","Reserve bid gap limited to 1.0 one-step sigma, floor 0.1 tick; {\"discovery_256\":{\"diff\":{\"mean\":-19.002131302327733,\"standard_error\":6.669275436944139,\"retail\":-15.222125625358203,\"arb\":-3.7800056769703128},\"failures\":0}}","Reserve bid gap limited to 2.0 one-step sigma, floor 0.1 tick; {\"discovery_256\":{\"diff\":{\"mean\":-10.899467903271875,\"standard_error\":6.185474129553159,\"retail\":-10.930103349920703,\"arb\":0.03063544663945305},\"failures\":0}}","Reserve bid gap limited to 3.0 one-step sigma, floor 0.1 tick; {\"discovery_256\":{\"diff\":{\"mean\":-2.9961999569105466,\"standard_error\":5.531894874195544,\"retail\":-6.636458695342188,\"arb\":3.6402587384316405},\"failures\":0}}","Reserve bid gap limited to 5.0 one-step sigma, floor 0.1 tick; {\"discovery_256\":{\"diff\":{\"mean\":2.2760045138136715,\"standard_error\":5.087480829740253,\"retail\":-2.186235493297656,\"arb\":4.462240007112109},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":-0.8779916981998048,\"standard_error\":1.6723334349906456,\"retail\":-1.3244965813727538,\"arb\":0.4465048831726562},\"failures\":0}}","Reserve bid gap limited to 8.0 one-step sigma, floor 0.1 tick; {\"discovery_256\":{\"diff\":{\"mean\":1.3231087401863282,\"standard_error\":0.8354458721423272,\"retail\":-0.8956608762691407,\"arb\":2.218769616455469},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":0.44225579014277344,\"standard_error\":0.5023044689443943,\"retail\":-0.39476558053466804,\"arb\":0.8370213706777344},\"failures\":0},\"validation_1012\":{\"diff\":{\"mean\":-1.1174104559731226,\"standard_error\":0.47224161040702756,\"retail\":-0.25695994388794463,\"arb\":-0.8604505120850791},\"failures\":0}}","Tick-1 stock rate ydf1=0.1; {\"discovery_256\":{\"diff\":{\"mean\":-14.457236695947266,\"standard_error\":6.6270208630180125,\"retail\":-27.443851140453127,\"arb\":12.98661444450742},\"failures\":0}}","Tick-1 stock rate ydf1=0.2; {\"discovery_256\":{\"diff\":{\"mean\":-6.985042893291797,\"standard_error\":6.001637330393449,\"retail\":-18.324704918828907,\"arb\":11.339662025535548},\"failures\":0}}","Tick-1 stock rate ydf1=0.3; {\"discovery_256\":{\"diff\":{\"mean\":-0.6198340302253907,\"standard_error\":5.535121166383952,\"retail\":-11.153387709787891,\"arb\":10.533553679563672},\"failures\":0}}","Tick-1 stock rate ydf1=0.4; {\"discovery_256\":{\"diff\":{\"mean\":2.3717097558445306,\"standard_error\":4.168886082211372,\"retail\":-5.6896159638414066,\"arb\":8.061325719684374},\"failures\":0},\"discovery_1024\":{\"diff\":{\"mean\":-2.307749972367676,\"standard_error\":1.2603448362065315,\"retail\":-5.172065210716601,\"arb\":2.864315238348535},\"failures\":0}}","Unchanged base retained; {\"tuning\":{},\"unseen\":{\"mean\":0.0,\"standard_error\":0.0,\"retail\":0.0,\"arb\":0.0},\"frozen_utc\":\"2026-11-06T08:44:54.013476+00:00\",\"other_spread_full_results_identical\":900,\"timing\":{\"base\":92.833317338489,\"yours\":92.71133088413626,\"failures\":[0,0],\"runs_per_strategy\":200,\"method\":\"One process; same 200 spread-1 unseen seeds; one warmup each; alternating execution order; engine construction and run timed, config sampling and factory load excluded.\"},\"initial_timing_with_concurrent_batches\":{\"base\":107.20519805070944,\"yours\":109.09285394358449,\"failures\":[0,0],\"runs_per_strategy\":200,\"method\":\"One process; same 200 spread-1 unseen seeds; one warmup each; alternating execution order; engine construction and run timed, config sampling and factory load excluded.\"}}"],"next":"Study a cash-budget-aware reserve policy on fresh seeds: the remaining effect is dominated by rare jumps and by how freed bid collateral changes later exposure. Preserve the single-spread gate and validate on an independent tuning block before unseen evaluation."}