{"approach": "Only for self.s == 3, suppress fresh ammunition and tick-1 stock purchases for three callbacks starting with the callback observing a downward rival-bid shift of at least two ticks or a missing buy probe more than half a tick below the previous sub-tick belief mean. These crossings can leave the estimate stale; delaying new cover aims to avoid paying into that move. Ordinary bid/ask target sizing, the original probability filter, and base parameters are unchanged. This fixed three-callback mechanism passed discovery, unused choosing, and the full halved choosing set before freezing; confirmation is reported separately. The positive confirmation mean is smaller than its standard error.", "blocked": null, "spread": 3, "base_mean_edge": 108.63974289615767, "found": ["Logging-only diagnostic on 160 spread-3 seeds, first matching seeds in 30000..30999: unmodified total/retail/arb scores exactly identical on every run; failures=0. Loss numbers below are positive dollars; windows overlap and cannot be added. Shift/probe lag 1 is the first scored step at the callback observing the signal; arb lag 1 is the next scored step after the fill.", "rival best bid or ask changes by at least two ticks: events=9091; next-1..5 step counts=[9091, 9085, 9077, 9067, 9059]; next-1..5 arb loss totals=[136.13380497017886, 92.2647272109295, 114.37061551987371, 96.08864524383179, 117.77265834109124]; union steps=34683, union arb loss=389.71150644360154, loss/step=0.011236384004947713; plain steps=285317, plain arb loss=4248.305105653188, loss/step=0.014889772097888271.", "surprising probe: removed ask above prior mean by >0.5 tick or removed bid below it by >0.5 tick: events=48320; next-1..5 step counts=[48320, 48317, 48317, 48314, 48313]; next-1..5 arb loss totals=[676.9823337250363, 521.4996761652918, 630.6460889207193, 543.5306927456412, 442.14080245285425]; union steps=160866, union arb loss=1828.890087066367, loss/step=0.01136902817914517; plain steps=159134, plain arb loss=2809.1265250304227, loss/step=0.017652585399917195.", "arbitrage fills an order whose pre-fill quantity exceeds 0.01 shares: events=16410; next-1..5 step counts=[16410, 16409, 16407, 16403, 16401]; next-1..5 arb loss totals=[557.3028517501709, 444.4150957258209, 403.47190244508454, 622.9083132568451, 462.36439143203205]; union steps=70545, union arb loss=1547.0365034476981, loss/step=0.02192978245726413; plain steps=249455, plain arb loss=3090.9801086490916, loss/step=0.012390932667812197.", "Any removed probe-sized order tick (remaining quantity <=0.010000001), including routine depletion; lag 1 starts after the observing callback: events=319762; next-1..5 step counts=[319603, 319444, 319284, 319124, 318964]; next-1..5 arb loss totals=[4616.984393572488, 4618.842506964684, 4619.120819396679, 4605.37306049647, 4603.478242434212]; union steps=319647, union arb loss=4625.059993092692, loss/step=0.014469273896181387; plain steps=353, plain arb loss=12.95661900409762, loss/step=0.0367043031277553. These near-continuous signals are not selective stale-estimate warnings.", "Literal any arbitrage fill, including tiny probes; lag 1 starts after the fill: events=319952; next-1..5 step counts=[319794, 319635, 319476, 319316, 319156]; next-1..5 arb loss totals=[4634.054278479682, 4629.9432917210315, 4629.165090182397, 4629.835724256933, 4616.679136979014]; union steps=319833, union arb loss=4637.938241886052, loss/step=0.01450112478038868; plain steps=167, plain arb loss=0.07837021073734823, loss/step=0.0004692826990260373. These near-continuous signals are not selective stale-estimate warnings."], "holdout": {"mean_edge": 126.58355487307674, "retail_edge": 155.39882800218663, "arb_edge": -28.815273129051484, "failures": 0}, "diff": {"mean": 0.060450114178910885, "standard_error": 0.10657843571557472, "retail": -0.06726682179752483, "arb": 0.12771693597465336, "trimmed": 0.030032759339090772, "runs_up": 204, "runs_down": 157}, "others_identical": {"runs": 450, "identical": true}, "seconds": {"start": 96.98001461452805, "yours": 99.26206299988553}, "code": "\"\"\"Crossing-cover base with isolated, untuned per-spread overrides stacked: each acts only in runs of its own competitor spread.\"\"\"\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 == 4:\n                # Censored compound-Poisson flow likelihood, using only our fills.\n                self.f4_exposure = [0, 0]\n                self.f4_events = [0, 0]\n                self.f4_weights = [[0.0] * 9, [0.0] * 9]\n                self.f4_means = [2.64 + i * (6.336 - 2.64) / 8 for i in range(9)]\n                # Positive aggregate flow is approximately lognormal; +0.065\n                # accounts for the occasional second arrival in a timestep.\n                self.f4_mu = [math.log(m) - 0.72 + 0.065 for m in self.f4_means]\n                self.f4_last = [None, None]\n                self.f4_rate = 0.1265\n                self.f4_mean = 4.488\n                self.f4_flow = self.f4_rate * self.f4_mean\n                self.f4_extreme = inv(1 - 1e-6)\n            if self.s == 2:\n                self.params.update(dict(W=150, ammo_pmax=0.02, fy=0.7, fu=0.25, Hu=500))\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 == 4:\n            for side, filled, bound in ((0, state.sell_filled_quantity, ca), (1, state.buy_filled_quantity, cb)):\n                last = self.f4_last[side]\n                if last is None:\n                    continue\n                tick, conv, cap, old_bound, ids = last\n                if (side == 0 and bound > old_bound + 1) or (side == 1 and bound < old_bound - 1):\n                    continue\n                # Track only the main quote, excluding probes and stock orders.\n                remaining = sum(o.remaining_quantity for o in state.own_orders if o.order_id in ids)\n                value = max(0.0, cap - remaining * conv)\n                self.f4_exposure[side] += 1\n                if value > 0.01:\n                    self.f4_events[side] += 1\n                    censored = remaining < 0.011\n                    logv = math.log(max(value, 0.01))\n                    weights = self.f4_weights[side]\n                    for i, mu4 in enumerate(self.f4_mu):\n                        z4 = (logv - mu4) / 1.2\n                        weights[i] += math.log(max(1e-12, 1.0 - cdf(z4))) if censored else -0.5 * z4 * z4\n            if state.step % 25 == 0:\n                exposure = sum(self.f4_exposure)\n                events = sum(self.f4_events)\n                event_probability = (events + 80.0 * (1.0 - math.exp(-0.1265))) / (exposure + 80.0)\n                self.f4_rate = max(0.077, min(0.176, -math.log(max(1e-6, 1.0 - event_probability))))\n                weights = [a + b for a, b in zip(*self.f4_weights)]\n                peak = max(weights)\n                weights = [math.exp(w - peak) for w in weights]\n                self.f4_mean = sum(m * w for m, w in zip(self.f4_means, weights)) / sum(weights)\n                self.f4_flow = self.f4_rate * self.f4_mean\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        after_up = after_down = False\n        if self.s == 3:\n            live_b = {o.price_ticks for o in state.own_orders if o.side is Side.BUY and o.remaining_quantity <= PROBE + 1e-9}\n            live_a = {o.price_ticks for o in state.own_orders if o.side is Side.SELL and o.remaining_quantity <= PROBE + 1e-9}\n            prior_tick = sum(c * w for c, w in zip(self.bc, self.bw)) if self.bc else 50.0\n            ea, eb = self.pa - live_a, self.pb - live_b\n            up = (self.pca is not None and ca > self.pca + 1) or bool(ea and max(ea) > prior_tick + 0.5)\n            down = (self.pcb is not None and cb < self.pcb - 1) or bool(eb and min(eb) < prior_tick - 0.5)\n            if up:\n                self.after_up_until = state.step + 3\n            if down:\n                self.after_down_until = state.step + 3\n            after_up = state.step < getattr(self, 'after_up_until', -1)\n            after_down = state.step < getattr(self, 'after_down_until', -1)\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            if self.s == 4:\n                exp = math.exp\n                if self.bc == cs and 1.0 <= wid <= 6.0 and nb == 8 * wid:\n                    # On this stationary grid, spacing is exactly 1/8 tick.\n                    # Equal index distances therefore have bit-identical d*d*k.\n                    # Reuse exp values while retaining the original sum order.\n                    kernel = []\n                    c0 = cs[0]\n                    for ci in self.bc:\n                        d = c0 - ci\n                        d2 = d * d * k\n                        kernel.append(exp(d2) if d2 > -12.5 else 0.0)\n                    kernel = kernel[:0:-1] + kernel\n                    for i in range(nb):\n                        t = uni\n                        start = nb - 1 - i\n                        for wi, e in zip(self.bw, kernel[start:start + nb]):\n                            if e:\n                                t += wi * e\n                        ws.append(t)\n                else:\n                    previous = tuple(zip(self.bc, self.bw))\n                    for c in cs:\n                        t = uni\n                        for ci, wi in previous:\n                            d = c - ci\n                            d2 = d * d * k\n                            if d2 > -12.5:\n                                t += wi * exp(d2)\n                        ws.append(t)\n            else:\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            if self.s == 4:\n                ja = jb = 0.0\n                for p, w in jp:\n                    if x > p:\n                        ja += w * (x - p)\n                    else:\n                        jb += w * (p - x)\n            else:\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            if self.s == 4 and tail <= 1e-6:\n                return min(P['qmax'], math.exp(mu + P['sig_n'] * self.f4_extreme) / px)\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            if self.s == 4 and phat * 100 - t < P['dmin']:\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            if self.s == 4 and t - phat * 100 < P['dmin']:\n                return 0.0\n            a, b = AB(t / 100.0)\n            if t - phat * 100 < P['dmin']:\n                return 0.0\n            if self.s == 4:\n                tail = b * kA / max(self.f4_rate * a, 1e-30)\n                if a <= 0 or tail >= 1.0:\n                    return 0.0\n                return min(P['qmax'], math.exp(math.log(self.f4_mean) - 0.72 + 1.2 * (self.f4_extreme if tail <= 1e-6 else inv(1 - tail))) / (t / 100.0))\n            if self.s == 2 and phat < 0.1:\n                a = max(0.0, a - 0.0015 * (1 - min(1.0, state.yes_inventory / 3000.0)))\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            threshold = max(P['min_ahead'], 20 * 100.0 / comp) if self.s == 3 and step == -1 and 1 <= comp <= 5 else P['min_ahead']\n            if sticky and sum(o.remaining_quantity for o in orders if o.price_ticks == comp and o.order_id in self.ahead) >= threshold:\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        if self.s == 1 and ask_t == 2 and ask_t < ca and phat < 0.01:\n            qa *= 5\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            flow_scale = self.f4_flow / 0.6 if self.s == 4 else 1.0\n            target = min(flow_scale * P['ydem'] * min(H, P['W']) / x, capw)\n            full = min(flow_scale * 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 == 4:\n                stock_rate *= self.f4_flow / 0.6\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        if self.s == 3 and after_down:\n            qam = 0.0\n            q1 = 0.0\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) or (self.s == 1 and (o.side is Side.SELL) and o.price_ticks <= 2 and o.order_id in self.ahead)):\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                if self.s == 2:\n                    ub = min(ub, max(0.0, free - 200 * min(1.0, H / 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        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        if self.s == 4:\n            self.f4_last = [None, None]\n            # Eligibility is decided before observing fills, so depleted quotes\n            # remain in the sample as right-censored observations.\n            for side, tick, bound, conv, distance in (\n                (0, ask_t, ca, ask_t / 100.0, ask_t / 100.0 - phat),\n                (1, bid_t, cb, max(phat, 0.05), phat - bid_t / 100.0)):\n                if distance < max(0.01, 3.0 * self.st / 100.0):\n                    continue\n                if side == 0:\n                    if not (ask_t < ca or any(o.price_ticks == ask_t and o.order_id in self.ahead for o in asks)):\n                        continue\n                    orders = asks\n                    order_side = Side.SELL\n                else:\n                    if not (bid_t > cb or any(o.price_ticks == bid_t and o.order_id in self.ahead for o in bids)):\n                        continue\n                    if (qam > 0 and amt >= bid_t) or (q1 > 0 and bid_t <= 1):\n                        continue\n                    orders = bids\n                    order_side = Side.BUY\n                tracked = {o.order_id: o.remaining_quantity for o in orders if o.order_id in kept_ids and o.price_ticks == tick}\n                tracked.update({o.client_order_id: o.quantity for o in out if o.side is order_side and o.price_ticks == tick and o.client_order_id is not None})\n                cap = sum(tracked.values()) * conv\n                if cap >= 0.5:\n                    self.f4_last[side] = (tick, conv, cap, bound, tracked)\n        return actions + out\n", "code_sha256": "4b355108973846632dfa97b86aec145210a2185176176bae66779c0b1da6e2f4", "tried": ["Scorer: required 600 simulations, seeds 1000..1599, --workers 4, no sandbox; exact author mean reproduced, failures=0. The scorer overlapped with exploratory logging/evaluation and exceeded 300 seconds (still running at 317.60761308670044 seconds); subsequent required counts halved: confirming uses every other matching spread-3 seed in 90000..97999, other-spread checks use 150 each (450 total), timing uses 100 each. Already running exploratory jobs completed; their exact counts are reported below.", "screen reset_shift (reset sub-tick belief to uniform on a rival quote shift of at least two ticks): {\"n\":160,\"mean\":-0.01124277136937622,\"standard_error\":0.028104698590839066,\"retail\":0.011483477026875844,\"arb\":-0.02272624837937505,\"trimmed\":-0.008682154987858074,\"runs_up\":72,\"runs_down\":85,\"median\":-0.0008415069000022868,\"failures\":0}", "screen reset_probe (reset belief after any interior probe depletion): {\"n\":160,\"mean\":-0.8867673332618737,\"standard_error\":0.41019704008156355,\"retail\":-0.33016342674437305,\"arb\":-0.5566039065374994,\"trimmed\":-0.21674077254785584,\"runs_up\":62,\"runs_down\":98,\"median\":-0.21692525634999882,\"failures\":0}", "screen reset_both (reset belief after either quote-shift or interior-probe signal): {\"n\":160,\"mean\":-0.8730730450506261,\"standard_error\":0.4117951426803494,\"retail\":-0.3001739367856247,\"arb\":-0.5728991082824995,\"trimmed\":-0.18571637314071546,\"runs_up\":62,\"runs_down\":98,\"median\":-0.25951372194999855,\"failures\":0}", "screen wide_shift (broaden predictive Gaussian SD to at least half the feasible interval width after quote shift): {\"n\":160,\"mean\":-0.01841750793249967,\"standard_error\":0.011867663691498508,\"retail\":-0.021750164718125208,\"arb\":0.003332656781250036,\"trimmed\":0.0041668198521429365,\"runs_up\":56,\"runs_down\":62,\"median\":0.0,\"failures\":0}", "screen wide_both (broaden predictive Gaussian after quote-shift or interior-probe signal): {\"n\":160,\"mean\":-0.2741578482731268,\"standard_error\":0.3041238511246539,\"retail\":0.06613675260187654,\"arb\":-0.3402946008831248,\"trimmed\":-0.07021114087000152,\"runs_up\":67,\"runs_down\":84,\"median\":-0.0007665911500005507,\"failures\":0}", "screen cautious_shift (halve bid, ask, ammunition and tick-1 stock quantities for the callback observing a two-tick rival quote shift): {\"n\":160,\"mean\":0.09784719289312398,\"standard_error\":0.07104701576879899,\"retail\":-0.32031954921312367,\"arb\":0.4181667421175001,\"trimmed\":-0.048996831897143774,\"runs_up\":79,\"runs_down\":74,\"median\":0.0,\"failures\":0}", "screen cautious_both (halve quantities after quote-shift or any interior-probe signal): {\"n\":160,\"mean\":-1.0914772934868742,\"standard_error\":1.8984262354426389,\"retail\":-7.903522693977499,\"arb\":6.81204540041125,\"trimmed\":-2.3081370104028567,\"runs_up\":43,\"runs_down\":117,\"median\":-1.9104465161999968,\"failures\":0}", "screen wide_persist (broaden predictive Gaussian for three callbacks after either signal): {\"n\":160,\"mean\":-0.2819627212631255,\"standard_error\":0.39345883946160987,\"retail\":-0.6046552545881249,\"arb\":0.322692533345625,\"trimmed\":-0.04407520996500093,\"runs_up\":77,\"runs_down\":83,\"median\":-0.05603555260000004,\"failures\":0}", "screen2 reset_probe_surprise (reset belief only after probe crossing more than half a tick against the prior mean): {\"n\":160,\"mean\":-1.2543934133068757,\"standard_error\":0.47306102223948304,\"retail\":-0.9698525151987508,\"arb\":-0.2845408980831251,\"trimmed\":-0.3690362095650015,\"runs_up\":55,\"runs_down\":105,\"median\":-0.4721890238000057,\"failures\":0}", "screen2 reset_both_surprise (reset after quote shift or surprising probe): {\"n\":160,\"mean\":-1.2663594119168762,\"standard_error\":0.47296457827910243,\"retail\":-0.9537071309306241,\"arb\":-0.31265228096625003,\"trimmed\":-0.3820345021257156,\"runs_up\":51,\"runs_down\":109,\"median\":-0.43775536690000116,\"failures\":0}", "screen2 wide_both_surprise (broaden predictive Gaussian after quote shift or surprising probe): {\"n\":160,\"mean\":-0.6421474245818749,\"standard_error\":0.40186912958306886,\"retail\":-0.8726920609731244,\"arb\":0.2305446364012499,\"trimmed\":-0.01676283046142809,\"runs_up\":77,\"runs_down\":83,\"median\":-0.04567622024999807,\"failures\":0}", "screen2 wide_persist_surprise (broaden predictive Gaussian for three callbacks after quote shift or surprising probe): {\"n\":160,\"mean\":-0.8563945139424991,\"standard_error\":0.4068104357262193,\"retail\":-1.1948593185793743,\"arb\":0.33846480466562484,\"trimmed\":-0.15241344151499894,\"runs_up\":73,\"runs_down\":87,\"median\":-0.15184952865000412,\"failures\":0}", "screen2 cautious_both_surprise (halve quantities for one callback after quote shift or surprising probe): {\"n\":160,\"mean\":-1.388495488139376,\"standard_error\":0.4356988502337966,\"retail\":-3.705754495153124,\"arb\":2.3172590070187504,\"trimmed\":-0.9155778863878575,\"runs_up\":49,\"runs_down\":111,\"median\":-0.9865114244499988,\"failures\":0}", "screen2 down_stock1 (suppress stock/ammunition purchases for one callback after downward quote shift or surprising downward probe): {\"n\":160,\"mean\":0.007348184557498661,\"standard_error\":0.036672903894872405,\"retail\":-0.005477214125624919,\"arb\":0.012825398685625067,\"trimmed\":-0.001985397602858084,\"runs_up\":17,\"runs_down\":15,\"median\":0.0,\"failures\":0}", "screen2 down_stock3 (suppress stock/ammunition purchases for three callbacks after downward signal): {\"n\":160,\"mean\":0.024016273051874298,\"standard_error\":0.05911689390856458,\"retail\":-0.04460969278499971,\"arb\":0.0686259658375003,\"trimmed\":0.011925696488571504,\"runs_up\":29,\"runs_down\":24,\"median\":0.0,\"failures\":0}", "screen2 down_bid3 (halve regular bids and suppress stock/ammunition for three callbacks after downward signal): {\"n\":160,\"mean\":-1.1379356900425013,\"standard_error\":0.19675713295232744,\"retail\":-1.667418818058124,\"arb\":0.5294831280006254,\"trimmed\":-0.5057480397935722,\"runs_up\":43,\"runs_down\":117,\"median\":-0.6263349165999941,\"failures\":0}", "screen2 direction1 (halve only the quote side exposed to the observed move and suppress stock after downward moves, one callback): {\"n\":160,\"mean\":-1.3593613544675,\"standard_error\":0.2977354409564666,\"retail\":-2.32156758340375,\"arb\":0.9622062289493752,\"trimmed\":-0.888434530057856,\"runs_up\":41,\"runs_down\":119,\"median\":-1.040874563500001,\"failures\":0}", "screen2 direction3 (same directional response for three callbacks): {\"n\":160,\"mean\":-2.0771996414775002,\"standard_error\":0.46282450322853247,\"retail\":-3.4820820411431246,\"arb\":1.4048823996587503,\"trimmed\":-1.1619017465464279,\"runs_up\":39,\"runs_down\":121,\"median\":-1.2138270866500012,\"failures\":0}", "screen3 full_probe (use completely depleted probe sides as probability bounds, retaining existing bound-conflict protection): {\"n\":160,\"mean\":-15.708044084408126,\"standard_error\":2.0299990549198985,\"retail\":-0.4415111688331239,\"arb\":-15.266532915554375,\"trimmed\":-9.346069445556427,\"runs_up\":15,\"runs_down\":145,\"median\":-5.5215595039,\"failures\":0}", "screen3 full_probe_reset (full-depletion bounds plus uniform reset on complete probe-side depletion): {\"n\":160,\"mean\":-15.630425860203125,\"standard_error\":1.9665734327262792,\"retail\":-0.9335149816412498,\"arb\":-14.696910878571874,\"trimmed\":-8.642257108499287,\"runs_up\":14,\"runs_down\":146,\"median\":-5.588366006999999,\"failures\":0}", "screen4 main_half (halve all quote and stock quantities for one callback after a previously tracked main order fully disappears): {\"n\":160,\"mean\":-1.1994774712575016,\"standard_error\":0.5199713949490545,\"retail\":-2.191280603838123,\"arb\":0.9918031325762503,\"trimmed\":-0.5255547522442873,\"runs_up\":57,\"runs_down\":103,\"median\":-0.4599764045499999,\"failures\":0}", "screen4 main_reset (uniform belief reset on tracked main-order disappearance): {\"n\":160,\"mean\":-0.2596753537981253,\"standard_error\":1.0488158103021425,\"retail\":-0.8709729857924983,\"arb\":0.6112976320075002,\"trimmed\":-0.2018657296785731,\"runs_up\":70,\"runs_down\":90,\"median\":-0.2307291824999993,\"failures\":0}", "screen4 main_wide (broaden predictive Gaussian on tracked main-order disappearance): {\"n\":160,\"mean\":-1.025862119773125,\"standard_error\":0.5313788315587211,\"retail\":-0.4265701437318742,\"arb\":-0.5992919760362497,\"trimmed\":-0.172053665872857,\"runs_up\":74,\"runs_down\":86,\"median\":-0.042101591850000286,\"failures\":0}", "validation cautious_shift (halve bid, ask, ammunition and tick-1 stock quantities for the callback observing a two-tick rival quote shift): {\"n\":243,\"mean\":0.18416315636501884,\"standard_error\":0.11505624932805787,\"retail\":-0.23632772269423893,\"arb\":0.42049087905720134,\"trimmed\":-0.049446120717939045,\"runs_up\":125,\"runs_down\":106,\"median\":0.00979191210000252,\"failures\":0}", "validation cautious_both_surprise (halve quantities for one callback after quote shift or surprising probe): {\"n\":243,\"mean\":-1.8070269201275728,\"standard_error\":0.7318472143509537,\"retail\":-3.74465420915144,\"arb\":1.9376272890477364,\"trimmed\":-1.0537570710417048,\"runs_up\":81,\"runs_down\":162,\"median\":-0.9244046819000005,\"failures\":0}", "validation full_probe (use completely depleted probe sides as probability bounds, retaining existing bound-conflict protection): {\"n\":243,\"mean\":-21.592370336471607,\"standard_error\":3.1481218354687517,\"retail\":-0.05762433826666559,\"arb\":-21.534745998206585,\"trimmed\":-13.504839753801795,\"runs_up\":18,\"runs_down\":225,\"median\":-7.891006992599998,\"failures\":0}", "Unused choosing reset_shift: {\"n\":243,\"mean\":0.0004916425773638819,\"standard_error\":0.025407018144856353,\"retail\":0.06838226994773534,\"arb\":-0.06789062737201637,\"trimmed\":-0.012736542018836417,\"runs_up\":119,\"runs_down\":121,\"median\":0.0,\"failures\":0}", "Unused choosing down_stock1: {\"n\":243,\"mean\":0.05975934677366038,\"standard_error\":0.07302512699615761,\"retail\":0.03454305445555575,\"arb\":0.02521629231563775,\"trimmed\":0.0027585364264565244,\"runs_up\":38,\"runs_down\":25,\"median\":0.0,\"failures\":0}", "Final choosing, every other matching spread-3 seed in 30000..37999: {\"n\":969,\"mean\":0.1528414938377707,\"standard_error\":0.08960042638767515,\"retail\":-0.2478163078661505,\"arb\":0.4006578017033022,\"trimmed\":0.08942841669399339,\"runs_up\":520,\"runs_down\":410,\"median\":0.016888475500000055,\"failures\":0}", "Selection policy: {\"primary\":\"cautious_shift\",\"criterion\":\"Positive paired mean, positive mean after removing 20 largest absolute differences, and more runs up than down, separately on discovery and unused choosing seeds; positive corresponding metrics on the half-sized full choosing set. No confirmation results inspected before freeze.\",\"discovery\":\"first 160 spread-3 matching seeds in 30000..30999\",\"validation\":\"every other spread-3 matching seed in 31000..32999\",\"final_choose\":\"every other spread-3 matching seed in 30000..37999\",\"secondary\":\"reset_shift, pending the same discovery and unused-choosing criteria\",\"tertiary\":\"down_stock1, pending the same discovery and unused-choosing criteria\",\"confirmation_rule\":\"Frozen candidate is not retuned. Return original if confirmation fails to show positive mean, positive 20-outlier-trimmed mean, and more improved than worsened runs; report that rejected confirmation in tried.\",\"quaternary\":\"The pre-existing down_stock3 experiment passed discovery: validate its fixed three-callback design under the same unused-choosing and full-choosing criteria before freezing.\"}", "Final choosing down_stock1, every other matching spread-3 seed in 30000..37999: {\"n\":969,\"mean\":0.00813118859256916,\"standard_error\":0.01764264447477784,\"retail\":-0.009034599743962602,\"arb\":0.017165788337048505,\"trimmed\":0.012850946475658149,\"runs_up\":139,\"runs_down\":92,\"median\":0.0,\"failures\":0}", "Unused choosing down_stock3: {\"n\":243,\"mean\":0.07080532132427823,\"standard_error\":0.06875916451014087,\"retail\":-0.08164054525720135,\"arb\":0.1524458665794238,\"trimmed\":0.013398257036321653,\"runs_up\":55,\"runs_down\":43,\"median\":0.0,\"failures\":0}", "Full half-sized choosing down_stock3: {\"n\":969,\"mean\":0.02013688470815234,\"standard_error\":0.03544020487134477,\"retail\":-0.03370230370794622,\"arb\":0.05383918841609905,\"trimmed\":0.06390643149209664,\"runs_up\":205,\"runs_down\":134,\"median\":0.0,\"failures\":0}", "Freeze decision before inspecting confirmation results: {\"name\":\"down_stock3\",\"code_sha256\":\"4b355108973846632dfa97b86aec145210a2185176176bae66779c0b1da6e2f4\",\"decision\":\"Require positive mean, positive mean after removing the 20 largest absolute run differences, and more improved than worsened runs on discovery, unused choosing, and the half-sized full choosing set. No confirmation score used.\",\"metrics\":{\"cautious_shift\":{\"discovery\":{\"n\":160,\"mean\":0.09784719289312398,\"standard_error\":0.07104701576879899,\"retail\":-0.32031954921312367,\"arb\":0.4181667421175001,\"trimmed\":-0.048996831897143774,\"runs_up\":79,\"runs_down\":74,\"median\":0.0,\"failures\":0},\"unused_choosing\":{\"n\":243,\"mean\":0.18416315636501884,\"standard_error\":0.11505624932805787,\"retail\":-0.23632772269423893,\"arb\":0.42049087905720134,\"trimmed\":-0.049446120717939045,\"runs_up\":125,\"runs_down\":106,\"median\":0.00979191210000252,\"failures\":0},\"full_half_choosing\":{\"n\":969,\"mean\":0.1528414938377707,\"standard_error\":0.08960042638767515,\"retail\":-0.2478163078661505,\"arb\":0.4006578017033022,\"trimmed\":0.08942841669399339,\"runs_up\":520,\"runs_down\":410,\"median\":0.016888475500000055,\"failures\":0}},\"reset_shift\":{\"discovery\":{\"n\":160,\"mean\":-0.01124277136937622,\"standard_error\":0.028104698590839066,\"retail\":0.011483477026875844,\"arb\":-0.02272624837937505,\"trimmed\":-0.008682154987858074,\"runs_up\":72,\"runs_down\":85,\"median\":-0.0008415069000022868,\"failures\":0},\"unused_choosing\":{\"n\":243,\"mean\":0.0004916425773638819,\"standard_error\":0.025407018144856353,\"retail\":0.06838226994773534,\"arb\":-0.06789062737201637,\"trimmed\":-0.012736542018836417,\"runs_up\":119,\"runs_down\":121,\"median\":0.0,\"failures\":0}},\"down_stock3\":{\"discovery\":{\"n\":160,\"mean\":0.024016273051874298,\"standard_error\":0.05911689390856458,\"retail\":-0.04460969278499971,\"arb\":0.0686259658375003,\"trimmed\":0.011925696488571504,\"runs_up\":29,\"runs_down\":24,\"median\":0.0,\"failures\":0},\"unused_choosing\":{\"n\":243,\"mean\":0.07080532132427823,\"standard_error\":0.06875916451014087,\"retail\":-0.08164054525720135,\"arb\":0.1524458665794238,\"trimmed\":0.013398257036321653,\"runs_up\":55,\"runs_down\":43,\"median\":0.0,\"failures\":0},\"full_half_choosing\":{\"n\":969,\"mean\":0.02013688470815234,\"standard_error\":0.03544020487134477,\"retail\":-0.03370230370794622,\"arb\":0.05383918841609905,\"trimmed\":0.06390643149209664,\"runs_up\":205,\"runs_down\":134,\"median\":0.0,\"failures\":0}},\"down_stock1\":{\"discovery\":{\"n\":160,\"mean\":0.007348184557498661,\"standard_error\":0.036672903894872405,\"retail\":-0.005477214125624919,\"arb\":0.012825398685625067,\"trimmed\":-0.001985397602858084,\"runs_up\":17,\"runs_down\":15,\"median\":0.0,\"failures\":0},\"unused_choosing\":{\"n\":243,\"mean\":0.05975934677366038,\"standard_error\":0.07302512699615761,\"retail\":0.03454305445555575,\"arb\":0.02521629231563775,\"trimmed\":0.0027585364264565244,\"runs_up\":38,\"runs_down\":25,\"median\":0.0,\"failures\":0},\"full_half_choosing\":{\"n\":969,\"mean\":0.00813118859256916,\"standard_error\":0.01764264447477784,\"retail\":-0.009034599743962602,\"arb\":0.017165788337048505,\"trimmed\":0.012850946475658149,\"runs_up\":139,\"runs_down\":92,\"median\":0.0,\"failures\":0}}},\"approach\":\"Only for self.s == 3, suppress fresh ammunition and tick-1 stock purchases for three callbacks starting with the callback observing a downward rival-bid shift of at least two ticks or a missing buy probe more than half a tick below the previous sub-tick belief mean. These crossings can leave the estimate stale; delaying new cover aims to avoid paying into that move. Ordinary bid/ask target sizing, the original probability filter, and base parameters are unchanged. This fixed three-callback mechanism passed discovery, unused choosing, and the full halved choosing set before freezing; confirmation is reported separately.\"}", "Other spreads: complete SimulationResult dictionaries compared, including wealth and inventory; {\"runs\":450,\"identical\":true,\"mismatches\":[],\"failures\":0,\"by_spread\":{\"1\":150,\"2\":150,\"4\":150}}", "Timing: both files in one process, same 100 spread-3 seeds, no sandbox; {\"runs_each\":100,\"method\":\"balanced interleaving in one process\",\"start\":96.98001461452805,\"yours\":99.26206299988553,\"start_cpu\":96.96280601300009,\"yours_cpu\":99.24491408400002}"], "next": "Explain the large negative stock-holdback outliers using only callback-visible inventory, cash and directional probe evidence. Test keeping cover purchases when near-term ask demand would otherwise become uncovered, rather than strengthening a generic post-move pause. Use new choosing and confirming seeds; this small positive mean remains statistically uncertain."}