{"approach": "The supplied base combines tick probes, a sub-tick probability belief, risk-sized passive quotes and cheap YES inventory. The graft fixes one FIFO bookkeeping gap: a surviving economic bid above the current competitor bid, or ask below its ask, is marked ahead even when it did not have that position at submission. The existing sticky-order manager can then retain its seniority when competitor liquidity returns at the same tick. Independent tail policies measured the value of resting queues; broader queue-joining and stock-retention grafts were rejected in training. The minimal acquired-priority patch was selected on all 600 training seeds and frozen before holdout evaluation.", "blocked": null, "python_version": "3.12.3", "base_mean_edge": 102.33197908899267, "score": {"mean_edge": 107.2752344684335, "retail_edge": 135.8212954705185, "arb_edge": -28.54606100209883, "simulations": 600, "seed_start": 1000, "failures": 0}, "holdout": {"mean_edge": 96.06785581906733, "simulations": 600, "seed_start": 30000, "failures": 0}, "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)\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\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        # A surviving economic order can acquire seniority after placement.\n        # Recognize the retreat before competitor liquidity returns at its tick.\n        for o in state.own_orders:\n            if o.remaining_quantity > PROBE + 1e-9 and (\n                (o.side is Side.BUY and o.price_ticks > cb) or\n                (o.side is Side.SELL and o.price_ticks < ca)\n            ):\n                self.ahead.add(o.order_id)\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            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 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        return actions + out\n", "code_sha256": "5f1f28ef998033d5e349998f8f7640a937e8cac8c8bd85c01fe7b6ceeadb8f5a", "tried": ["Official scorer calibration: mean_edge=102.33197908899267, 600 simulations seeds0..599, failures=0; all 600 complete result objects agree between official serial, official parallel, and scratch heap engines. Base code was not read until the final graft phase.", "Initial economic three-level queue ladder: mean_edge=-39.214187440337, seeds1000..1099, failures=0. Merely waiting behind incumbent liquidity is unprofitable.", "Oracle premise FIFO priority: attained mean_edge=-37.124564522777504 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise selective adverse-fill cancellation: attained mean_edge=6.486852965759999 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise jump avoidance: attained mean_edge=-47.3364205386825 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise retail-arrival timing: attained mean_edge=5.21235385337 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise retail-side foresight: attained mean_edge=5.21235385337 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise retail-size foresight: attained mean_edge=15.633901261435 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise one-step fair probability: attained mean_edge=25.14181709115 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise hidden-book safe gaps: attained mean_edge=30.823277560334997 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise last-300-step timing: attained mean_edge=7.635758818169999 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise covered-only inventory sales (no initial YES): attained mean_edge=0.0 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle premise collateral allocation: attained mean_edge=37.0648469003725 on seeds1000..1039. Oracle receives future probability/flow as applicable; diagnostic policy return, not a global optimum proof.", "Oracle pre-replenishment placement: competitor-only local price/size relaxation gives 12.901147990028319 on seeds1000..1099. Same relaxation: first at best tick 251.10439458116488, behind incumbent 27.333612118702423, optimally priced front 253.89979950720797, hidden empty levels 178.6972278995262, last300 steps 76.59185068385231; unrestricted gross retail upper bound 1596.016327807678. Local book-path ceilings are not global policy bounds.", "Oracle front-of-queue plus perfect adverse-fill cancellation: 77.22355425423301 on seeds1000..1099. Granting priority only after ages10/100/300 yields 39.055490195346 / 11.694785623112 / 7.507083726369. These are unattainable-information diagnostics, not submitted policies.", "Time gates without the low-price focus: first frozen same-price ask candidate scored 0.6622195612715 over seeds1000..1599, failures=0. Hierarchically pooled public quote-age gate scored 5.400719328374667 over the same full training range, failures=0.", "Low-price 700-share asks, ten-step stability delay: no off-target retention 4.386676029850833 on all 600 training seeds; retained within two ticks 7.067929623807166. No cheap YES purchases or probability probes.", "Exact-price-and-quantity repost control: mean_edge=4.5326914546215, retail_edge=6.463075513471333, arb_edge=-1.9303840588498333, 600 training simulations, failures=0. Replace every otherwise-retained ask by CancelOrder plus PlaceOrder at the same quantity/price before new placements, preserving own FIFO order and remapping collateral records. This isolates loss of external FIFO seniority.", "Keeping original queue place versus exact repost: paired mean gain=2.5352381691856665, standard error=0.29406328935079884, 112 wins/68 losses/420 ties. Retail gain=2.4724236449595; arbitrage improvement=0.06281452422616667. All measured on seeds1000..1599; no holdout inspection.", "Coupled replay first FIFO effect: 180/600 seeds; original order age median101, minimum4, maximum310; 93 first effects at ages100+ and 2 at300+. Cases first affected at ages100..199 contribute 1.2640171555753332 to overall paired mean gain. Conditional gain by competitor spread1/2/3/4: 0.4647530618673611 / 1.7575621525854543 / 4.012346811737415 / 3.988928639586805.", "Actual retained-policy fill-age contribution: ages50..99 edge=2.7082150533940372, ages100..299=3.272976079707054, ages300..699=0.24041485845801777, ages700+=0.0. These are edge contributions, not separate causal gains.", "FIFO adapter reservation ledger tested against actual simulator reservations across partial bid fills, covered/uncovered asks, quantity reductions, and preserved lots. Independent 100-seed synthetic economic-policy smoke test: mean_edge=6.760833700238001, failures=0.", "Starter sandbox check: 20/20 fail before strategy loading because Python3.12 pathlib imports ntpath, rejected by sandbox import allowlist.", "Current retained-ask checkpoint: official mean_edge=7.067929623807166, retail_edge=8.935499158430833, arb_edge=-1.8675695346236667, simulations=600, seed_start=1000, failures=0. Code frozen before official training and holdout runs; holdout score remains uninspected while further training proceeds.", "Upper-tail-only retained bids: 1.451805776364 over600 training seeds; exact-price/quantity repost control 0.02675071887833333, failures=0. Upper fill-age edge contributions: ages100..299=0.5571249481208663, ages300..699=0.709741351284783, ages700+=0.23035576227177135.", "Combined-tail exact-price/quantity repost control: mean_edge=4.559442173499833, retail_edge=6.874271187073834, arb_edge=-2.314829013574, failures=0 over600 training seeds. Preserving original FIFO raises mean edge by3.9602932266713333; paired standard error0.30839348237392494, 272 wins/68 losses/260 ties. Lower and upper branch edge sums equal combined-policy edge on all600 seeds.", "Combined FIFO training bootstrap (20000 resamples): percentile95 interval [3.3781796963136665,4.581055836616167]; not selection-adjusted. Removing the30 largest positive paired gains leaves mean2.685122642367544. This is a training robustness diagnostic, not holdout validation.", "Two separate600-simulation adapter stress runs completed with failures=0, including changing quantities, covered/uncovered asks, both tail transitions, probe IDs, idle callbacks, and explicit per-order cancellations. Focused ledger checks match actual simulator reservations and enforce reduced same-price risk targets.", "Frozen standalone file sandbox check:20/20 failures before strategy loading, all the same ntpath allowlist error as starter; ordinary600-run training and holdout results have zero failures.", "Upper-tail mirror and combined-tail policy, full600 training comparison: ask-only 7.067929623807166; both tails with size200 7.682364489598167; both tails with size700 8.519735400171166 (retail10.771746229656832, arb-2.2520108294856667), failures=0. Code frozen before official training/holdout; holdout remains uninspected during subsequent tuning.", "Standalone full-training sensitivity fresh_final_tail_0: params={\"ask_offset\": 0, \"keep_grace\": 1, \"maximum_bid\": 0, \"quote_wait\": 30, \"size\": 900}, mean_edge=6.6880707944265, retail_edge=8.994276605518333, arb_edge=-2.3062058110918335, simulations=600, seed_start=1000, failures=0.", "Standalone full-training sensitivity fresh_final_tail_age_0: params={\"max_keep_age\": 300, \"min_keep_age\": 0, \"quote_wait\": 50, \"require_low_bid\": true, \"size\": 500}, mean_edge=5.734136461719, retail_edge=8.148606116581666, arb_edge=-2.4144696548626667, simulations=600, seed_start=1000, failures=0.", "Standalone full-training sensitivity fresh_final_tail_1: params={\"ask_offset\": 0, \"keep_grace\": 3, \"maximum_bid\": 0, \"quote_wait\": 30, \"size\": 900}, mean_edge=6.6880707944265, retail_edge=8.994276605518333, arb_edge=-2.3062058110918335, simulations=600, seed_start=1000, failures=0.", "Standalone full-training sensitivity fresh_final_tail_age_1: params={\"max_keep_age\": 300, \"min_keep_age\": 0, \"quote_wait\": 50, \"require_low_bid\": false, \"size\": 500}, mean_edge=5.563344532143167, retail_edge=8.143075160974, arb_edge=-2.5797306288308333, simulations=600, seed_start=1000, failures=0.", "Standalone full-training sensitivity fresh_final_lot_0: params={\"age_cap\": 300, \"dynamic\": true, \"queue_fraction\": 1, \"size\": 200, \"splits\": 1}, mean_edge=4.697563466208667, retail_edge=5.435303703025999, arb_edge=-0.7377402368173334, simulations=600, seed_start=1000, failures=0.", "Standalone full-training sensitivity fresh_final_combo: params={\"keep_grace\": 1, \"quote_wait\": 30, \"size\": 900, \"tails\": \"both\"}, mean_edge=8.010741270499834, retail_edge=10.7721466591985, arb_edge=-2.761405388698667, simulations=600, seed_start=1000, failures=0.", "Graft search base: params={}, mean_edge=125.69520508572083, retail_edge=153.04067831998086, arb_edge=-27.345473234341668, simulations=120, seed_start=1000, failures=0.", "Graft search ask_join: params={\"ask\": true}, mean_edge=99.69022096957833, retail_edge=126.50412532079417, arb_edge=-26.813904351275834, simulations=120, seed_start=1000, failures=0.", "Graft search mark_only: params={}, mean_edge=125.69520508572083, retail_edge=153.04067831998086, arb_edge=-27.345473234341668, simulations=120, seed_start=1000, failures=0.", "Graft search both_join: params={\"ask\": true, \"bid\": true}, mean_edge=99.20395796313333, retail_edge=126.01977184120166, arb_edge=-26.815813878141668, simulations=120, seed_start=1000, failures=0.", "Graft search bid_join: params={\"bid\": true}, mean_edge=125.20894207927583, retail_edge=152.55632484038833, arb_edge=-27.3473827612075, simulations=120, seed_start=1000, failures=0.", "Graft search ask_early: params={\"ask\": true, \"wait\": 0}, mean_edge=99.26721239882333, retail_edge=125.95708095581084, arb_edge=-26.689868557055, simulations=120, seed_start=1000, failures=0.", "Graft search ask_age300: params={\"age\": 300, \"ask\": true}, mean_edge=98.82277482279251, retail_edge=125.64092807206916, arb_edge=-26.818153249341666, simulations=120, seed_start=1000, failures=0.", "Graft search ask_patient: params={\"ask\": true, \"wait\": 50}, mean_edge=102.37288479652167, retail_edge=128.76532042209084, arb_edge=-26.392435625615, simulations=120, seed_start=1000, failures=0.", "Graft search ask_no_retain: params={\"ask\": true, \"retain\": false}, mean_edge=74.40889529062834, retail_edge=100.91266427066083, arb_edge=-26.50376898009, simulations=120, seed_start=1000, failures=0.", "Graft search ask_no_mark: params={\"ask\": true, \"mark\": false}, mean_edge=78.82878165533499, retail_edge=105.94539386299833, arb_edge=-27.116612207734168, simulations=120, seed_start=1000, failures=0.", "Graft search stock_keep: params={\"stock\": true}, mean_edge=125.44060308546, retail_edge=153.01619078564667, arb_edge=-27.575587700266667, simulations=120, seed_start=1000, failures=0.", "Graft search stock_nomark: params={\"mark\": false, \"stock\": true}, mean_edge=125.44060308546, retail_edge=153.01619078564667, arb_edge=-27.575587700266667, simulations=120, seed_start=1000, failures=0.", "Graft search stock_join: params={\"ask\": true, \"stock\": true, \"wait\": 50}, mean_edge=101.9367451246475, retail_edge=128.7428219010025, arb_edge=-26.806076776399166, simulations=120, seed_start=1000, failures=0.", "Graft search stock_strict: params={\"stock\": true, \"stock_factor\": 1.0}, mean_edge=125.57461120813583, retail_edge=152.93917312898333, arb_edge=-27.3645619209275, simulations=120, seed_start=1000, failures=0.", "Graft full-training confirmation base: params={}, mean_edge=107.2442092237515, retail_edge=135.80165652288784, arb_edge=-28.557447299150834, simulations=600, seed_start=1000, failures=0.", "Graft full-training confirmation stock_keep: params={\"stock\": true}, mean_edge=106.590943398137, retail_edge=135.70412153946182, arb_edge=-29.113178141340335, simulations=600, seed_start=1000, failures=0.", "Graft full-training confirmation mark_only: params={}, mean_edge=107.2752344684335, retail_edge=135.8212954705185, arb_edge=-28.54606100209883, simulations=600, seed_start=1000, failures=0.", "Graft full-training confirmation stock_strict: params={\"stock\": true, \"stock_factor\": 1.0}, mean_edge=106.9201995090315, retail_edge=135.54148807250985, arb_edge=-28.621288563493, simulations=600, seed_start=1000, failures=0.", "Final file sandbox check on20 simulations failed20/20 before strategy loading with the same ntpath import allowlist error as the official starter. Unsandboxed official final training and holdout runs each have600 successful simulations.", "Selected acquired-priority patch versus unchanged base on600 training seeds: paired gain=0.031025244681999943, standard error=0.02058668042311797, wins=4, losses=2, ties=594. Small and not sufficient to establish population improvement.", "Unchanged-base holdout control, evaluated after code choice was frozen: mean_edge=96.0405203261775, failures=0. Frozen selected patch paired holdout gain=0.02733549288983328, wins=3, losses=4, ties=593. Code choice was not changed after this measurement.", "Final frozen selection mark_only chosen by full600 training score, never by holdout. Code SHA256=5f1f28ef998033d5e349998f8f7640a937e8cac8c8bd85c01fe7b6ceeadb8f5a. Official training/holdout numbers below belong to this frozen code; no post-holdout tuning. Official mean_edge=107.2752344684335, holdout mean_edge=96.06785581906733."], "next": "The base already captures most of the independently measured FIFO benefit. Next estimate remaining competitor quantity and combine it with order seniority, expected retail arrival time, and the opportunity cost of reserved cash/YES. Stable-tail joining lost too much retail capture; preserving large stock bids also underperformed. The selected patch's training gain is small, so require a predeclared independent validation set before claiming a population improvement."}