{"approach": "Calibration investigation returning the supplied base code byte-for-byte unchanged: tick probes and a sub-tick grid belief locate fair value, marginal retail-versus-arbitrage sizing controls quotes, persistent orders retain queue priority, and low-price YES inventory covers asks. No strategy parameters were tuned. Tested contiguous and distant seed starts, Python 3.11/3.12/3.14, alternative horizons and seed-generation settings; none identified the server runs. The runtime change does not alter per-run trading scores on the reproduced 200 seeds. Detailed negative results and an independent 600-run holdout are recorded below.", "blocked": null, "python_version": "3.14.4", "base_mean_edge": 78.85441957511699, "score": {"mean_edge": 87.41650726068066, "retail_edge": 116.13125849331949, "arb_edge": -28.714751232636335, "simulations": 600, "seed_start": 0, "failures": 0}, "holdout": {"mean_edge": 85.46780344973116, "simulations": 600, "seed_start": 20000, "failures": 0}, "code": "\"\"\"Stale-quote defence with tick probes, a sub-tick belief and YES ammunition.\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.  That rule pulls\nquotes by itself when a move would hurt most.  Near p=0 a retail buy pays almost\nits whole notional as edge, so YES is held to cover low asks.\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=0.5, 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=1500.0, H1=100.0)\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\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        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 sb and eb:\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        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 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 = 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 < P['ammo_pmax']:\n            wealth = state.cash + Y * phat\n            x = max(ask_t, ptick + 1) / 100.0\n            target = min(P['ydem'] * min(H, P['W']) / x, P['fy'] * wealth / max(phat, 0.005))\n            if Y < target:\n                t = max(1, min(99, int(math.ceil(ptick + 1e-9))))\n                if bid_t <= t < ask_t and t / 100.0 - phat < P['ammo_maxpay']:\n                    amt = t\n                    qam = min(P['ammo_q'], target - Y)\n\n        if P['pre'] > 0 and ca == 2 and phat < 0.01 and H > P['H1'] and Y < P['pre'] and not qam:\n            amt, qam = 1, min(P['ammo_q'], P['pre'] - 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        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": "432d867b1459fdcae2aba14e8634d3aa8d181f3f81d16f8a8deed5252aab75c4", "tried": ["Public simulator commit b244530ee2a6247b5f930830eeca9dd950da0e7e, unmodified defaults (2000 steps, sampled regimes); all final scores use Python 3.14.4. Base code SHA256 matches the supplied artifact exactly.", "Reproduced seeds 0–199: base mean_edge 78.85441957511699; starter -6.4826639323115 (retail 0.612635466855, arb -7.0952993991665005); 200 successes each.", "Python 3.11.18, 3.12.16 and 3.14.4: all 200 per-seed edge, fill, and wealth results agree for both strategies on seeds 0–199. Python 3.11 differs only in inventory averages and regime probability diagnostics. Thus the float sum change does not explain the server score on these seeds.", "Sandbox: unchanged base and repository starter each pass 20/20 simulations on Python 3.14.4 and Python 3.12.16. Base sandbox mean_edge 90.48990905832001 and starter -4.3962377512 on seeds 0–19, on both runtimes. The previously reported Python 3.12 sandbox failure was not reproduced.", "--workers 4 fails locally with PermissionError opening the multiprocessing forkserver AF_UNIX socket. All evaluations used serial simulator batches, with independent commands running concurrently.", "Public submission API confirms base mean_edge 90.987078, retail 118.866503, arb -27.879424, final wealth 1060.16299; starter -6.504278, retail 0.945833, arb -7.450112, final wealth 994.152248. Both have 200 successes and zero failures. Public responses provide histograms but no individual seeds; no seed generator was found in the public simulator or inspected UI assets.", "Current public UI starter template is AST-equivalent to examples/starter_strategy.py after removing docstrings and the future-annotations import; no different trading logic was found there.", "Checked every 200-seed window with start 0–11800 (all seeds 0–11999): Exhaustive default-starter contiguous-window search: {\"seeds_scanned\":12000,\"max_seed\":11999,\"windows\":11801,\"closest\":[{\"start\":6647,\"mean_edge\":-6.5042948314695,\"distance\":1.683146949993386e-05,\"retail\":0.7226415677555,\"arb\":-7.226936399226},{\"start\":10189,\"mean_edge\":-6.504126633144,\"distance\":0.00015136685600047883,\"retail\":0.7485989475610001,\"arb\":-7.252725580702},{\"start\":5654,\"mean_edge\":-6.504492588127,\"distance\":0.00021458812700014818,\"retail\":0.7329381247019999,\"arb\":-7.237430712828},{\"start\":1611,\"mean_edge\":-6.503967622794001,\"distance\":0.0003103772059995791,\"retail\":0.7817038012615001,\"arb\":-7.285671424055},{\"start\":2618,\"mean_edge\":-6.503815290325,\"distance\":0.0004627096750002835,\"retail\":0.8395496559160001,\"arb\":-7.343364946242}],\"matches\":[],\"failures\":0}. Match criterion is equality after rounding to the server’s six decimal places; no match means these windows cannot reproduce both server scores under these defaults.", "Default starter, 200 sequential seeds: {\"start\": 12345, \"mean_edge\": -7.4191260354090005, \"retail\": 0.797179019318, \"arb\": -8.216305054729, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 42000, \"mean_edge\": -6.144783441032001, \"retail\": 0.659090067317, \"arb\": -6.8038735083485005, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 50000, \"mean_edge\": -6.741911025934001, \"retail\": 0.6910513120449999, \"arb\": -7.432962337978999, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 100000, \"mean_edge\": -6.326926019139, \"retail\": 0.696989634894, \"arb\": -7.0239156540305, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 1000000, \"mean_edge\": -5.929360147574999, \"retail\": 0.7487783993255, \"arb\": -6.6781385469005, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 123456, \"mean_edge\": -7.116638920629501, \"retail\": 0.7283180357400001, \"arb\": -7.844956956368, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 20260409, \"mean_edge\": -6.6250697605005, \"retail\": 0.7481704704144999, \"arb\": -7.3732402309165, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 20250409, \"mean_edge\": -6.701199543545, \"retail\": 0.8112978339910001, \"arb\": -7.512497377538, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 69420, \"mean_edge\": -5.541450013094, \"retail\": 0.7597880190265001, \"arb\": -6.301238032116999, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 13371337, \"mean_edge\": -7.520938671151, \"retail\": 0.6583874983115, \"arb\": -8.1793261694635, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 314159, \"mean_edge\": -5.8381791843785, \"retail\": 0.727880211568, \"arb\": -6.566059395947, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 8675309, \"mean_edge\": -6.7120505070859995, \"retail\": 0.603116065212, \"arb\": -7.3151665722985, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 10000, \"mean_edge\": -6.0257938930804995, \"retail\": 0.6899615751945, \"arb\": -6.715755468276, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 1000, \"mean_edge\": -5.8471411604984995, \"retail\": 0.6785175698160001, \"arb\": -6.525658730316, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 2026, \"mean_edge\": -7.496910514721, \"retail\": 0.603113261752, \"arb\": -8.100023776475, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 2025, \"mean_edge\": -7.5314066919785, \"retail\": 0.6041194811955, \"arb\": -8.135526173176, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 9999, \"mean_edge\": -5.959311108652501, \"retail\": 0.6874323182655, \"arb\": -6.646743426919, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 65536, \"mean_edge\": -6.321183727063, \"retail\": 0.6793173095935, \"arb\": -7.000501036655001, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 2147483647, \"mean_edge\": -7.904098180001999, \"retail\": 0.6464184679455001, \"arb\": -8.5505166479475, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 31415, \"mean_edge\": -5.686421443743, \"retail\": 0.8550076403245, \"arb\": -6.541429084070001, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 1234567, \"mean_edge\": -6.745702717344, \"retail\": 0.651665523944, \"arb\": -7.397368241286, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 12345678, \"mean_edge\": -5.6436953410815, \"retail\": 0.8135474700755, \"arb\": -6.457242811157, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 123456789, \"mean_edge\": -6.394038851366, \"retail\": 0.758649394478, \"arb\": -7.1526882458425, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 424242, \"mean_edge\": -5.6263576121455, \"retail\": 0.8421701906660001, \"arb\": -6.4685278028105, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 54321, \"mean_edge\": -5.87057003567, \"retail\": 0.7739580746625001, \"arb\": -6.644528110331501, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 98765, \"mean_edge\": -5.8700982978875, \"retail\": 0.7972317329499999, \"arb\": -6.667330030839, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 987654321, \"mean_edge\": -6.27194019787, \"retail\": 0.7079645666704999, \"arb\": -6.979904764540501, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 2024, \"mean_edge\": -7.4547875761805, \"retail\": 0.6042704556075, \"arb\": -8.05905803179, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 202604, \"mean_edge\": -5.716665893778001, \"retail\": 0.734077451714, \"arb\": -6.450743345492, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 202504, \"mean_edge\": -5.962377030384, \"retail\": 0.7803701740925, \"arb\": -6.7427472044779995, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 20240409, \"mean_edge\": -5.7938478108835, \"retail\": 0.8529244475655, \"arb\": -6.6467722584495, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 10000000, \"mean_edge\": -5.237062292484, \"retail\": 0.8213528658065, \"arb\": -6.058415158292999, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 100000000, \"mean_edge\": -6.323448655837, \"retail\": 0.8274099025114999, \"arb\": -7.150858558347499, \"failures\": 0}", "Default starter, 200 sequential seeds: {\"start\": 1000000000, \"mean_edge\": -6.158695412344, \"retail\": 0.787521438923, \"arb\": -6.946216851267, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 500, \"mean_edge\": -9.5347738738115, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 1000, \"mean_edge\": -7.8136962918799995, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 1500, \"mean_edge\": -7.3492287974875, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 1999, \"mean_edge\": -6.4576033429969995, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 2001, \"mean_edge\": -6.5285536594285, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 2500, \"mean_edge\": -6.875015836037001, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 3000, \"mean_edge\": -6.226922073768, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"steps\": 4000, \"mean_edge\": -6.7049382381689995, \"failures\": 0}", "Starter on seeds 0–199, alternate setting: {\"setting\": \"fixed default parameters, no randomization\", \"mean_edge\": 0.051513981897000016, \"failures\": 0}", "Starter, 200 reproducible random seeds: {\"generator\": \"random.Random(root).randrange(2**31)\", \"root\": 0, \"mean_edge\": -6.8894235637115, \"retail\": 0.765460578819, \"arb\": -7.6548841425285, \"failures\": 0}", "Starter, 200 reproducible random seeds: {\"generator\": \"random.Random(root).randrange(2**31)\", \"root\": 1, \"mean_edge\": -5.8498345331345005, \"retail\": 0.7208044214855001, \"arb\": -6.570638954622, \"failures\": 0}", "Starter, 200 reproducible random seeds: {\"generator\": \"random.Random(root).randrange(2**31)\", \"root\": 42, \"mean_edge\": -7.053270364255, \"retail\": 0.7070683853055, \"arb\": -7.7603387495605, \"failures\": 0}", "Starter, 200 reproducible random seeds: {\"generator\": \"random.Random(root).randrange(2**31)\", \"root\": 12345, \"mean_edge\": -6.9026424564615, \"retail\": 0.7488342325795, \"arb\": -7.651476689038, \"failures\": 0}", "Starter, 200 reproducible random seeds: {\"generator\": \"random.Random(root).randrange(2**31)\", \"root\": 2026, \"mean_edge\": -6.7942330777115, \"retail\": 0.7872889395955001, \"arb\": -7.5815220173075, \"failures\": 0}", "Starter, 200 reproducible random seeds: {\"generator\": \"random.Random(root).randrange(2**31)\", \"root\": 1337, \"mean_edge\": -6.196405239624999, \"retail\": 0.8912699780845, \"arb\": -7.087675217711499, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 1, \"engine_seed_offset\": 0, \"stride\": 1, \"mean_edge\": -6.7084471716985, \"retail\": 0.646447489643, \"arb\": -7.3548946613395, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 42, \"engine_seed_offset\": 0, \"stride\": 1, \"mean_edge\": -6.1063368138684995, \"retail\": 0.754495331564, \"arb\": -6.8608321454365, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 10000, \"engine_seed_offset\": 0, \"stride\": 1, \"mean_edge\": -5.658141150031001, \"retail\": 0.6734438693695001, \"arb\": -6.3315850194015, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 0, \"engine_seed_offset\": 1, \"stride\": 1, \"mean_edge\": -6.77481675471, \"retail\": 0.5992779750775, \"arb\": -7.374094729789, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 0, \"engine_seed_offset\": 42, \"stride\": 1, \"mean_edge\": -6.206285615947, \"retail\": 0.640543230112, \"arb\": -6.84682884606, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 0, \"engine_seed_offset\": 0, \"stride\": 10, \"mean_edge\": -5.768385357443, \"retail\": 0.8763875161325, \"arb\": -6.6447728735750005, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 0, \"engine_seed_offset\": 0, \"stride\": 100, \"mean_edge\": -7.176375722105501, \"retail\": 0.7292283408725, \"arb\": -7.905604062976501, \"failures\": 0}", "Starter, 200 seeds with altered configuration/engine seed relationship: {\"config_seed_offset\": 0, \"engine_seed_offset\": 0, \"stride\": 1000, \"mean_edge\": -6.142107598009, \"retail\": 0.873273565976, \"arb\": -7.015381163984, \"failures\": 0}", "Cross-check of the closest starter window, seeds 6647–6846: unchanged base mean_edge 69.90216407512, retail 104.73894613566699, arb -34.836782060526495, failures 0. This is not the server base score. Starter retail 0.7226415677555 and arb -7.226936399226 also reject that near-match.", "Calibration conclusion: did not identify Paradigm’s 200-run seed set. Tested alternatives above do not reproduce the starter to six decimals; runtime alone, tested horizons, fixed default regimes and tested seed schemes are ruled out only for the configurations evaluated. Arbitrary hidden seeds, different randomization bands and untested server implementations remain unresolved. No strategy constants or behavior were tuned, including outside seeds 0–599.", "Holdout sample standard deviation 145.68021087578228 implies estimated standard error 5.947369704445318 for 600 runs, or 10.301146499495188 for 200 independent runs under a comparable distribution. This is sampling uncertainty, not evidence of a server bug.", "Returned candidate is unchanged base: mean_edge 87.41650726068066, retail 116.13125849331949, arb -28.714751232636335 on seeds 0–599; independent holdout mean_edge 85.46780344973116 on seeds 20000–20599. Each has 600 successes and zero failures; code frozen before holdout."], "next": "Obtain the scorer’s seed-generation algorithm and exact regime-sampling configuration from the maintainers before further blind seed search. Require simultaneous agreement on starter total/retail/arb and unchanged-base total/retail/arb, using the public histograms as additional fingerprints. A near starter mean is insufficient. Preserve separate holdouts for actual strategy improvements."}