{
  "approach": "Starts from the published wave-2 base: tiny tick probes, a sub-tick probability grid, marginal retail-versus-arbitrage quote sizing, queue retention, and large cheap crossing bids for YES cover. Tested the six public additions in the required order: late-game traps, latent belief, overflow/FIFO slicing, constants, two-cent asks, and cash planning; only the complete overflow graft cleared the paired one-SE rule. Further full 600-seed comparisons retained competitor-price overflow only on spreads 2-4, four FIFO slices on all spreads, and a 6000-share marginal quote cap with main bids limited to 3000. The original near-zero estimator and crossing-stock policy remain the core. Every retained addition improved the same 600 tuning seeds by more than its paired standard error; code was frozen before the single untouched holdout.",
  "blocked": null,
  "python_version": "3.14.4",
  "base_mean_edge": 102.331987422326,
  "score": {
    "mean_edge": 108.82311690588183,
    "retail_edge": 137.79040742643517,
    "arb_edge": -28.967290520565,
    "simulations": 600,
    "seed_start": 1000,
    "failures": 0
  },
  "holdout": {
    "mean_edge": 95.6841292191785,
    "simulations": 600,
    "seed_start": 30000,
    "failures": 0
  },
  "code": "\"\"\"Passive binary-market maker with cheap crossing stock and FIFO slices.\n\nTick probes and a probability grid estimate fair value. Marginal retail edge\nagainst arbitrage loss sets quote size; four FIFO slices preserve older queue\npositions when downsizing. Competitor-price overflow levels are enabled only\non spreads two through four. Crossing bids acquire YES cover for 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=0.7, xu=0.1, sticky=1.0, min_ahead=2.0, keep_hi=1.5, keep_lo=0.7, Hu=300.0, bins=8.0, filt=1.0, uni=0.01, jumpinfo=1.0, dmin=0.0, kLb=0.08, kLf=0.08, pinf=1.0, pre=0.0, H1=100.0,\n         ydf=0.6, Wf=2000.0, g_hi=0.15, g_lo=0.15, qf=400.0, pmaxf=0.05, pre_gap=1.0,\n         ydf1=0.6, g1=5.0, f1=0.6, a1=100.0, nb1=0.0, gs=1.0, p1t=1.0, m1=1.0, zd=1.0, pfl=0.0005)\nP.update(qmax=6000.0)\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        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        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 not o.order_id.startswith('d') and o.side is Side.BUY and o.remaining_quantity > PROBE + 1e-9]\n        asks = [o for o in state.own_orders if not o.order_id.startswith('d') and o.side is Side.SELL and o.remaining_quantity > PROBE + 1e-9]\n        sticky = P['sticky'] > 0\n        def top(orders, comp, step):\n            if sticky and sum(o.remaining_quantity for o in orders if o.price_ticks == comp and o.order_id in self.ahead) >= P['min_ahead']:\n                return comp\n            return comp + step\n        bid_t = top(bids, cb, 1)\n        ask_t = top(asks, ca, -1)\n        qb = min(3000.0, qbid(bid_t))\n        qa = qask(ask_t)\n\n        Y = state.yes_inventory\n        if ask_t == 1 and H > P['H1'] and P['pre'] > 0:\n            qa = qa if Y >= P['a1'] > 0 else 0.0          # let the competitor's 2-tick ask erode instead of fronting it for nothing\n        # ammunition: hold YES so that low asks are covered\n        ptick = phat * 100\n        amt = 0\n        qam = 0.0\n        if P['ammo'] > 0 and ask_t >= 2 and phat < max(P['ammo_pmax'], P['pmaxf']):\n            wealth = state.cash + Y * phat\n            x = max(ask_t, ptick + 1) / 100.0\n            capw = P['fy'] * wealth / max(phat, 0.005)\n            target = min(P['ydem'] * min(H, P['W']) / x, capw)\n            full = min(P['ydf'] * min(H, P['Wf']) / x, capw) if phat < P['pmaxf'] else 0.0\n            t = max(1, min(99, int(math.ceil(ptick + 1e-9))))\n            g = t - ptick\n            if Y < full and g <= P['g_hi'] and bid_t <= t < ask_t:\n                amt, qam = t, min(P['qf'], full - Y)     # a tick p has just crossed: nearly free\n            elif Y < target and phat < P['ammo_pmax'] and bid_t <= t < ask_t and t / 100.0 - phat < P['ammo_maxpay']:\n                amt, qam = t, min(P['ammo_q'], target - Y)\n            elif Y < full and t >= 2 and 1.0 - g <= P['g_lo']:\n                amt, qam = t - 1, min(P['qf'], full - Y)  # rest just under p: filled only on the crossing, or by retail\n\n        if P['pre'] > 0 and ca == 2 and phat < 0.01 and H > P['H1'] and Y < P['pre'] and not qam and 1.0 - ptick < P['pre_gap']:\n            amt, qam = 1, min(P['ammo_q'], P['pre'] - Y)\n        q1 = 0.0\n        if P['ydf1'] > 0 and P['m1'] < ptick < P['g1'] + 1.0 and amt != 1:\n            q1 = max(0.0, P['ydf1'] * min(H, P['Wf']) / (self.s / 100.0) - Y)\n        # order management\n        actions = []\n        free = state.free_cash - 2.0\n        keep_ask = 0.0\n        new_b = []\n        new_a = []\n        def cancel(o):\n            nonlocal free\n            actions.append(CancelOrder(o.order_id))\n            x = o.price_ticks / 100.0\n            if o.side is Side.BUY:\n                free += x * o.remaining_quantity\n            else:\n                free += (1 - x) * min(self.res.get(o.order_id, 0.0), o.remaining_quantity)\n            self.ahead.discard(o.order_id)\n            self.res.pop(o.order_id, None)\n        for o in state.own_orders:\n            if o.remaining_quantity <= PROBE + 1e-9 or o.order_id.startswith('d'):\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        # A small second level can collect retail overflow past finite competitor liquidity.\n        if self.s in (2, 3, 4) and cb >= 1 and cb < bid_t:\n            q = fl(max(0.0, min(qbid(cb) - 24 / max(phat, 0.05) - max(qb, kb), free * 0.15 / (cb / 100.0))))\n            if q >= 0.02:\n                out.append(PlaceOrder(side=Side.BUY, price_ticks=cb, quantity=q, client_order_id=self._oid('db')))\n                free -= q * cb / 100.0 + 1e-6\n        if self.s in (2, 3, 4) and ca <= 99 and ca > ask_t:\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            covnew = sum(o.quantity - self.res.get(o.client_order_id, 0.0)\n                         for o in out if o.side is Side.SELL and o.client_order_id)\n            cov = max(0.0, Y - covk - covnew - 0.1)\n            x = ca / 100.0\n            q = fl(max(0.0, min(qask(ca) - 24 / x - max(qa, ka), cov + max(0.0, free - 10.0) * 0.15 / (1 - x))))\n            if q >= 0.02:\n                oid = self._oid('da')\n                r = max(0.0, q - cov)\n                self.res[oid] = r\n                out.append(PlaceOrder(side=Side.SELL, price_ticks=ca, quantity=q, client_order_id=oid))\n                free -= r * (1 - x) + 1e-6\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        # Cancel oversized quotes in small pieces while retaining the oldest FIFO slice.\n        pieces = []\n        for order in out:\n            oid = order.client_order_id\n            if oid is None or oid.startswith('d') or order.quantity < 0.08:\n                pieces.append(order)\n                continue\n            cents = int(round(order.quantity * 100))\n            covered_left = order.quantity - self.res.pop(oid, 0.0)\n            ahead = oid in self.ahead\n            self.ahead.discard(oid)\n            for i in range(4):\n                q = (cents // 4 + (i < cents % 4)) / 100.0\n                child = oid + '_' + str(i)\n                pieces.append(PlaceOrder(side=order.side, price_ticks=order.price_ticks,\n                                         quantity=q, client_order_id=child))\n                if ahead:\n                    self.ahead.add(child)\n                if order.side is Side.SELL:\n                    covered = min(covered_left, q)\n                    covered_left -= covered\n                    self.res[child] = max(0.0, q - covered)\n        return actions + pieces\n",
  "code_sha256": "d5bd551e7ca90b5c76c83828dc1d784ed5768ee3d321d031c961d1d0a0905521",
  "tried": [
    "Unmodified simulator commit b244530ee2a6247b5f930830eeca9dd950da0e7e. --workers 4 refused with PermissionError during forkserver socket creation; all reported scores use serial unmodified CLI batches.",
    "Base reproduction on seeds 0-599: {\"mean_edge\": 102.331987422326, \"retail_edge\": 127.3199510028995, \"arb_edge\": -24.987963580578832, \"simulations\": 600, \"seed_start\": 0, \"failures\": 0}; supplied reference 102.33197908899267 differs by 8.333333326504544e-06. No scoring code was patched.",
    "Tuning base seeds 1000-1599: {\"mean_edge\": 107.2442092237515, \"retail_edge\": 135.801656522888, \"arb_edge\": -28.557447299150834, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}. Each retention test uses paired total-edge differences across the same seeds, with sample standard deviation divided by sqrt(n); the gain must exceed one paired SE. This is a selection rule, not a multiple-testing-corrected significance claim.",
    "Mechanism grafts preserve the wave-2 base: late-game adds higher-tick traps because tick one is already implemented; belief replaces estimation and tracks explicit IDs for fill likelihoods; overflow adds competitor-price second levels and four FIFO slices; constants ports the six published changed values; two-cent asks replace the 1c front quote above the terminal horizon; cash ports cover horizon, inventory-dependent bids, larger asks, scarcity charge and tapering reserve without re-enabling the superseded pre-buy.",
    "sequence.jsonl: {\"step\": 1, \"mechanism\": \"late\", \"parent\": \"base1000\", \"candidate\": \"seq1\", \"score\": {\"mean_edge\": 106.68792330284516, \"retail_edge\": 136.06076743299448, \"arb_edge\": -29.372844130167334, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.5562859209063336, \"paired_se\": 0.4650320988779329, \"retained\": false}",
    "sequence.jsonl: {\"step\": 2, \"mechanism\": \"belief\", \"parent\": \"base1000\", \"candidate\": \"seq2\", \"score\": {\"mean_edge\": 105.47736546872316, \"retail_edge\": 138.131417599906, \"arb_edge\": -32.65405213119983, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -1.7668437550283338, \"paired_se\": 0.846871518282263, \"retained\": false}",
    "sequence.jsonl: {\"step\": 3, \"mechanism\": \"overflow\", \"parent\": \"base1000\", \"candidate\": \"seq3\", \"score\": {\"mean_edge\": 107.7794164879445, \"retail_edge\": 137.01055490399082, \"arb_edge\": -29.231138416059004, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.535207264192999, \"paired_se\": 0.49744149802840276, \"retained\": true}",
    "sequence.jsonl: {\"step\": 4, \"mechanism\": \"constants\", \"parent\": \"seq3\", \"candidate\": \"seq4\", \"score\": {\"mean_edge\": 103.1494158219395, \"retail_edge\": 140.42179377417835, \"arb_edge\": -37.27237795228517, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -4.6300006660049995, \"paired_se\": 1.000642843657921, \"retained\": false}",
    "sequence.jsonl: {\"step\": 5, \"mechanism\": \"ask\", \"parent\": \"seq3\", \"candidate\": \"seq5\", \"score\": {\"mean_edge\": 103.36000032637934, \"retail_edge\": 133.22610319804866, \"arb_edge\": -29.866102871677334, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -4.419416161565167, \"paired_se\": 1.4029729629290186, \"retained\": false}",
    "sequence.jsonl: {\"step\": 6, \"mechanism\": \"cash\", \"parent\": \"seq3\", \"candidate\": \"seq6\", \"score\": {\"mean_edge\": 105.51974931455851, \"retail_edge\": 138.1482204331165, \"arb_edge\": -32.62847111857584, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -2.2596671733860005, \"paired_se\": 0.678207261676042, \"retained\": false}",
    "screens.jsonl: {\"name\": \"late_c0.1\", \"n\": 200, \"mean\": 111.5026302570985, \"gain\": 0.07072311616850108, \"se\": 0.20838763778053082, \"failures\": 0}",
    "screens.jsonl: {\"name\": \"late_c0.25\", \"n\": 200, \"mean\": 111.762725452133, \"gain\": 0.3308183112029999, \"se\": 0.2739115971126371, \"failures\": 0}",
    "screens.jsonl: {\"name\": \"belief_novar\", \"n\": 200, \"mean\": 111.0416782236285, \"gain\": -0.3902289173014999, \"se\": 1.1713757016233097, \"failures\": 0}",
    "screens.jsonl: {\"name\": \"belief_quartervar\", \"n\": 200, \"mean\": 111.76318734958801, \"gain\": 0.33128020865799923, \"se\": 1.0248275493858114, \"failures\": 0}",
    "screens.jsonl: {\"name\": \"overflow_slicesonly\", \"n\": 200, \"mean\": 112.3597921556885, \"gain\": 0.9278850147585002, \"se\": 0.5549024608660228, \"failures\": 0}",
    "screens.jsonl: {\"name\": \"ask_stock100\", \"n\": 200, \"mean\": 111.43190714093, \"gain\": 0.0, \"se\": 0.0, \"failures\": 0}",
    "screens.jsonl: {\"name\": \"ask_stock500\", \"n\": 200, \"mean\": 111.43190714093, \"gain\": 0.0, \"se\": 0.0, \"failures\": 0}",
    "screens.jsonl: {\"name\": \"ask_stock1500\", \"n\": 200, \"mean\": 111.43190714093, \"gain\": 0.0, \"se\": 0.0, \"failures\": 0}",
    "refinements.jsonl: {\"idea\": \"late_spread1\", \"parent\": \"seq3\", \"score\": {\"mean_edge\": 111.8099958155415, \"retail_edge\": 137.45976530861, \"arb_edge\": -25.649769493119003, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.04718745324349969, \"paired_se\": 0.3624414753257823, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"late_quarter\", \"parent\": \"seq3\", \"score\": {\"mean_edge\": 111.5247690639055, \"retail_edge\": 137.4317919880585, \"arb_edge\": -25.907022924204497, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.23803929839249816, \"paired_se\": 0.5970477645339525, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_spreads234\", \"parent\": \"seq3\", \"score\": {\"mean_edge\": 112.88606876450599, \"retail_edge\": 137.26742233110602, \"arb_edge\": -24.381353566653, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 1.1232604022079997, \"paired_se\": 1.2514490844153559, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_spreads34\", \"parent\": \"seq3\", \"score\": {\"mean_edge\": 112.514027217256, \"retail_edge\": 137.1209828338545, \"arb_edge\": -24.6069556166565, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.7512188549580011, \"paired_se\": 1.2685926552291973, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_no_slices\", \"parent\": \"seq3\", \"score\": {\"mean_edge\": 110.72073805826899, \"retail_edge\": 136.473387329108, \"arb_edge\": -25.7526492709115, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -1.0420703040289965, \"paired_se\": 0.552077837680256, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_slices_only\", \"parent\": \"seq3\", \"score\": {\"mean_edge\": 112.3597921556885, \"retail_edge\": 137.003843719022, \"arb_edge\": -24.6440515633895, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.5969837933905028, \"paired_se\": 1.2770707602457478, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"ask_stock100\", \"parent\": \"seq3\", \"score\": {\"mean_edge\": 111.762808362298, \"retail_edge\": 137.361120566599, \"arb_edge\": -25.598312204347, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.0, \"paired_se\": 0.0, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"ask_stock500\", \"parent\": \"forced_overflow234\", \"score\": {\"mean_edge\": 112.88606876450599, \"retail_edge\": 137.26742233110602, \"arb_edge\": -24.381353566653, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.0, \"paired_se\": 0.0, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"ask_stock1500\", \"parent\": \"forced_overflow234\", \"score\": {\"mean_edge\": 112.88606876450599, \"retail_edge\": 137.26742233110602, \"arb_edge\": -24.381353566653, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.0, \"paired_se\": 0.0, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"cash_reserve_only100\", \"parent\": \"forced_overflow234\", \"score\": {\"mean_edge\": 112.946011679512, \"retail_edge\": 137.209382446317, \"arb_edge\": -24.2633707668585, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.05994291500600105, \"paired_se\": 0.0795350908461025, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"cash_ask_cap_only\", \"parent\": \"forced_overflow234\", \"score\": {\"mean_edge\": 113.5735617960365, \"retail_edge\": 138.03394580885148, \"arb_edge\": -24.460384012865003, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.6874930315305007, \"paired_se\": 0.3757710999963016, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"cash_ask_cap_only\", \"parent\": \"forced_overflow234\", \"candidate\": \"ref11\", \"score\": {\"mean_edge\": 108.82311690588183, \"retail_edge\": 137.79040742643517, \"arb_edge\": -28.967290520565, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.3942667413454996, \"paired_se\": 0.2215270138198668, \"retained\": true, \"screen_only\": false}",
    "refinements.jsonl: {\"idea\": \"belief_middle_only\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.0224612026025, \"retail_edge\": 139.137120894828, \"arb_edge\": -26.114659692240497, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.551100593433997, \"paired_se\": 0.19038105446193596, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"belief_nonzero_only\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.466239817805, \"retail_edge\": 139.69006946123199, \"arb_edge\": -26.2238296434295, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.10732197823149933, \"paired_se\": 0.5139053377506642, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"constants_var0\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 111.9413839962825, \"retail_edge\": 140.373486216848, \"arb_edge\": -28.4321022205885, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -1.6321777997539983, \"paired_se\": 1.044569056086723, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"constants_varquarter\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.48233120238, \"retail_edge\": 139.816799140118, \"arb_edge\": -26.33446793781, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.091230593656498, \"paired_se\": 1.0339574308224913, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"constants_lamj\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.132212375389, \"retail_edge\": 138.127784423413, \"arb_edge\": -24.995572048066002, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.4413494206474974, \"paired_se\": 0.9966212649721353, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"constants_retail_tail\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 114.7018646733955, \"retail_edge\": 139.0166041478135, \"arb_edge\": -24.3147394744855, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 1.1283028773590014, \"paired_se\": 1.02382385244475, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"constants_retail_tail\", \"parent\": \"ref11\", \"candidate\": \"ref17\", \"score\": {\"mean_edge\": 108.04762636286866, \"retail_edge\": 138.61064069644348, \"arb_edge\": -30.563014333609832, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.7754905430131661, \"paired_se\": 0.7185453668664444, \"retained\": false, \"screen_only\": false}",
    "refinements.jsonl: {\"idea\": \"constants_kLb\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.4598638386505, \"retail_edge\": 137.994750006653, \"arb_edge\": -24.5348861680455, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.1136979573859988, \"paired_se\": 0.22915786952079012, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"constants_grid\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 112.944411951392, \"retail_edge\": 137.788162271333, \"arb_edge\": -24.843750320008, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.6291498446444991, \"paired_se\": 0.3464497898667813, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_queue12\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.3697229349965, \"retail_edge\": 138.241039989239, \"arb_edge\": -24.871317054288003, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.2038388610399983, \"paired_se\": 0.13427080482223033, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_queue36\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 112.980692970021, \"retail_edge\": 137.66823374291, \"arb_edge\": -24.687540772941002, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.5928688260154992, \"paired_se\": 0.2445561543548872, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_budget10\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.559684789994, \"retail_edge\": 138.0222623046855, \"arb_edge\": -24.462577514742502, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.013877006042500284, \"paired_se\": 0.011414927028584938, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"overflow_budget20\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.5735043150495, \"retail_edge\": 138.034782820068, \"arb_edge\": -24.4612785050685, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -5.7480987000246844e-05, \"paired_se\": 0.0019949364535119477, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"cash_reserve50\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.47174781608501, \"retail_edge\": 137.8220205919855, \"arb_edge\": -24.3502727759485, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -0.10181397995149925, \"paired_se\": 0.14758344159614079, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"cash_no_reserve\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.5735617960365, \"retail_edge\": 138.03394580885148, \"arb_edge\": -24.460384012865003, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.0, \"paired_se\": 0.0, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"cash_bid_strength\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 111.08253185453101, \"retail_edge\": 138.25131183499198, \"arb_edge\": -27.1687799805265, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": -2.491029941505498, \"paired_se\": 0.7048320813639523, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"late_spread1small\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.6730867306555, \"retail_edge\": 137.9861910718695, \"arb_edge\": -24.3131043412665, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.09952493461900032, \"paired_se\": 0.21325495422364935, \"retained\": false, \"screen_only\": true}",
    "refinements.jsonl: {\"idea\": \"late_low_price\", \"parent\": \"ref11\", \"score\": {\"mean_edge\": 113.80006674335249, \"retail_edge\": 138.056934083371, \"arb_edge\": -24.256867340073, \"simulations\": 200, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.22650494731600088, \"paired_se\": 0.2319433166348449, \"retained\": false, \"screen_only\": true}",
    "forced.jsonl: {\"idea\": \"Full 600-seed follow-up despite marginal 200-seed screen: overflow only on spreads 2,3,4; FIFO slices on all spreads\", \"parent\": \"seq3\", \"candidate\": \"forced_overflow234\", \"score\": {\"mean_edge\": 108.42885016453633, \"retail_edge\": 136.80336323950317, \"arb_edge\": -28.37451307498033, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.6494336765918337, \"paired_se\": 0.5041198190266442, \"retained\": true}",
    "forced.jsonl: {\"idea\": \"Separate 3000-share main/overflow bid cap with 6000-share ask cap; strict gain > SE not met\", \"parent\": \"ref11\", \"candidate\": \"forced_sidecaps\", \"score\": {\"mean_edge\": 108.82634217726682, \"retail_edge\": 137.79040742643517, \"arb_edge\": -28.964065249180003, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.0032252713849999994, \"paired_se\": 0.0032252713849999994, \"changed_runs\": 1, \"retained\": false}",
    "forced.jsonl: {\"idea\": \"Revisit late-game higher-tick traps on spread 1 after overflow restriction and larger ask capacity: c=0.5, W=500, pmax=0.04\", \"parent\": \"ref11\", \"candidate\": \"last_trap_candidate\", \"score\": {\"mean_edge\": 108.84528607322834, \"retail_edge\": 137.85930882414067, \"arb_edge\": -29.014022750927996, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}, \"paired_gain\": 0.022169167346499895, \"paired_se\": 0.3683255011332416, \"retained\": false}",
    "Sandbox: unmodified starter {\"mean_edge\": -4.3962377512, \"retail_edge\": 0.451435815155, \"arb_edge\": -4.847673566355001, \"simulations\": 20, \"seed_start\": 0, \"failures\": 0}; frozen candidate {\"mean_edge\": 96.17506206637499, \"retail_edge\": 118.32317176440002, \"arb_edge\": -22.148109698115, \"simulations\": 20, \"seed_start\": 0, \"failures\": 0}. nsjail is unavailable, so the runner uses its Python-level sandbox.",
    "Frozen-code final tuning run: {\"mean_edge\": 108.82311690588183, \"retail_edge\": 137.79040742643517, \"arb_edge\": -28.967290520565, \"simulations\": 600, \"seed_start\": 1000, \"failures\": 0}; untouched holdout {\"mean_edge\": 95.6841292191785, \"retail_edge\": 125.44805438408568, \"arb_edge\": -29.763925164893337, \"simulations\": 600, \"seed_start\": 30000, \"failures\": 0}. Holdout was scored once after freezing, and no code was changed afterward.",
    "Frozen tuning gain versus the wave-2 base on the same 600 seeds: 1.5789076821303323; paired SE 0.384205139156741. Final code static check passed: only math and the challenge API imports, public quote/inventory/cash/remaining-step fields, no file or seed access. All 13 source quotations were checked against fresh URL responses. Parameter difference from base: {\"qmax\": 6000.0}; structural changes are FIFO slices, spread-restricted overflow and a 3000-share main-bid cap. Frozen at 2026-11-05T23:56:37.222571+00:00.\n",
    "Best retained frozen code: sha256 d5bd551e7ca90b5c76c83828dc1d784ed5768ee3d321d031c961d1d0a0905521, tuning mean 108.82311690588183, holdout mean 95.6841292191785. Any differences between selection-time and frozen re-run scores are reported, not used for further selection."
  ],
  "next": "Use new tuning and holdout windows before further selection. Estimate each run\u2019s retail demand and competitor queue depth online, then price crossing-stock purchases against the probability that inventory sells; the surviving fixed policies still cannot adapt to the fivefold flow variation. Avoid treating the 30000-30599 evaluation as a new tuning set."
}