{
  "approach": "Take away: retains tick probes, the eight-bin-per-tick belief filter, competitor-jump information, one-tick-inside marginal quotes, queue retention, boundary decay, and one resting tick-one YES stock bid. Removes the secondary inventory-target and near-boundary crossing-purchase system, its short-window/wealth targets and quantity branches, dead pre-buy controls, redundant inventory-dependent bid-risk branching, unused settings/state, and the bespoke inverse-normal approximation (uses standard-library NormalDist instead). The smaller strategy replaces the upper probability bound on stock entry with competitor best bid at most one tick and raises general risk to 0.9; removes the separate 60% stock-cash cap. Code is 9972 bytes versus 13882 for the base. Selection used only seeds 1000-1599; code was frozen before reading either holdout. On seeds 30000-30599, base mean edge 96.0405203261775 becomes 97.70763523638367, a difference of 1.6671149102061662; both have zero failures.",
  "blocked": null,
  "python_version": "3.12.3",
  "base_mean_edge": 102.33197908899267,
  "score": {
    "mean_edge": 109.05194228328166,
    "retail_edge": 131.3166036311765,
    "arb_edge": -22.2646613479065,
    "simulations": 600,
    "seed_start": 1000,
    "failures": 0
  },
  "holdout": {
    "mean_edge": 97.70763523638367,
    "simulations": 600,
    "seed_start": 30000,
    "failures": 0
  },
  "code": "\"\"\"Probe-informed market maker with one cheap-stock purchase rule.\n\nQuotes at the competitor inside tick, retaining priority where possible.\nThe remaining YES stock rule rests a bid at one cent before probability\nfalls through that tick, so low asks can be covered cheaply.\n\"\"\"\nimport math\nfrom statistics import NormalDist\nfrom orderbook_pm_challenge.strategy import BaseStrategy\nfrom orderbook_pm_challenge.types import CancelOrder, PlaceOrder, Side\nSQ2 = math.sqrt(2.0)\nSQ2PI = math.sqrt(2.0 * math.pi)\n\ndef cdf(x):\n    return 0.5 * (1.0 + math.erf(x / SQ2))\n\ndef pdf(x):\n    return math.exp(-0.5 * x * x) / SQ2PI\n\n_normal = NormalDist()\n\ndef inv(p):\n    return _normal.inv_cdf(min(max(p, 1e-9), 1 - 1e-9))\n\ndef lpm(k):\n    return pdf(k) + k * cdf(k)\n\ndef fl(q):\n    return math.floor(q * 100 + 1e-09) / 100\nNODES = [(-2.2, 0.06), (-1.3, 0.17), (-0.6, 0.27), (0.6, 0.27), (1.3, 0.17), (2.2, 0.06)]\nPROBE = 0.01\n\nclass Strategy(BaseStrategy):\n\n    def __init__(self):\n        self.n = 0\n        self.ahead = set()\n        self.res = {}\n        self.bc = None\n        self.bw = None\n        self.st = 0.5\n        self.pcb = self.pca = None\n        self.pb = set()\n        self.pa = set()\n        self.tb = 0\n        self.s = None\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        # Surviving orders bracket the preceding fair probability.\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        sb = {o.price_ticks for o in state.own_orders if o.side is Side.BUY and o.remaining_quantity <= PROBE + 1e-09}\n        sa = {o.price_ticks for o in state.own_orders if o.side is Side.SELL and o.remaining_quantity <= PROBE + 1e-09}\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) <= 1.0):\n            hi = min(hi, max(min(eb), lo))\n        if 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        # Predict and truncate the belief inside the observed bracket.\n        wid = max(hi - lo, 1e-06)\n        nb = max(2, min(48, int(round(wid * 8.0))))\n        cs = [lo + (i + 0.5) * wid / nb for i in range(nb)]\n        if self.bc is None:\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 = 0.01 * 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 = 0.02 ** 2 + 0.0019 * 0.35 ** 2\n        sd = math.sqrt(H * var)\n        self.tb = self.tb + 1 if hi <= 1 else 0\n        if self.tb > 0:\n            phat = min(phat, max(0.0005, cdf(inv(0.01) - 1.0 * 0.02 * math.sqrt(self.tb) / sd)))\n        z = inv(phat)\n        Z = z * sd\n        sp = pdf(z) / sd * 0.02\n        self.st = sp * 100.0\n        s = math.sqrt(sp * sp + var_t / 10000.0 + 1e-08)\n        sd1 = math.sqrt(max(1.0, H - 1.0) * var)\n        jp = [(cdf((Z + n * 0.35) / sd1), w) for n, w in NODES]\n        lj = 0.0019\n\n        # Expected one-step stale-quote losses, including rare jumps.\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        if H == 1:\n\n            def AB(x):\n                return ((1 - phat) * x, phat * (1 - x))\n        rho = 0.25 * 0.5\n        mu = math.log(5.0) - 0.5 * 1.2 ** 2\n        kA = 0.15 if phat < 0.05 else 0.9\n\n        # Quote until marginal retail edge no longer covers adverse selection.\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(3000.0, math.exp(mu + 1.2 * inv(1 - max(tail, 1e-06))) / px)\n\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 < 0.0:\n                return 0.0\n            if phat < 0.05:\n                a *= 0.08 / 0.15\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 < 0.0:\n                return 0.0\n            return qsize(b, a, t / 100.0)\n        bids = [o for o in state.own_orders if o.side is Side.BUY and o.remaining_quantity > PROBE + 1e-09]\n        asks = [o for o in state.own_orders if o.side is Side.SELL and o.remaining_quantity > PROBE + 1e-09]\n\n        def top(orders, comp, step):\n            if sum((o.remaining_quantity for o in orders if o.price_ticks == comp and o.order_id in self.ahead)) >= 2.0:\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        Y = state.yes_inventory\n        ptick = phat * 100\n        # The only inventory purchase rule: rest at one cent before crossing.\n        q1 = 0.0\n        if 1.0 < ptick and cb <= 1:\n            q1 = max(0.0, 0.6 * min(H, 2000.0) / (self.s / 100.0) - Y)\n        actions = []\n        free = state.free_cash - 2.0\n\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-09:\n                cancel(o)\n        kept_ids = set()\n\n        # Preserve price-time priority while sizes remain close to target.\n        def manage(orders, t, q):\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 * 1.5, 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)\n        ka = manage(asks, ask_t, qa)\n        add_b = qb - kb if kb < qb * 0.7 and bid_t != cb else 0.0\n        add_a = qa - ka if ka < qa * 0.7 and ask_t != ca else 0.0\n        budget = 0.9 * max(free, 0.0)\n        cost = add_b * bid_t / 100.0\n        if cost > budget:\n            f = budget / cost\n            add_b *= f\n            cost = budget\n        out = []\n        q1 = min(q1, 1.0 * 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-06\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-06\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) 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 - 0.7) * max(state.cash, 0.0)) if x >= 0.1 else 0.0\n                if H < 300.0 and phat < 0.05:\n                    ub = max(0.0, free * (1 - H / 300.0))\n                unc = min(unc, ub / (1 - x))\n            q = fl(min(add_a, cov + unc))\n            if q >= 0.01:\n                oid = self._oid('a')\n                out.append(PlaceOrder(side=Side.SELL, price_ticks=ask_t, quantity=q, client_order_id=oid))\n                r = max(0.0, q - cov)\n                self.res[oid] = r\n                free -= r * (1 - x) + 1e-06\n                if ask_t < ca:\n                    self.ahead.add(oid)\n        # Small two-sided probes reveal the next probability bracket.\n        f = int(math.floor(ptick + 1e-09))\n        r = max(int(2), 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": "bd69d74807d70fc0acd7b35765b602bd05813b920c2ad706b10160baff45de22",
  "tried": [
    "Scorer check, seeds 0-599: base mean 102.33197908899267, retail 127.3199510028995, arb -24.987971913912165, failures 0; matches the supplied author measurement exactly.",
    "Base tuning, seeds 1000-1599: mean 107.2442092237515, retail 135.80165652288784, arb -28.557447299150834, failures 0.",
    "Remove jump-loss quadrature only: seeds 1000-1119, mean 113.33190952206999, retail 156.35445709795334, arb -43.02254757586167, failures 0.",
    "Remove main tick-one stock bid: seeds 1000-1119, mean 113.67822487891917, retail 144.72895470727084, arb -31.05072982842, failures 0.",
    "Remove queue retention: seeds 1000-1119, mean 114.44492534324499, retail 143.34389684052414, arb -28.898971497325, failures 0.",
    "simple_no_sticky overrides {'ammo': 0, 'sticky': 0}: seeds 1000-1119, mean 114.89163984147, retail 140.73060615022416, arb -25.838966308801666, failures 0.",
    "Remove belief persistence (uniform bracket belief): seeds 1000-1119, mean 115.59348476979083, retail 148.7258390514425, arb -33.132354281685, failures 0.",
    "simple_stock03 overrides {'ammo': 0, 'ydf1': 0.3}: seeds 1000-1119, mean 117.62522562228918, retail 140.74661461601585, arb -23.121388993793335, failures 0.",
    "Remove jump intensity from risk model: seeds 1000-1119, mean 118.81628451895668, retail 152.2042765347625, arb -33.38799201585, failures 0.",
    "simple_stock15 overrides {'ammo': 0, 'ydf1': 1.5}: seeds 1000-1119, mean 121.39117735881084, retail 151.69387276253082, arb -30.302695403785833, failures 0.",
    "Remove below-one-cent probability decay: seeds 1000-1119, mean 124.24051235290418, retail 151.68820598556502, arb -27.4476936327525, failures 0.",
    "Remove competitor-jump information: seeds 1000-1119, mean 124.26171282536833, retail 152.36271885214833, arb -28.1010060268025, failures 0.",
    "simple_nouncovered overrides {'ammo': 0, 'fu': 0, 'Hu': 0}: seeds 1000-1119, mean 124.34886978932667, retail 145.86344479341167, arb -21.51457500413, failures 0.",
    "simple_k12 overrides {'ammo': 0, 'kA': 1.2}: seeds 1000-1119, mean 124.8565405072725, retail 145.00364384304916, arb -20.147103335810833, failures 0.",
    "coarse4 overrides {'bins': 4}: seeds 1000-1119, mean 125.22917796402584, retail 152.73898446117, arb -27.509806497181668, failures 0.",
    "coarse2 overrides {'bins': 2}: seeds 1000-1119, mean 125.39739943081167, retail 153.13203956868082, arb -27.734640137955, failures 0.",
    "simple_no_decay overrides {'ammo': 0, 'zd': 0}: seeds 1000-1119, mean 125.59083413141084, retail 148.8935022923608, arb -23.302668161013333, failures 0.",
    "simple_stock09 overrides {'ammo': 0, 'ydf1': 0.9}: seeds 1000-1119, mean 125.66706366120167, retail 151.47378432488082, arb -25.806720663739167, failures 0.",
    "simple_no_jinfo overrides {'ammo': 0, 'jumpinfo': 0}: seeds 1000-1119, mean 125.816767246875, retail 149.85266179285333, arb -24.035894545989166, failures 0.",
    "simple_no_probeinfo overrides {'ammo': 0, 'pinf': 0}: seeds 1000-1119, mean 126.305044535625, retail 149.31753780509334, arb -23.012493269485834, failures 0.",
    "simple_k06 overrides {'ammo': 0, 'kA': 0.6}: seeds 1000-1119, mean 126.46988460754001, retail 151.29519965439334, arb -24.825315046838334, failures 0.",
    "simple_coarse4 overrides {'ammo': 0, 'bins': 4}: seeds 1000-1119, mean 126.98421395757583, retail 150.23229340135583, arb -23.24807944381917, failures 0.",
    "simple_kl04 overrides {'ammo': 0, 'kL': 0.1, 'kLb': 0.04, 'kLf': 0.04}: seeds 1000-1119, mean 127.00896323345583, retail 152.12676728932166, arb -25.11780405592667, failures 0.",
    "Remove all probes: seeds 1200-1399, mean -21.2508418357755, retail 107.51547086652751, arb -128.766312702273, failures 0.",
    "grid_noj09 overrides {'ammo': 0, 'pinf': 0, 'bins': 2, 'jumpinfo': 0, 'kA': 0.9}: seeds 1400-1599, mean 95.7380557096485, retail 125.1529546171235, arb -29.414898907443497, failures 0.",
    "grid_noj07 overrides {'ammo': 0, 'pinf': 0, 'bins': 2, 'jumpinfo': 0}: seeds 1400-1599, mean 95.804954831747, retail 127.56962602833049, arb -31.7646711965645, failures 0.",
    "lean_noj07 overrides {'ammo': 0, 'pinf': 0, 'jumpinfo': 0}: seeds 1400-1599, mean 96.1953585128625, retail 127.332854957007, arb -31.137496444103498, failures 0.",
    "lean_noj09 overrides {'ammo': 0, 'pinf': 0, 'jumpinfo': 0, 'kA': 0.9}: seeds 1400-1599, mean 96.3486426462135, retail 124.989250965338, arb -28.6406083190845, failures 0.",
    "Use three moment-matched jump points: seeds 1400-1599, mean 96.78715352198749, retail 129.0879359951725, arb -32.300782473142, failures 0.",
    "Use three jump points and prior-matched jump variance: seeds 1400-1599, mean 96.9585632489675, retail 130.447581417816, arb -33.489018168794, failures 0.",
    "grid_lean07 overrides {'ammo': 0, 'pinf': 0, 'bins': 2}: seeds 1400-1599, mean 96.9714555778335, retail 127.706286064447, arb -30.73483048659, failures 0.",
    "grid_lean09 overrides {'ammo': 0, 'pinf': 0, 'bins': 2, 'kA': 0.9}: seeds 1400-1599, mean 97.231735306787, retail 125.5716633891665, arb -28.339928082331998, failures 0.",
    "lean09 overrides {'ammo': 0, 'pinf': 0, 'kA': 0.9}: seeds 1400-1599, mean 97.7668628482105, retail 124.9351446075465, arb -27.168281759290497, failures 0.",
    "lean07 overrides {'ammo': 0, 'pinf': 0}: seeds 1400-1599, mean 98.243538166523, retail 127.605075856088, arb -29.361537689526997, failures 0.",
    "Remove ask-side queue retention: seeds 1200-1399, mean 102.1519754869345, retail 134.3500593710835, arb -32.19808388419, failures 0.",
    "u_k15 overrides {'ammo': 0, 'filt': 0, 'kA': 1.5}: seeds 1200-1399, mean 103.5240432463785, retail 129.697097981564, arb -26.1730547352505, failures 0.",
    "sc_stock03 overrides {'ammo': 0, 'ydf1': 0.3}: seeds 1200-1399, mean 103.751884744203, retail 128.81817011136351, arb -25.066285367217002, failures 0.",
    "u_k10 overrides {'ammo': 0, 'filt': 0, 'kA': 1.0}: seeds 1200-1399, mean 104.215957862829, retail 132.904579177135, arb -28.688621314379997, failures 0.",
    "u_simple overrides {'ammo': 0, 'filt': 0}: seeds 1200-1399, mean 105.0041102950015, retail 136.22405633862851, arb -31.219946043714, failures 0.",
    "u_joint overrides {'ammo': 0, 'filt': 0, 'kA': 1.0, 'kLb': 0.12, 'kLf': 0.12, 'kL': 0.2}: seeds 1200-1399, mean 105.87492074798, retail 131.50237090646348, arb -25.6274501585405, failures 0.",
    "u_kl12 overrides {'ammo': 0, 'filt': 0, 'kLb': 0.12, 'kLf': 0.12, 'kL': 0.2}: seeds 1200-1399, mean 106.6740201260275, retail 134.8762706733, arb -28.202250547354, failures 0.",
    "u_kl20 overrides {'ammo': 0, 'filt': 0, 'kLb': 0.2, 'kLf': 0.2, 'kL': 0.3}: seeds 1200-1399, mean 107.8241820739115, retail 132.829227595877, arb -25.0050455220585, failures 0.",
    "Remove bid-side queue retention: seeds 1200-1399, mean 108.55751145706199, retail 136.00108387909148, arb -27.4435724220665, failures 0.",
    "Remove carried belief variance: seeds 1200-1399, mean 109.4289626802015, retail 139.693701413041, arb -30.264738732891, failures 0.",
    "sc_nojinfo overrides {'ammo': 0, 'jumpinfo': 0}: seeds 1200-1399, mean 109.518487680027, retail 138.857185751859, arb -29.3386980718705, failures 0.",
    "sc_nouncovered overrides {'ammo': 0, 'fu': 0, 'Hu': 0}: seeds 1200-1399, mean 109.52737429480851, retail 135.76302960380102, arb -26.235655309029998, failures 0.",
    "sc_stock12 overrides {'ammo': 0, 'ydf1': 1.2}: seeds 1200-1399, mean 109.961890190401, retail 140.91210331194, arb -30.950213121584998, failures 0.",
    "sc_nodecay overrides {'ammo': 0, 'zd': 0}: seeds 1200-1399, mean 111.2262231815, retail 137.91148253013648, arb -26.6852593486865, failures 0.",
    "sc_stock09 overrides {'ammo': 0, 'ydf1': 0.9}: seeds 1200-1399, mean 111.484605992015, retail 140.6794461743385, arb -29.194840182369, failures 0.",
    "Fix probe radius to one tick: seeds 1200-1399, mean 111.53067751593, retail 138.9661006384745, arb -27.435423122548, failures 0.",
    "Remove late low-probability uncovered-ask allowance: seeds 1200-1399, mean 111.733868418079, retail 138.613732893503, arb -26.8798644754755, failures 0.",
    "sc_kl12 overrides {'ammo': 0, 'kLb': 0.12, 'kLf': 0.12}: seeds 1200-1399, mean 112.18896524857449, retail 138.1147959855355, arb -25.925830737013, failures 0.",
    "sc_k11 overrides {'ammo': 0, 'kA': 1.1}: seeds 1200-1399, mean 112.405563114726, retail 135.900408473674, arb -23.494845358994, failures 0.",
    "Reduce minimum probe radius to one, retain adaptive radius: seeds 1200-1399, mean 112.57476429680601, retail 139.7503372204055, arb -27.175572923648, failures 0.",
    "Remove quote-distance guards from scalar/no-secondary version: seeds 1200-1399, mean 112.5957607543055, retail 139.3477163217445, arb -26.751955567487997, failures 0.",
    "sc_mix05 overrides {'ammo': 0}: seeds 1200-1399, mean 112.6060741006805, retail 138.7947379422815, arb -26.188663841614, failures 0.",
    "Use two jump quadrature points: seeds 1200-1399, mean 112.85628433535851, retail 138.6544469704425, arb -25.798162635146, failures 0.",
    "sc_kl04 overrides {'ammo': 0, 'kLb': 0.04, 'kLf': 0.04}: seeds 1200-1399, mean 112.87180253993151, retail 141.24526629783048, arb -28.373463757949498, failures 0.",
    "window125 overrides {'ammo': 0, 'g1': 0.25}: seeds 1000-1599, mean 99.64207549215617, retail 126.98625583778184, arb -27.344180345642666, failures 0.",
    "ask_target045 overrides {'ammo': 0, 'kA': 0.9, 'ydf1': 0.45}: seeds 1000-1599, mean 103.126503752256, retail 125.26735310912316, arb -22.140849356872334, failures 0.",
    "window15 overrides {'ammo': 0, 'g1': 0.5}: seeds 1000-1599, mean 104.18930953396999, retail 130.66488396449267, arb -26.475574430538, failures 0.",
    "target045 overrides {'ammo': 0, 'kA': 0.9, 'ydf1': 0.45}: seeds 1000-1599, mean 105.84370297617934, retail 127.66857584499233, arb -21.824872868824336, failures 0.",
    "Replace belief grid by truncated-normal scalar moments: seeds 1000-1599, mean 106.55356013131566, retail 135.36413413080933, arb -28.81057399950467, failures 0.",
    "ask_target overrides {'ammo': 0, 'kA': 0.9}: seeds 1000-1599, mean 106.63760011363233, retail 128.90455950907267, arb -22.26695939544783, failures 0.",
    "ask_fullcash overrides {'ammo': 0, 'kA': 0.9, 'f1': 1.0}: seeds 1000-1599, mean 106.94010877638883, retail 129.3863785599725, arb -22.446269783592335, failures 0.",
    "Remove disappeared-probe inference from scalar/no-secondary version: seeds 1000-1599, mean 107.08072862124651, retail 132.924170119212, arb -25.843441497983, failures 0.",
    "ask_target075 overrides {'ammo': 0, 'kA': 0.9, 'ydf1': 0.75}: seeds 1000-1599, mean 107.48642336769883, retail 130.427360014385, arb -22.94093664669583, failures 0.",
    "sc_mix0 overrides {'ammo': 0}: seeds 1000-1599, mean 107.5240319028635, retail 132.84521277300883, arb -25.321180870147668, failures 0.",
    "Remove secondary purchases plus scalar belief: seeds 1000-1599, mean 107.54943429440867, retail 133.11710340321298, arb -25.567669108819, failures 0.",
    "simple_kl12 overrides {'ammo': 0, 'kL': 0.2, 'kLb': 0.12, 'kLf': 0.12}: seeds 1000-1599, mean 107.56311404304451, retail 132.32487317696584, arb -24.76175913393917, failures 0.",
    "simple_coarse2 overrides {'ammo': 0, 'bins': 2}: seeds 1000-1599, mean 107.68336061313883, retail 134.2771257489805, arb -26.5937651358725, failures 0.",
    "sc_k09 overrides {'ammo': 0, 'kA': 0.9}: seeds 1000-1599, mean 107.73744816924366, retail 131.2353904838025, arb -23.497942314567332, failures 0.",
    "window4 overrides {'ammo': 0, 'g1': 3.0}: seeds 1000-1599, mean 108.17605784448067, retail 133.43015095026718, arb -25.254093105801335, failures 0.",
    "Remove secondary YES purchases: seeds 1000-1599, mean 108.23052839965034, retail 133.56467411974282, arb -25.334145720107166, failures 0.",
    "window3 overrides {'ammo': 0, 'g1': 2.0}: seeds 1000-1599, mean 108.24363291235633, retail 133.38623600998832, arb -25.142603097647, failures 0.",
    "simple_k09 overrides {'ammo': 0, 'kA': 0.9}: seeds 1000-1599, mean 108.33453281546234, retail 131.5922649874175, arb -23.257732171965166, failures 0.",
    "cash04 overrides {'ammo': 0, 'kA': 0.9, 'f1': 0.4}: seeds 1000-1599, mean 108.34972259981534, retail 130.67021131236683, arb -22.320488712561335, failures 0.",
    "window2 overrides {'ammo': 0, 'g1': 1.0}: seeds 1000-1599, mean 108.450255099836, retail 132.8780887738438, arb -24.427833674023002, failures 0.",
    "window10_k09 overrides {'ammo': 0, 'g1': 9.0, 'kA': 0.9}: seeds 1000-1599, mean 108.58454985189967, retail 131.8150415414117, arb -23.230491689519166, failures 0.",
    "unbounded09 overrides {'ammo': 0, 'kA': 0.9}: seeds 1000-1599, mean 108.626103216782, retail 131.82428380544235, arb -23.198180588668336, failures 0.",
    "accessible07 overrides {'ammo': 0, 'kA': 0.7}: seeds 1000-1599, mean 108.63024141118983, retail 133.00098487838383, arb -24.370743467208, failures 0.",
    "window2_k09 overrides {'ammo': 0, 'g1': 1.0, 'kA': 0.9}: seeds 1000-1599, mean 108.63390629024433, retail 131.02673154595215, arb -22.392825255717167, failures 0.",
    "window10 overrides {'ammo': 0, 'g1': 9.0}: seeds 1000-1599, mean 108.67199644248333, retail 133.87218062895383, arb -25.200184186485334, failures 0.",
    "unbounded07 overrides {'ammo': 0, 'kA': 0.7}: seeds 1000-1599, mean 108.68089578837983, retail 133.86873431051364, arb -25.187838522148834, failures 0.",
    "accessible09 overrides {'ammo': 0, 'kA': 0.9}: seeds 1000-1599, mean 108.73721999984117, retail 131.003905805589, arb -22.266685805757167, failures 0.",
    "cash08 overrides {'ammo': 0, 'kA': 0.9, 'f1': 0.8}: seeds 1000-1599, mean 108.87680120932266, retail 131.16585419270083, arb -22.289052983388334, failures 0.",
    "Cleanup verification: standard-library quantile and removed dead branches matched actions in 20 complete tuning simulations; the frozen final file then reproduced every per-seed result field of the pre-cleanup selected variant over all 600 tuning seeds exactly.",
    "Sandbox check, final strategy: 20 simulations, 20 failures under Python 3.12.3; sandbox loader raises ImportError for ntpath before loading strategy; starter fails identically, so accepted the brief's framework-failure exception.",
    "Sandbox check, examples/starter_strategy.py: 20 simulations, 20 failures under Python 3.12.3; sandbox loader raises ImportError for ntpath before loading strategy; starter fails identically, so accepted the brief's framework-failure exception.",
    "Frozen holdout comparison only, seeds 30000-30599: base 96.0405203261775 (retail 124.3725985363135, arb -28.332078210128167); selected 97.70763523638367 (retail 119.80796407959468, arb -22.100328843206); paired improvement 1.6671149102061666, paired standard error 1.1776597053936184. No holdout-guided revisions or candidate comparisons.",
    "Selected fullcash, frozen code sha256 bd69d74807d70fc0acd7b35765b602bd05813b920c2ad706b10160baff45de22: tuning mean 109.05194228328166, retail 131.3166036311765, arb -22.2646613479065; holdout mean 97.70763523638367; 600 simulations per range and zero ordinary simulation failures. This is the delivered code and its rerun scores."
  ],
  "next": "Test the secondary-purchase removal and competitor-bid stock-entry gate as a graft onto independent strategies. Preserve probes, queue retention, and belief/jump logic; remeasure on fresh seeds rather than extending the constant search on 1000-1599."
}