{
  "approach": "Measurement-only ablation map; returned code is byte-for-byte the supplied base, with no strategy changes. The base uses tiny probes and a sub-tick probability filter, marginally sized quotes one tick inside the competitor, queue-aware order retention, cheap YES purchases including a large resting tick-1 bid, spread-1 stock sales, and a terminal-step loss rule. Each of the seven requested parts is independently disabled and compared on seeds 1000-1599; three supplemental deletions separate overlapping stock and spread-1 mechanisms. The tried entries define every switch, report unrounded edge and paired uncertainty, identify inactive or costly components, and record the common sandbox failure. Only the unchanged base is scored on the untouched 30000-30599 holdout.",
  "blocked": null,
  "python_version": "3.13.5",
  "base_mean_edge": 102.33197908899267,
  "score": {
    "mean_edge": 107.2442092237515,
    "retail_edge": 135.80165652288784,
    "arb_edge": -28.557447299150834,
    "simulations": 600,
    "seed_start": 1000,
    "failures": 0
  },
  "holdout": {
    "mean_edge": 96.0405203261775,
    "simulations": 600,
    "seed_start": 30000,
    "failures": 0
  },
  "code": "\"\"\"Stale-quote defence with tick probes, a sub-tick belief and cheap YES stock.\n\nEvery step the arbitrageur removes any order on the wrong side of p, so tiny\ntwo-sided probes around the estimate locate p to a tick; a grid filter narrows\nthat further.  Quotes sit one tick inside the competitor and are sized by the\nmarginal rule: one more share is worth quoting while the chance a retail order\nreaches it, times its edge, exceeds the expected arbitrage loss.  Near p=0 a\nretail buy pays almost its whole notional as edge, so YES is held to cover low\nasks.  That YES is bought when it is cheap: a large bid rests at tick 1 while p\nis above it, so the arbitrageur fills it on the crossing for about 0.1 tick a\nshare instead of nearly a full tick once p is near zero, and smaller bids sit on\nwhichever tick p is within 0.15 of.  Below tick 1 the estimate of p decays with\nthe time spent there, since no probe can see it.\n\"\"\"\nimport math\nfrom orderbook_pm_challenge.strategy import BaseStrategy\nfrom orderbook_pm_challenge.types import CancelOrder, PlaceOrder, Side\n\nP = dict(lam_r=0.25, m=5.0, sig_n=1.2, lam_j=0.0019, sig_j=0.35, sig=0.02,\n         qmax=3000.0, rmin=2, kA=0.7, kL=0.15, pL=0.05,\n         ammo=1.0, ydem=0.4, W=200.0, fy=0.6, ammo_q=60.0, ammo_pmax=0.05, ammo_maxpay=0.02,\n         fb=0.9, fu=0.7, xu=0.1, sticky=1.0, min_ahead=2.0, keep_hi=1.5, keep_lo=0.7, Hu=300.0, bins=8.0, filt=1.0, uni=0.01, jumpinfo=1.0, dmin=0.0, kLb=0.08, kLf=0.08, pinf=1.0, pre=0.0, H1=100.0,\n         ydf=0.6, Wf=2000.0, g_hi=0.15, g_lo=0.15, qf=400.0, pmaxf=0.05, pre_gap=1.0,\n         ydf1=0.6, g1=5.0, f1=0.6, a1=100.0, nb1=0.0, gs=1.0, p1t=1.0, m1=1.0, zd=1.0, pfl=0.0005)\nSQ2 = math.sqrt(2.0)\nSQ2PI = math.sqrt(2.0 * math.pi)\ndef cdf(x): return 0.5 * (1.0 + math.erf(x / SQ2))\ndef pdf(x): return math.exp(-0.5 * x * x) / SQ2PI\ndef inv(p):\n    p = min(max(p, 1e-9), 1 - 1e-9)\n    t = math.sqrt(-2.0 * math.log(min(p, 1 - p)))\n    x = t - (2.515517 + 0.802853 * t + 0.010328 * t * t) / (1 + 1.432788 * t + 0.189269 * t * t + 0.001308 * t ** 3)\n    x = -x if p < 0.5 else x\n    for _ in range(2):\n        d = pdf(x)\n        if d < 1e-12:\n            break\n        x -= (cdf(x) - p) / d\n    return x\ndef lpm(k):\n    return pdf(k) + k * cdf(k)\ndef fl(q):\n    return math.floor(q * 100 + 1e-9) / 100\n\nNODES = [(-2.2, .06), (-1.3, .17), (-0.6, .27), (0.6, .27), (1.3, .17), (2.2, .06)]\nPROBE = 0.01\n\n\nclass Strategy(BaseStrategy):\n    def __init__(self):\n        self.n = 0\n        self.ahead = set()     # main orders placed strictly ahead of any competitor order at their tick\n        self.res = {}          # order id -> uncovered quantity at placement\n        self.bc = None         # belief: sub-tick grid centres (ticks)\n        self.bw = None         # belief: weights\n        self.st = 0.5          # last one-step sd in ticks\n        self.pcb = self.pca = None\n        self.pb = set()\n        self.pa = set()\n        self.tb = 0\n        self.s = None          # competitor spread parameter\n\n    def _oid(self, tag):\n        self.n += 1\n        return tag + str(self.n)\n\n    def on_step(self, state):\n        H = max(1, state.steps_remaining)\n        cb = state.competitor_best_bid_ticks or 0\n        ca = state.competitor_best_ask_ticks or 100\n        if self.s is None:\n            self.s = max(1, (ca - cb + 1) // 2)\n        lo, hi = cb, ca\n        for o in state.own_orders:\n            if o.side is Side.BUY:\n                lo = max(lo, o.price_ticks)\n            else:\n                hi = min(hi, o.price_ticks)\n        if P['pinf'] > 0:\n            sb = {o.price_ticks for o in state.own_orders if o.side is Side.BUY and o.remaining_quantity <= PROBE + 1e-9}\n            sa = {o.price_ticks for o in state.own_orders if o.side is Side.SELL and o.remaining_quantity <= PROBE + 1e-9}\n            ea = self.pa - sa\n            eb = self.pb - sb\n            if sa and ea:\n                lo = max(lo, min(max(ea), hi))\n            if eb and (sb or min(eb) <= P['p1t']):\n                hi = min(hi, max(min(eb), lo))\n        if P['jumpinfo'] > 0 and self.pcb is not None:\n            if ca > self.pca + 1:\n                lo = max(lo, ca - 1)\n            if cb < self.pcb - 1:\n                hi = min(hi, cb + 1)\n        self.pcb, self.pca = cb, ca\n        if lo > hi:\n            lo, hi = hi, lo\n        # sub-tick belief over p_(t-1): predict with one-step noise, truncate to [lo, hi]\n        wid = max(hi - lo, 1e-6)\n        nb = max(2, min(48, int(round(wid * P['bins']))))\n        cs = [lo + (i + 0.5) * wid / nb for i in range(nb)]\n        if self.bc is None or P['filt'] <= 0:\n            ws = [1.0 / nb] * nb\n        else:\n            sg = max(self.st, 0.6 * wid / nb)\n            k = -0.5 / (sg * sg)\n            ws = []\n            uni = P['uni'] * sg\n            for c in cs:\n                t = uni\n                for ci, wi in zip(self.bc, self.bw):\n                    d = c - ci\n                    d2 = d * d * k\n                    if d2 > -12.5:\n                        t += wi * math.exp(d2)\n                ws.append(t)\n            tot = sum(ws)\n            ws = [w / tot for w in ws]\n        self.bc, self.bw = cs, ws\n        mean_t = sum(c * w for c, w in zip(cs, ws))\n        var_t = max(sum(c * c * w for c, w in zip(cs, ws)) - mean_t * mean_t, 0.0)\n        phat = min(max(mean_t / 100.0, 0.002), 0.998)\n        var = P['sig'] ** 2 + P['lam_j'] * P['sig_j'] ** 2\n        sd = math.sqrt(H * var)\n        self.tb = self.tb + 1 if hi <= 1 else 0\n        if self.tb > 0 and P['zd'] > 0:\n            # below the last tick there is no probe: the score keeps walking away from it\n            phat = min(phat, max(P['pfl'], cdf(inv(0.01) - P['zd'] * 0.02 * math.sqrt(self.tb) / sd)))\n        z = inv(phat)\n        Z = z * sd\n        sp = pdf(z) / sd * P['sig']\n        self.st = sp * 100.0\n        s = math.sqrt(sp * sp + var_t / 1e4 + 1e-8)\n        sd1 = math.sqrt(max(1.0, H - 1.0) * var)\n        jp = [(cdf((Z + n * P['sig_j']) / sd1), w) for n, w in NODES]\n        lj = P['lam_j']\n\n        def AB(x):\n            k = (x - phat) / s\n            a = s * lpm(k)\n            b = a - (x - phat)\n            ja = sum(w * max(0.0, x - p) for p, w in jp)\n            jb = sum(w * max(0.0, p - x) for p, w in jp)\n            return (1 - lj) * a + lj * ja, (1 - lj) * b + lj * jb\n\n        if H == 1:\n            def AB(x):\n                return (1 - phat) * x, phat * (1 - x)\n        rho = P['lam_r'] * 0.5\n        mu = math.log(P['m']) - 0.5 * P['sig_n'] ** 2\n        kA = P['kL'] if phat < P['pL'] else P['kA']\n\n        def qsize(loss, gain, px):\n            loss *= kA\n            if gain <= 0:\n                return 0.0\n            tail = loss / (rho * gain)\n            if tail >= 1.0:\n                return 0.0\n            return min(P['qmax'], math.exp(mu + P['sig_n'] * inv(1 - max(tail, 1e-6))) / px)\n\n        ptk = phat * 100\n        def qbid(t):\n            if not 1 <= t <= 99:\n                return 0.0\n            a, b = AB(t / 100.0)\n            if phat * 100 - t < P['dmin']:\n                return 0.0\n            if P['nb1'] > 0 and self.s == 1 and t == 1 and ptk < 1.0:\n                return 0.0\n            if phat < P['pL']:\n                ytg = P['ydem'] * min(H, P['W']) / max(ca - 1, ptk + 1) * 100.0\n                a *= (P['kLb'] if state.yes_inventory < ytg else P['kLf']) / P['kL']\n            return qsize(a, b, max(phat, 0.05))\n\n        def qask(t):\n            if not 1 <= t <= 99:\n                return 0.0\n            a, b = AB(t / 100.0)\n            if t - phat * 100 < P['dmin']:\n                return 0.0\n            return qsize(b, a, t / 100.0)\n\n        bids = [o for o in state.own_orders if o.side is Side.BUY and o.remaining_quantity > PROBE + 1e-9]\n        asks = [o for o in state.own_orders if o.side is Side.SELL and o.remaining_quantity > PROBE + 1e-9]\n        sticky = P['sticky'] > 0\n        def top(orders, comp, step):\n            if sticky and sum(o.remaining_quantity for o in orders if o.price_ticks == comp and o.order_id in self.ahead) >= P['min_ahead']:\n                return comp\n            return comp + step\n        bid_t = top(bids, cb, 1)\n        ask_t = top(asks, ca, -1)\n        qb = qbid(bid_t)\n        qa = qask(ask_t)\n\n        Y = state.yes_inventory\n        if ask_t == 1 and H > P['H1'] and P['pre'] > 0:\n            qa = qa if Y >= P['a1'] > 0 else 0.0          # let the competitor's 2-tick ask erode instead of fronting it for nothing\n        # ammunition: hold YES so that low asks are covered\n        ptick = phat * 100\n        amt = 0\n        qam = 0.0\n        if P['ammo'] > 0 and ask_t >= 2 and phat < max(P['ammo_pmax'], P['pmaxf']):\n            wealth = state.cash + Y * phat\n            x = max(ask_t, ptick + 1) / 100.0\n            capw = P['fy'] * wealth / max(phat, 0.005)\n            target = min(P['ydem'] * min(H, P['W']) / x, capw)\n            full = min(P['ydf'] * min(H, P['Wf']) / x, capw) if phat < P['pmaxf'] else 0.0\n            t = max(1, min(99, int(math.ceil(ptick + 1e-9))))\n            g = t - ptick\n            if Y < full and g <= P['g_hi'] and bid_t <= t < ask_t:\n                amt, qam = t, min(P['qf'], full - Y)     # a tick p has just crossed: nearly free\n            elif Y < target and phat < P['ammo_pmax'] and bid_t <= t < ask_t and t / 100.0 - phat < P['ammo_maxpay']:\n                amt, qam = t, min(P['ammo_q'], target - Y)\n            elif Y < full and t >= 2 and 1.0 - g <= P['g_lo']:\n                amt, qam = t - 1, min(P['qf'], full - Y)  # rest just under p: filled only on the crossing, or by retail\n\n        if P['pre'] > 0 and ca == 2 and phat < 0.01 and H > P['H1'] and Y < P['pre'] and not qam and 1.0 - ptick < P['pre_gap']:\n            amt, qam = 1, min(P['ammo_q'], P['pre'] - Y)\n        q1 = 0.0\n        if P['ydf1'] > 0 and P['m1'] < ptick < P['g1'] + 1.0 and amt != 1:\n            q1 = max(0.0, P['ydf1'] * min(H, P['Wf']) / (self.s / 100.0) - Y)\n        # order management\n        actions = []\n        free = state.free_cash - 2.0\n        keep_ask = 0.0\n        new_b = []\n        new_a = []\n        def cancel(o):\n            nonlocal free\n            actions.append(CancelOrder(o.order_id))\n            x = o.price_ticks / 100.0\n            if o.side is Side.BUY:\n                free += x * o.remaining_quantity\n            else:\n                free += (1 - x) * min(self.res.get(o.order_id, 0.0), o.remaining_quantity)\n            self.ahead.discard(o.order_id)\n            self.res.pop(o.order_id, None)\n        for o in state.own_orders:\n            if o.remaining_quantity <= PROBE + 1e-9:\n                cancel(o)\n        kept_ids = set()\n        def manage(orders, t, q, comp):\n            kept = 0.0\n            for o in orders:\n                if o.price_ticks == t and q > 0 and kept + o.remaining_quantity <= max(q * P['keep_hi'], 1.0):\n                    kept += o.remaining_quantity\n                    kept_ids.add(o.order_id)\n                else:\n                    cancel(o)\n            return kept\n        kb = manage(bids, bid_t, qb, cb)\n        ka = manage(asks, ask_t, qa, ca)\n        add_b = (qb - kb) if (kb < qb * P['keep_lo'] and bid_t != cb) else 0.0\n        add_a = (qa - ka) if (ka < qa * P['keep_lo'] and ask_t != ca) else 0.0\n\n        budget = P['fb'] * max(free, 0.0)\n        cost = add_b * bid_t / 100.0 + qam * amt / 100.0\n        if cost > budget:\n            f = budget / cost\n            add_b *= f\n            qam *= f\n            cost = budget\n        out = []\n        q1 = min(q1, P['f1'] * max(budget - cost, 0.0) * 100.0)\n        if q1 >= 0.01:\n            out.append(PlaceOrder(side=Side.BUY, price_ticks=1, quantity=fl(q1)))\n            free -= fl(q1) / 100.0 + 1e-6\n        if amt and qam >= 0.01:\n            q = fl(qam)\n            out.append(PlaceOrder(side=Side.BUY, price_ticks=amt, quantity=q))\n            free -= q * amt / 100.0 + 1e-6\n        if bid_t >= 1 and add_b >= 0.01:\n            q = fl(add_b)\n            oid = self._oid('b')\n            out.append(PlaceOrder(side=Side.BUY, price_ticks=bid_t, quantity=q, client_order_id=oid))\n            free -= q * bid_t / 100.0 + 1e-6\n            if bid_t > cb:\n                self.ahead.add(oid)\n        if ask_t <= 99 and add_a >= 0.01:\n            x = ask_t / 100.0\n            covk = sum(o.remaining_quantity - min(self.res.get(o.order_id, 0.0), o.remaining_quantity)\n                       for o in asks if o.order_id in kept_ids)\n            cov = max(0.0, Y - covk - 0.1)\n            unc = max(0.0, add_a - cov)\n            if unc > 0:\n                ub = max(0.0, free - (1 - P['fu']) * max(state.cash, 0.0)) if x >= P['xu'] else 0.0\n                if H < P['Hu'] and phat < 0.05:\n                    ub = max(0.0, free * (1 - H / P['Hu']))\n                unc = min(unc, ub / (1 - x))\n            q = fl(min(add_a, cov + unc))\n            if q >= 0.01:\n                oid = self._oid('a')\n                out.append(PlaceOrder(side=Side.SELL, price_ticks=ask_t, quantity=q, client_order_id=oid))\n                r = max(0.0, q - cov)\n                self.res[oid] = r\n                free -= r * (1 - x) + 1e-6\n                if ask_t < ca:\n                    self.ahead.add(oid)\n\n        # probes: tiny orders that the arbitrageur removes when p crosses them\n        f = int(math.floor(ptick + 1e-9))\n        r = max(int(P['rmin']), int(math.ceil(2.0 * s * 100)))\n        self.pb = set()\n        self.pa = set()\n        if free > 1.0:\n            for t in range(f, f + r + 1):\n                if cb < t < ca and 1 <= t <= 99:\n                    out.append(PlaceOrder(side=Side.BUY, price_ticks=t, quantity=PROBE))\n                    self.pb.add(t)\n            for t in range(f + 1 - r, f + 2):\n                if cb < t < ca and 1 <= t <= 99:\n                    out.append(PlaceOrder(side=Side.SELL, price_ticks=t, quantity=PROBE))\n                    self.pa.add(t)\n        return actions + out\n",
  "code_sha256": "d68e658732b99a47eb8004f684319f0bc3dc286fe52a066ab019442f8c91aac2",
  "tried": [
    "SCORER: unmodified upstream commit b244530ee2a6247b5f930830eeca9dd950da0e7e; Python 3.13.5; official CLI --workers 4 worked. Seeds 0-599, n=600, failures=0: mean_edge=102.33197908899267, retail_edge=127.3199510028995, arb_edge=-24.987971913912165; exact match to the base author's 102.33197908899267. Base source: https://api.imd.fun/artifacts/5ec4e47200eb5e16cec281f133e5e7fbfd73b3157fcf5f2c60d013ffa9300b76.",
    "METHOD: every ablation starts independently from the exact supplied base; constants were not tuned. All comparisons use the same 600 seeds 1000-1599 and default 2000 steps. Worth means base minus disabled, so negative worth means that component costs points in this sample. The final code was frozen before measurement; only it was evaluated on 30000-30599. No ablation was selected or tuned on holdout. These conditional marginal effects overlap and must not be added.",
    "NUMBERS: official CLI JSON contains per-simulation results rather than mean properties. Reported means use the upstream BatchResult.mean_edge/mean_retail_edge/mean_arb_edge properties on those JSON numbers, in original seed order, without rounding. Paired standard errors use sample standard deviation of 600 per-seed base-minus-disabled differences divided by sqrt(600). Intervals are exploratory mean +/- 1.96 SE, without multiplicity correction; a zero-crossing interval does not prove a feature is worthless.",
    "REPRODUCTION: for each ablation independently copy the submitted code, then apply its edits list as exact single-occurrence string replacements [old,new] in order; each old string must occur exactly once. The resulting SHA-256 must match disabled_code_sha256. From the pinned upstream clone run python3 -m orderbook_pm_challenge run FILE --simulations 600 --seed-start 1000 --workers 4 --json (or omit --workers for serial). No ablation depends on a private file or extra package.",
    "BASE MEASUREMENT: seeds 1000-1599, n=600, failures=0, mean_edge=107.2442092237515, retail_edge=135.80165652288784, arb_edge=-28.557447299150834.",
    "SWITCH SCOPE: YES cover means the ammo replenishment block, separated from the requested large tick-1 bid; the supplemental joint deletion measures the broader intentional-stock policy. Exchange YES collateral and incidental inventory from normal market-making buys remain. One-tick-spread rules means the active main ask at tick 1 plus spread-1 stock-target doubling, using self.s; individual deletions are also measured. Inactive pre/nb1 branches are not credited as active rules.",
    "SANDBOX base: official --sandbox --simulations 20 --seed-start 1000 returned 20/20 failures before strategy loading: ImportError: Import of 'ntpath' is not allowed in sandbox mode, from pathlib. Both the unchanged base and examples/starter_strategy.py have this runner compatibility failure on Python 3.13.5; no runner patch was used for any score.",
    "SANDBOX starter: official --sandbox --simulations 20 --seed-start 1000 returned 20/20 failures before strategy loading: ImportError: Import of 'ntpath' is not allowed in sandbox mode, from pathlib. Both the unchanged base and examples/starter_strategy.py have this runner compatibility failure on Python 3.13.5; no runner patch was used for any score.",
    "SOURCE NO-OPS: pre=0 disables the ask_t==1 pre-buy guard and the ca==2 pre-buy branch; nb1=0 disables its spread-1 low-bid veto; gs is never read. kLb=kLf=0.08 makes the YES-target choice in qbid select the same multiplier either way. These disabled branches/settings contribute exactly zero under the supplied parameters by code inspection. This is distinct from an estimated zero for the active policies.",
    "ABLATION no_probes: Remove both tiny-probe placement loops and eaten-probe inference; retain constraints from surviving main orders and competitor movement. Seeds 1000-1599, n=600, failures=0; mean_edge=-24.616810273335503, retail_edge=101.27529291708916, arb_edge=-125.89210319042817; worth(base-disabled)=131.861019497087, paired_SE=6.907918817022786, normal_95_CI=[118.32149861572233, 145.40054037845167]; retail_worth=34.526363605798664, arb_worth=97.33465589127734; median_seed_worth=60.6333297664; seeds base better/disabled better/tied within 1e-9=571/29/0; disabled_code_sha256=8c6ecd27d37af3722edc1f4b492bb56646bfd653b0ce62ff7abbf953fc70b77a; edits=[[\"if P['pinf'] > 0:\",\"if False:\"],[\"if free > 1.0:\",\"if False:\"]].",
    "SUPPLEMENT no_all_stock_purchase: Interaction check: ammo=0 and ydf1=0 jointly remove both explicit YES-stock purchase mechanisms. Normal market-making bids and natural YES collateral remain. Seeds 1000-1599, n=600, failures=0; mean_edge=82.851768902842, retail_edge=102.92166900537983, arb_edge=-20.069900102550335; worth(base-disabled)=24.3924403209095, paired_SE=3.4032421535157575, normal_95_CI=[17.722085700018617, 31.062794941800384]; retail_worth=32.879987517508, arb_worth=-8.4875471966005; median_seed_worth=0.0; seeds base better/disabled better/tied within 1e-9=141/169/290; disabled_code_sha256=3d90d8839dd169d7edd964f15e6d1102b9c4055d954b92c8e8eb58c47604f6e2; edits=[[\"ammo=1.0\",\"ammo=0.0\"],[\"ydf1=0.6\",\"ydf1=0.0\"]].",
    "ABLATION no_tick1_bid: ydf1=0: remove the extra large resting tick-1 crossing bid only; ordinary qbid and ammunition bids may still quote tick 1. Seeds 1000-1599, n=600, failures=0; mean_edge=93.025762533368, retail_edge=121.43014976388334, arb_edge=-28.404387230519504; worth(base-disabled)=14.2184466903835, paired_SE=2.5082145908575018, normal_95_CI=[9.302346092302797, 19.134547288464205]; retail_worth=14.371506759004498, arb_worth=-0.15306006863133317; median_seed_worth=0.0; seeds base better/disabled better/tied within 1e-9=131/108/361; disabled_code_sha256=672ef13fc977712c85e31b53e98e5e29abfb3f65a7dcd39a1d5a71fadafc2b44; edits=[[\"ydf1=0.6\",\"ydf1=0.0\"]].",
    "ABLATION no_order_retention: sticky=0 and manage() never retains a main order: cancel/requote each step at one tick inside the competitor, losing all saved queue priority. Seeds 1000-1599, n=600, failures=0; mean_edge=95.4052494564685, retail_edge=128.21985993904883, arb_edge=-32.81461048259433; worth(base-disabled)=11.838959767283, paired_SE=1.4511208736403967, normal_95_CI=[8.994762854947822, 14.683156679618179]; retail_worth=7.581796583839, arb_worth=4.2571631834435; median_seed_worth=5.614339034450002; seeds base better/disabled better/tied within 1e-9=558/40/2; disabled_code_sha256=8e9d22a5bcde4212b9f0f45d212660eece2a7f432a333a38d7039342ed8f827c; edits=[[\"sticky=1.0\",\"sticky=0.0\"],[\"if o.price_ticks == t and q > 0 and kept + o.remaining_quantity <= max(q * P['keep_hi'], 1.0):\",\"if False:\"]].",
    "ABLATION no_subtick_filter: filt=0: replace temporal grid prediction with uniform weights on the current observable [lo,hi]; retain probes, interval variance and below-1c time decay. Seeds 1000-1599, n=600, failures=0; mean_edge=96.6743838522075, retail_edge=132.74851295554532, arb_edge=-36.0741291033685; worth(base-disabled)=10.569825371544, paired_SE=1.0898175019797527, normal_95_CI=[8.433783067663686, 12.705867675424315]; retail_worth=3.0531435673425, arb_worth=7.516681804217667; median_seed_worth=2.5084251157000037; seeds base better/disabled better/tied within 1e-9=466/133/1; disabled_code_sha256=3761155e5cb4a71399866e653ca665e26f277a77a182a10b3990bbe14b10eb1b; edits=[[\"filt=1.0\",\"filt=0.0\"]].",
    "SUPPLEMENT no_spread1_tick1_asks: One-tick-spread decomposition: disable main tick-1 asks only when self.s==1; leave the original tick-1 inventory target. Seeds 1000-1599, n=600, failures=0; mean_edge=96.838458049037, retail_edge=124.89755172261717, arb_edge=-28.0590936735885; worth(base-disabled)=10.4057511747145, paired_SE=1.8647131624900866, normal_95_CI=[6.75091337623393, 14.060588973195069]; retail_worth=10.904104800270666, arb_worth=-0.4983536255623333; median_seed_worth=0.0; seeds base better/disabled better/tied within 1e-9=68/4/528; disabled_code_sha256=4d45ae4240c7c09d1500f4963c5d2299b74907681ec6ea71c647793d30b95e05; edits=[[\"        qa = qask(ask_t)\\n\",\"        qa = qask(ask_t)\\n        if self.s == 1 and ask_t == 1:\\n            qa = 0.0\\n\"]].",
    "ABLATION no_one_tick_spread_rules: For inferred competitor spread self.s==1 only: stop main asks at tick 1 and use a 2c minimum denominator in the large tick-1 inventory target. Removes the active sell-at-1c and doubled-stock package. The old nb1/pre branches are already inactive in the base. Seeds 1000-1599, n=600, failures=0; mean_edge=98.67447505702184, retail_edge=124.88064929664898, arb_edge=-26.206174239635832; worth(base-disabled)=8.569734166729667, paired_SE=1.637468828421088, normal_95_CI=[5.360295263024334, 11.779173070435]; retail_worth=10.921007226238833, arb_worth=-2.351273059515; median_seed_worth=0.0; seeds base better/disabled better/tied within 1e-9=64/18/518; disabled_code_sha256=0447579a8600d27a7d8c469921d11fd6b34f337548a90361b1b9c4c1e800d85d; edits=[[\"        qa = qask(ask_t)\\n\",\"        qa = qask(ask_t)\\n        if self.s == 1 and ask_t == 1:\\n            qa = 0.0\\n\"],[\"/ (self.s / 100.0)\",\"/ (max(self.s, 2) / 100.0)\"]].",
    "SUPPLEMENT no_spread1_stock_scaling: One-tick-spread decomposition: use max(self.s,2) only in q1 inventory-target denominator; keep main tick-1 asks enabled. Seeds 1000-1599, n=600, failures=0; mean_edge=102.68693047321867, retail_edge=130.62740655654883, arb_edge=-27.940476083345498; worth(base-disabled)=4.557278750532833, paired_SE=1.1750261579510146, normal_95_CI=[2.254227480948845, 6.860330020116821]; retail_worth=5.174249966339, arb_worth=-0.6169712158053333; median_seed_worth=0.0; seeds base better/disabled better/tied within 1e-9=40/41/519; disabled_code_sha256=083a4228c1b40317696bee29c90c538c64cf91e4478b8c8bf173a474fd81ac2f; edits=[[\"/ (self.s / 100.0)\",\"/ (max(self.s, 2) / 100.0)\"]].",
    "ABLATION no_last_step_rule: Remove the H==1 terminal Bernoulli loss override in AB(); use the usual diffusion/jump approximation at the last step too. Seeds 1000-1599, n=600, failures=0; mean_edge=107.21534889041817, retail_edge=135.77249585622116, arb_edge=-28.557146965817502; worth(base-disabled)=0.02886033333333323, paired_SE=0.015721791532183938, normal_95_CI=[-0.0019543780697472875, 0.059675044736413746]; retail_worth=0.029160666666666564, arb_worth=-0.0003003333333333195; median_seed_worth=0.0; seeds base better/disabled better/tied within 1e-9=18/21/561; disabled_code_sha256=c40dc56aee1764e304fcd9500cf0eafe8fd49306fc19725f9fe0daa826681a21; edits=[[\"if H == 1:\",\"if False:\"]].",
    "ABLATION no_yes_cover_ammo: ammo=0: disable the non-q1 ammunition block, including qam target purchases and near-tick crossing purchases; retain the separate large tick-1 bid and exchange collateral mechanics. Seeds 1000-1599, n=600, failures=0; mean_edge=108.23052839965034, retail_edge=133.56467411974282, arb_edge=-25.334145720107166; worth(base-disabled)=-0.986319175898833, paired_SE=0.5424440496150541, normal_95_CI=[-2.049509513144339, 0.07687116134667304]; retail_worth=2.2369824031450003, arb_worth=-3.2233015790436665; median_seed_worth=0.0; seeds base better/disabled better/tied within 1e-9=73/231/296; disabled_code_sha256=40e3d6a76b133aca632da031fac3ca5563a79732edae6dcd23f46c62d65df216; edits=[[\"ammo=1.0\",\"ammo=0.0\"]].",
    "READOUT: components with negative point-estimate worth (removing them improved this sample): no_yes_cover_ammo. Primary effects whose normal 95% interval includes zero: no_yes_cover_ammo, no_last_step_rule. Treat these as local paired measurements, not claims about Paradigm hidden seeds.",
    "PRIMARY COMPONENT WORTH MAP (base minus disabled): no_probes=131.861019497087; no_subtick_filter=10.569825371544; no_tick1_bid=14.2184466903835; no_yes_cover_ammo=-0.986319175898833; no_order_retention=11.838959767283; no_one_tick_spread_rules=8.569734166729667; no_last_step_rule=0.02886033333333323.",
    "LOW/NEGATIVE VALUE: the active last-step rule is practically small on this sample: worth=0.02886033333333323, normal_95_CI=[-0.0019543780697472875, 0.059675044736413746], with 561/600 effects zero within 1e-9. The non-q1 YES ammunition block costs 0.986319175898833 points by the sample mean, but its worth interval [-2.049509513144339, 0.07687116134667304] still includes zero. Neither result proves an exactly zero or harmful true-mean effect; only the inactive controls identified above have exactly zero effect by inspection.",
    "SPREAD-1 DETAIL no_one_tick_spread_rules: n=144, worth=35.70722569470694, paired_SE=6.3262599423199015, normal_95_CI=[23.307756207759937, 48.10669518165395]; all spread-2/3/4 seed effects individually checked to absolute numerical tolerance below 1e-8 in total, retail and arb edge.",
    "SPREAD-1 DETAIL no_spread1_tick1_asks: n=144, worth=43.35729656131042, paired_SE=7.120201671661035, normal_95_CI=[29.40170128485479, 57.312891837766045]; all spread-2/3/4 seed effects individually checked to absolute numerical tolerance below 1e-8 in total, retail and arb edge.",
    "SPREAD-1 DETAIL no_spread1_stock_scaling: n=144, worth=18.988661460553473, paired_SE=4.7097062984201274, normal_95_CI=[9.757637115650024, 28.219685805456923]; all spread-2/3/4 seed effects individually checked to absolute numerical tolerance below 1e-8 in total, retail and arb edge.",
    "SPREAD-1 INTERACTION: main tick-1 asks alone are worth 10.4057511747145, and the doubled stock target alone is worth 4.557278750532833, each conditional on the rest of the base. The package is worth 8.569734166729667, so these estimates must not be added. With tick-1 asks disabled, the doubled target is instead worth -1.8360170079848332, paired_SE=0.4850876260179295, normal_95_CI=[-2.786788754979975, -0.8852452609896915].",
    "BASE SCORE CONCENTRATION 1000-1599: the top 60 of 600 simulations contribute 0.47645775398393336 of total edge. This is a descriptive check of local score concentration; all simulations remain equally weighted in every reported mean.",
    "BASE SCORE CONCENTRATION 30000-30599: the top 60 of 600 simulations contribute 0.507781059780843 of total edge. This is a descriptive check of local score concentration; all simulations remain equally weighted in every reported mean.",
    "STOCK INTERACTION: large tick-1 bid marginal worth=14.2184466903835; other ammunition marginal worth=-0.986319175898833; joint deletion cost=24.3924403209095. Joint-minus-sum=11.160312806424834; the two purchase routes are not independent.",
    "CONDITIONAL AMMUNITION: with the large tick-1 bid already disabled, retaining the other ammunition is worth 10.173993630526, paired_SE=1.8253364113338353, normal_95_CI=[6.596334264311683, 13.751652996740319]. The negative primary ammo estimate applies only with the large tick-1 bid present; it does not justify eliminating all intentional YES purchases.",
    "FINAL UNCHANGED BASE: code_sha256=d68e658732b99a47eb8004f684319f0bc3dc286fe52a066ab019442f8c91aac2; seeds 1000-1599 mean_edge=107.2442092237515, holdout 30000-30599 mean_edge=96.0405203261775, holdout retail_edge=124.3725985363135, holdout arb_edge=-28.332078210128167; 600 simulations and zero failures in each unsandboxed batch. Ablation idea rows are ordered by disabled-strategy mean score, best last; the submitted code remains the base as requested."
  ],
  "next": "Independently confirm ammo=0 with the large tick-1 bid retained on a new untouched seed block: it scored 108.23052839965034 versus base 107.2442092237515 on 1000-1599, with lower arb losses, but its paired interval still includes zero. Preserve probes, the sub-tick filter, the large tick-1 bid, order retention and the active spread-1 package: their deletions all have clearly positive costs here. Treat the last-step rule as a low-priority simplification, not a route to several points of improvement. Use the joint stock deletion and split spread-1 results to avoid counting overlapping gains twice; do not tune on the reported holdout. Inactive pre/nb1/gs controls can be cleaned up without changing behavior, but that cannot improve the score."
}