{
  "approach": "Coarsens the posterior belief grid from eight to four centres per tick only for spread 2. This was the highest-mean candidate completed at freeze that gained on both disjoint training halves; the gains came mainly from less arbitrage loss with approximately unchanged retail edge. Simulator commit b244530ee2a6247b5f930830eeca9dd950da0e7e; Python standard library only. Training screens used only spread-2 runs in seeds 4000-7999; the two disjoint confirmation blocks are recorded in tried. Parameters are instance-local and overridden only when the base inference self.s equals 2. Full per-run result dictionaries match the base on every non-2 run in the 600-seed check, 4000 training runs, and 4000 unseen runs. The code was frozen before evaluating it once on seeds 50000-53999. Positive arb_edge changes mean reduced arbitrage loss. All figures are measured locally; no missing scores or fabricated values. Unseen paired whole-file difference=0.026186278869049916, standard_error=0.028480053439220766; this does not establish an improvement at two paired standard errors.",
  "blocked": null,
  "python_version": "3.12.3",
  "base_mean_edge": 109.27254289017199,
  "base_holdout_mean_edge": 98.28063388702982,
  "score": {
    "mean_edge": 98.83942460660653,
    "retail_edge": 124.34260207298652,
    "arb_edge": -25.503177466397474,
    "simulations": 4000,
    "seed_start": 4000,
    "failures": 0
  },
  "holdout": {
    "mean_edge": 98.30682016589887,
    "retail_edge": 126.04095539629678,
    "arb_edge": -27.73413523039735,
    "simulations": 4000,
    "seed_start": 50000,
    "failures": 0
  },
  "by_spread": [
    {
      "spread": 1,
      "runs": 1016,
      "base": 35.099921878704336,
      "yours": 35.099921878704336,
      "diff": 0.0,
      "standard_error": 0.0
    },
    {
      "spread": 2,
      "runs": 998,
      "base": 83.51205221971222,
      "yours": 83.61700724523948,
      "diff": 0.10495502552725416,
      "standard_error": 0.11415515237099481
    },
    {
      "spread": 3,
      "runs": 1017,
      "base": 122.97345583671554,
      "yours": 122.97345583671554,
      "diff": 0.0,
      "standard_error": 0.0
    },
    {
      "spread": 4,
      "runs": 969,
      "base": 153.82041508580312,
      "yours": 153.82041508580312,
      "diff": 0.0,
      "standard_error": 0.0
    }
  ],
  "constants": {
    "P.bins": 4
  },
  "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)\nP.update({'W': 50, 'ammo_pmax': 0.02, 'fy': 0.7, 'fu': 0.25, 'Hu': 500})\nC = {'W': 50, 'ammo_pmax': 0.02, 'fy': 0.7, 'reserve': 200, 'scar': 0.0025, 'fu': 0.25, 'Hu': 500}\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.params = P.copy()\n        self.controls = C.copy()\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        P, C = self.params, self.controls\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        if self.s == 2:\n            P.update({'bins': 4})\n            C.update({})\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            if phat < C.get('scar_p', .1):\n                a = max(0.0, a - C.get('scar', 0.0) * (1 - min(1.0, state.yes_inventory / C.get('stock', 3000.0))))\n            return min(C.get('askcap', P['qmax']), 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 = min(C.get('bidcap', 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:\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 not (C.get('recover', 0) and o.side is Side.SELL and t < comp and self.res.get(o.order_id, 0.0) > 1 and state.yes_inventory > C.get('recover_yes', 1) and state.free_cash < C.get('recover_cash', 200)) and 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                ub = min(ub, max(0.0, free - C.get('reserve', 0.0) * min(1.0, H / C.get('release', 50.0))))\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-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": "99d6ea7cf785661315df84c874ac4578158c1b373bb5a76b5d4fc0e2c537ffb6",
  "tried": [
    "Official scorer check: seeds 1000-1599, n=600, base mean=109.27254289017199, expected 109.27254289017199, failures=0.",
    "sticky0: P={'sticky': 0}; spread 2 seeds 4004-4399, n=88, mean=93.94287106559091, retail=115.85319943884888, arb=-21.910328373273863, failures=0, paired delta=-14.073170296821589, SE=1.608949415185596, retail delta=-12.080580406442039, arb delta=-1.992589890357955.",
    "asymstrong: P={'bid_risk': 3, 'ask_risk': 0.5}; spread 2 seeds 4004-4399, n=88, mean=96.20866556872728, retail=118.18214548351703, arb=-21.97347991469432, failures=0, paired delta=-11.807375793685225, SE=1.8618555576922518, retail delta=-9.751634361773881, arb delta=-2.0557414317784115.",
    "q750: P={'qmax': 750}, C={'bidcap': 750}; spread 2 seeds 4004-4399, n=88, mean=96.56505395581931, retail=115.23292617254546, arb=-18.667872216761364, failures=0, paired delta=-11.450987406593184, SE=2.5359036269678463, retail delta=-12.700853672745453, arb delta=1.2498662661545445.",
    "asym: P={'bid_risk': 2, 'ask_risk': 0.7}; spread 2 seeds 4004-4399, n=88, mean=101.39258956292728, retail=121.8986413439409, arb=-20.506051780995453, failures=0, paired delta=-6.623451799485227, SE=1.3897008351003712, retail delta=-6.035138501350019, arb delta=-0.5883132980795445.",
    "dmin10: P={'dmin': 1.0}; spread 2 seeds 4004-4399, n=88, mean=101.4627725963716, retail=117.76077288337841, arb=-16.298000287007955, failures=0, paired delta=-6.553268766040909, SE=1.8483388125395626, retail delta=-10.173006961912506, arb delta=3.619738195907953.",
    "bid3: P={'bid_risk': 3, 'ask_risk': 1}; spread 2 seeds 4004-4399, n=88, mean=102.29828163792614, retail=118.8196925905625, arb=-16.521410952639773, failures=0, paired delta=-5.717759724486364, SE=0.8547481975950356, retail delta=-9.114087254728418, arb delta=3.3963275302761353.",
    "ask05: P={'bid_risk': 1, 'ask_risk': 0.5}; spread 2 seeds 4004-4399, n=88, mean=103.25546474906022, retail=129.92401529833296, arb=-26.6685505492125, failures=0, paired delta=-4.7605766133522724, SE=1.2434510596231576, retail delta=1.9902354530420467, arb delta=-6.750812066296593.",
    "stock03: P={'ydf1': 0.3}; spread 2 seeds 4004-4399, n=88, mean=103.67176673996931, retail=127.39736888863864, arb=-23.725602148711367, failures=0, paired delta=-4.344274622443182, SE=1.3532639228187655, retail delta=-0.5364109566522757, arb delta=-3.807863665795459.",
    "stock15: P={'ydf1': 1.5}; spread 2 seeds 4004-4399, n=88, mean=104.00388091440796, retail=128.2238741111625, arb=-24.21999319680227, failures=0, paired delta=-4.012160448004546, SE=1.4082493905077247, retail delta=0.2900942658715877, arb delta=-4.302254713886363.",
    "nojumpinfo: P={'jumpinfo': 0}; spread 2 seeds 4004-4399, n=88, mean=104.89577265410001, retail=127.4736596723943, arb=-22.5778870183125, failures=0, paired delta=-3.1202687083124987, SE=1.0101043901978104, retail delta=-0.4601201728966089, arb delta=-2.6601485353965906.",
    "q1500: P={'qmax': 1500}, C={'bidcap': 1500}; spread 2 seeds 4004-4399, n=88, mean=105.15236919576364, retail=124.78530349909887, arb=-19.632934303377272, failures=0, paired delta=-2.8636721666488643, SE=0.9734753146593096, retail delta=-3.148476346192041, arb delta=0.2848041795386358.",
    "k14: P={'kA': 1.4}; spread 2 seeds 4004-4399, n=88, mean=105.23080864598751, retail=121.30601856017728, arb=-16.07520991421818, failures=0, paired delta=-2.785232716425001, SE=0.6392966914581927, retail delta=-6.627761285113635, arb delta=3.842528568697727.",
    "bid2: P={'bid_risk': 2, 'ask_risk': 1}; spread 2 seeds 4004-4399, n=88, mean=105.26917370766591, retail=122.34932086993977, arb=-17.080147162279545, failures=0, paired delta=-2.746867654746591, SE=0.6337461058130113, retail delta=-5.58445897535114, arb delta=2.8375913206363634.",
    "stock06w500: P={'Wf': 500}; spread 2 seeds 4004-4399, n=88, mean=105.3774392131625, retail=127.27977828819772, arb=-21.902339075077272, failures=0, paired delta=-2.6386021492499996, SE=1.1364408024242874, retail delta=-0.6540015570931956, arb delta=-1.9846005921613639.",
    "tickcap2: C={'askcap2': 1500}; spread 2 seeds 4004-4399, n=88, mean=105.38165600638068, retail=124.97485273747158, arb=-19.593196731130682, failures=0, paired delta=-2.6343853560318187, SE=0.865402003396959, retail delta=-2.958927107819335, arb delta=0.32454175178522604.",
    "tickcaps: P={'qmax': 6000}, C={'bidcap': 3000, 'askcap': 3000, 'askcap1': 6000, 'askcap2': 1500}; spread 2 seeds 4004-4399, n=88, mean=105.38165600638068, retail=124.97485273747158, arb=-19.593196731130682, failures=0, paired delta=-2.6343853560318187, SE=0.865402003396959, retail delta=-2.958927107819335, arb delta=0.32454175178522604.",
    "kLb02: P={'kLb': 0.02, 'kLf': 0.02}; spread 2 seeds 4004-4399, n=88, mean=105.43760714372159, retail=128.67558767034546, arb=-23.237980526667045, failures=0, paired delta=-2.578434218690909, SE=1.0870627658863743, retail delta=0.7418078250545506, arb delta=-3.3202420437511364.",
    "nopinf: P={'pinf': 0}; spread 2 seeds 4004-4399, n=88, mean=105.57843733414205, retail=126.2850657839659, arb=-20.706628449868184, failures=0, paired delta=-2.4376040282704556, SE=0.9245828373148081, retail delta=-1.648714061325009, arb delta=-0.7888899669522758.",
    "ask07: P={'bid_risk': 1, 'ask_risk': 0.7}; spread 2 seeds 4004-4399, n=88, mean=105.81086936348183, retail=129.3490373329159, arb=-23.538167969435225, failures=0, paired delta=-2.2051719989306813, SE=1.00986320434026, retail delta=1.4152574876249986, arb delta=-3.620429486519317.",
    "sigj45: P={'sig_j': 0.45}; spread 2 seeds 4004-4399, n=88, mean=105.84304993349092, retail=128.2355907427159, arb=-22.392540809261366, failures=0, paired delta=-2.1729914289215917, SE=0.612724760243574, retail delta=0.3018108974249998, arb delta=-2.4748023263454577.",
    "lamj28: P={'lam_j': 0.0028}; spread 2 seeds 4004-4399, n=88, mean=106.11277073647499, retail=127.59813923463751, arb=-21.48536849820909, failures=0, paired delta=-1.9032706259375018, SE=0.47229859848547745, retail delta=-0.33564061065339956, arb delta=-1.567630015293183.",
    "lowfull: P={'ammo': 0, 'kLf': 0.3, 'fu': 0.7, 'Hu': 300}, C={'scar': 0, 'reserve': 0}, mid-price ask risk x2; spread 2 seeds 4004-4399, n=88, mean=106.2305674600716, retail=122.06632989537842, arb=-15.835762435364773, failures=0, paired delta=-1.7854739023409103, SE=0.8787340803155269, retail delta=-5.867449949912498, arb delta=4.0819760475511355.",
    "fu0: P={'fu': 0, 'Hu': 0}; spread 2 seeds 4004-4399, n=88, mean=106.31786893393637, retail=125.79538754773976, arb=-19.477518613870455, failures=0, paired delta=-1.6981724284761357, SE=0.4354529460812638, retail delta=-2.1383922975511496, arb delta=0.4402198690454533.",
    "dmin05: P={'dmin': 0.5}; spread 2 seeds 4004-4399, n=88, mean=106.68335766568863, retail=124.08942977701591, arb=-17.406072111331817, failures=0, paired delta=-1.3326836967238642, SE=1.2547793844830086, retail delta=-3.8443500682750056, arb delta=2.5116663715840915.",
    "bid15: P={'bid_risk': 1.5, 'ask_risk': 1}; spread 2 seeds 4004-4399, n=88, mean=106.78392649168522, retail=124.49423711225795, arb=-17.710310620575, failures=0, paired delta=-1.2321148707272729, SE=0.3994484249780804, retail delta=-3.4395427330329653, arb delta=2.207427862340907.",
    "k05: P={'kA': 0.5}; spread 2 seeds 4004-4399, n=88, mean=106.91113831436819, retail=131.25205761383296, arb=-24.34091929950682, failures=0, paired delta=-1.1049030480443174, SE=0.5471983101083029, retail delta=3.318277768542046, arb delta=-4.423180816590911.",
    "riskbelow: P={'kA': 0.7, 'kL': 0.3, 'kLb': 0.16, 'kLf': 0.16}; spread 2 seeds 4004-4399, n=88, mean=106.91400646795, retail=125.35161099054545, arb=-18.437604522626135, failures=0, paired delta=-1.1020348944625018, SE=0.5986508364084778, retail delta=-2.5821688547454613, arb delta=1.4801339602897734.",
    "k10: P={'kA': 1.0}; spread 2 seeds 4004-4399, n=88, mean=106.9970677092659, retail=124.55634737954546, arb=-17.559279670286365, failures=0, paired delta=-1.0189736531465925, SE=0.4090161185442543, retail delta=-3.377432465745457, arb delta=2.358458812629543.",
    "uni001: P={'uni': 0.001}; spread 2 seeds 4004-4399, n=88, mean=107.07530151459204, retail=127.91205082163637, arb=-20.836749307102274, failures=0, paired delta=-0.9407398478204566, SE=0.4312391905150238, retail delta=-0.021729023654543766, arb delta=-0.9190108241863655.",
    "lamj10: P={'lam_j': 0.001}; spread 2 seeds 4004-7998, n=1033, mean=78.32984723683252, retail=106.27073270383447, arb=-27.9408854670333, failures=0, paired delta=-0.9338125676397868, SE=0.6134864934939793, retail delta=-0.09825653567065729, arb delta=-0.835556031969503.",
    "lowcombo: P={'ammo': 0, 'kLf': 0.3}, mid-price ask risk x2; spread 2 seeds 4004-4399, n=88, mean=107.18921115468638, retail=122.51433600943182, arb=-15.325124854790909, failures=0, paired delta=-0.8268302077261364, SE=0.7743015144857317, retail delta=-5.419443835859099, arb delta=4.592613628124999.",
    "stock09: P={'ydf1': 0.9}; spread 2 seeds 4004-4399, n=88, mean=107.19138856559204, retail=128.19761318463523, arb=-21.00622461909091, failures=0, paired delta=-0.8246527968204553, SE=0.9525577228420712, retail delta=0.2638333393443162, arb delta=-1.0884861361750033.",
    "ask2: mid-price ask risk x2; spread 2 seeds 4004-4399, n=88, mean=107.19460730962273, retail=125.30109336034091, arb=-18.10648605076023, failures=0, paired delta=-0.8214340527897733, SE=0.4721853244390788, retail delta=-2.63268648495, arb delta=1.8112524321556798.",
    "reserve0: C={'reserve': 0}; spread 2 seeds 4004-4399, n=88, mean=107.31531657029318, retail=127.47238700352045, arb=-20.15707043326591, failures=0, paired delta=-0.7007247921193183, SE=0.738056016581678, retail delta=-0.46139284177046136, arb delta=-0.2393319503500031.",
    "lowrisk: P={'kLb': 0.16, 'kLf': 0.3}; spread 2 seeds 4004-4399, n=88, mean=107.33407565381249, retail=126.1648399101466, arb=-18.830764256375, failures=0, paired delta=-0.6819657086000008, SE=0.48200170315456115, retail delta=-1.7689399351443171, arb delta=1.0869742265409066.",
    "simple09: P={'ammo': 0, 'kA': 0.9}; spread 2 seeds 4004-4399, n=88, mean=107.41573154264319, retail=124.18398610510795, arb=-16.768254562451137, failures=0, paired delta=-0.600309819769318, SE=0.6034422544934281, retail delta=-3.749793740182966, arb delta=3.149483920464771.",
    "noammo: P={'ammo': 0}; spread 2 seeds 6001-7998, n=499, mean=78.06302842194509, retail=105.11999933195831, arb=-27.05697091003467, failures=0, paired delta=-0.5634611730793582, SE=0.31341763318690286, retail delta=-2.04403144766934, arb delta=1.4805702745885725.",
    "bid750: C={'bidcap': 750}; spread 2 seeds 4004-4399, n=88, mean=107.57477197957387, retail=127.44150987110797, arb=-19.86673789156932, failures=0, paired delta=-0.4412693828386363, SE=0.353310795365147, retail delta=-0.49226997418294616, arb delta=0.05100059134658963.",
    "nosc: C={'scar': 0}; spread 2 seeds 4004-4399, n=88, mean=107.74065730762045, retail=128.0253402538193, arb=-20.28468294623295, failures=0, paired delta=-0.27538405479204614, SE=0.27189520823576474, retail delta=0.09156040852839453, arb delta=-0.36694446331704356.",
    "rmin1: P={'rmin': 1}; spread 2 seeds 4004-4399, n=88, mean=107.75354171020795, retail=127.81304171937613, arb=-20.0595000092, failures=0, paired delta=-0.2624996522045466, SE=0.1568397656357665, retail delta=-0.12073812591478372, arb delta=-0.14176152628409255.",
    "keep11: P={'keep_hi': 1.1, 'keep_lo': 0.9}; spread 2 seeds 4004-4399, n=88, mean=107.7790990583216, retail=127.99887386284318, arb=-20.219774804557954, failures=0, paired delta=-0.23694230409090825, SE=0.35370001071770935, retail delta=0.06509401755226918, arb delta=-0.30203632164204564.",
    "stockcap03: P={'f1': 0.3}; spread 2 seeds 4004-4399, n=88, mean=107.78395217693864, retail=127.94548764109432, arb=-20.16153546419432, failures=0, paired delta=-0.23208918547386306, SE=0.1676596312222895, retail delta=0.011707795803403087, arb delta=-0.2437969812784111.",
    "ask6000: P={'qmax': 6000}, C={'bidcap': 3000}; spread 2 seeds 6001-7998, n=499, mean=78.4093126701475, retail=107.64452102408377, arb=-29.23520835395671, failures=0, paired delta=-0.21717692487695417, SE=0.33070647124094116, retail delta=0.48049024445612076, arb delta=-0.6976671693334673.",
    "k06: P={'kA': 0.6}; spread 2 seeds 4004-5997, n=534, mean=79.6546351559337, retail=106.97441421817265, arb=-27.319779062290824, failures=0, paired delta=-0.20443276560692888, SE=0.09582878371676078, retail delta=1.3483570545498083, arb delta=-1.5527898201674155.",
    "ammo30: P={'ammo_q': 30, 'qf': 200}; spread 2 seeds 4004-4399, n=88, mean=107.85757002123523, retail=127.59909366453749, arb=-19.74152364334091, failures=0, paired delta=-0.1584713411772745, SE=0.32517776600974396, retail delta=-0.3346861807534225, arb delta=0.17621483957499962.",
    "hu2000: P={'Hu': 2000}; spread 2 seeds 4004-5997, n=534, mean=79.72001356345393, retail=105.82181389859345, arb=-26.10180033518427, failures=0, paired delta=-0.13905435808670408, SE=0.22850276092108132, retail delta=0.1957567349706011, arb delta=-0.33481109306086054.",
    "k08: P={'kA': 0.8}; spread 2 seeds 6001-7998, n=499, mean=78.4891499001491, retail=106.01368007001022, arb=-27.524530169886173, failures=0, paired delta=-0.13733969487534958, SE=0.11172202605766994, retail delta=-1.1503507096174275, arb delta=1.0130110147370708.",
    "reserve400: C={'reserve': 400}; spread 2 seeds 4004-4399, n=88, mean=107.87902696369092, retail=127.8250411679625, arb=-19.94601420431477, failures=0, paired delta=-0.13701439872159146, SE=0.09980933004389608, retail delta=-0.10873867732841802, arb delta=-0.02827572139886314.",
    "pfl10: P={'pfl': 0.001}; spread 2 seeds 4004-4399, n=88, mean=107.89749016050455, retail=127.81523091545569, arb=-19.917740754987502, failures=0, paired delta=-0.11855120190795371, SE=0.0844025979097711, retail delta=-0.11854892983522802, arb delta=-2.272071593978353e-06.",
    "zd05: P={'zd': 0.5}; spread 2 seeds 4004-4399, n=88, mean=107.90001115654091, retail=127.81738677871931, arb=-19.917375622217044, failures=0, paired delta=-0.1160302058715911, SE=0.11274264571846006, retail delta=-0.11639306657160375, arb delta=0.0003628606988641536.",
    "fu5: P={'fu': 0.5, 'Hu': 1000}; spread 2 seeds 4004-5997, n=534, mean=79.77214770311686, retail=105.72747871624156, arb=-25.9553310131676, failures=0, paired delta=-0.08692021842378277, SE=0.20544816726688994, retail delta=0.10142155261871721, arb delta=-0.18834177104419325.",
    "risklow: P={'kLb': 0.16, 'kLf': 0.16}; spread 2 seeds 4004-4399, n=88, mean=107.92978602327729, retail=127.22880097292614, arb=-19.29901494967727, failures=0, paired delta=-0.0862553391352279, SE=0.5285073688692662, retail delta=-0.7049788723647765, arb delta=0.6187235332386365.",
    "pfl1: P={'pfl': 0.0001}; spread 2 seeds 4004-4399, n=88, mean=107.93606269358408, retail=127.85379894197386, arb=-19.917736248426134, failures=0, paired delta=-0.07997866882840912, SE=0.08280678885163997, retail delta=-0.07998090331705043, arb delta=2.2344897736559233e-06.",
    "dmin02: P={'dmin': 0.2}; spread 2 seeds 4004-4399, n=88, mean=107.94504420626932, retail=127.8188075697125, arb=-19.873763363479547, failures=0, paired delta=-0.07099715614318208, SE=0.1656403742252949, retail delta=-0.11497227557840972, arb delta=0.0439751194363609.",
    "xu05: P={'xu': 0.05}; spread 2 seeds 4004-4399, n=88, mean=107.97347997403182, retail=128.17445033664205, arb=-20.20097036265568, failures=0, paired delta=-0.042561388380682734, SE=0.3159010914771712, retail delta=0.24067049135113905, arb delta=-0.28323187973977326.",
    "g18: P={'g1': 8}; spread 2 seeds 4004-4399, n=88, mean=108.00130051282727, retail=127.91426652826931, arb=-19.912966015479547, failures=0, paired delta=-0.014740849585226328, SE=0.013883438165588128, retail delta=-0.019513317021605303, arb delta=0.004772467436360728.",
    "zd15: P={'zd': 1.5}; spread 2 seeds 4004-4399, n=88, mean=108.01528044438182, retail=127.93434381555909, arb=-19.919063371217046, failures=0, paired delta=-0.0007609180306817494, SE=0.021204629500714382, retail delta=0.0005639702681747849, arb delta=-0.001324888301137861.",
    "fu75: P={'fu': 0.75}; spread 2 seeds 4004-4399, n=88, mean=108.0160413624125, retail=127.93377984529091, arb=-19.917738482915908, failures=0, paired delta=0.0, SE=0.0, retail delta=0.0, arb delta=0.0.",
    "stockcap09: P={'f1': 0.9}; spread 2 seeds 4004-4399, n=88, mean=108.0160413624125, retail=127.93377984529091, arb=-19.917738482915908, failures=0, paired delta=0.0, SE=0.0, retail delta=0.0, arb delta=0.0.",
    "tickcap1: P={'qmax': 6000}, C={'bidcap': 3000, 'askcap': 3000, 'askcap1': 6000}; spread 2 seeds 4004-4399, n=88, mean=108.0160413624125, retail=127.93377984529091, arb=-19.917738482915908, failures=0, paired delta=0.0, SE=0.0, retail delta=0.0, arb delta=0.0.",
    "sigj25: P={'sig_j': 0.25}; spread 2 seeds 4004-4399, n=88, mean=108.02198493081364, retail=126.8601264747091, arb=-18.838141543898864, failures=0, paired delta=0.005943568401136922, SE=0.7062705355374828, retail delta=-1.073653370581809, arb delta=1.0795969390170441.",
    "hu1000: P={'Hu': 1000}; spread 2 seeds 4004-7998, n=1033, mean=79.27840689467067, retail=106.46929646621074, arb=-27.19088957157086, failures=0, paired delta=0.014747090198354408, SE=0.11638960179602384, retail delta=0.10030722670560976, arb delta=-0.08556013650706262.",
    "k08: P={'kA': 0.8}; spread 2 seeds 4004-5997, n=534, mean=79.87522393214944, retail=104.51219613974962, arb=-24.636972207629775, failures=0, paired delta=0.01615601060880138, SE=0.19346299765387318, retail delta=-1.113861023873227, arb delta=1.1300170344936333.",
    "zd2: P={'zd': 2}; spread 2 seeds 4004-4399, n=88, mean=108.04834919459546, retail=127.9693369392659, arb=-19.92098774470568, failures=0, paired delta=0.03230783218295429, SE=0.03314612468354218, retail delta=0.03555709397498674, arb delta=-0.003249261789772362.",
    "hu2000: P={'Hu': 2000}; spread 2 seeds 4004-4399, n=88, mean=108.05756725797728, retail=128.12692745893636, arb=-20.069360201001135, failures=0, paired delta=0.041525895564773485, SE=0.23937210151530436, retail delta=0.19314761364545063, arb delta=-0.15162171808522729.",
    "noammo: P={'ammo': 0}; spread 2 seeds 4004-4399, n=88, mean=108.06147132141136, retail=126.56447715232046, arb=-18.503005830955683, failures=0, paired delta=0.04542995899886353, SE=0.4917458094314465, retail delta=-1.3693026929704502, arb delta=1.4147326519602252.",
    "bins2: P={'bins': 2}; spread 2 seeds 4004-7998, n=1033, mean=79.31159016205847, retail=106.66639446948373, arb=-27.3548043074576, failures=0, paired delta=0.04793035758615722, SE=0.486219721192283, retail delta=0.2974052299786081, arb delta=-0.24947487239380095.",
    "bid1500: C={'bidcap': 1500}; spread 2 seeds 4004-4399, n=88, mean=108.0664429633659, retail=128.0310994091409, arb=-19.964656445806817, failures=0, paired delta=0.050401600953408086, SE=0.23052220494319267, retail delta=0.09731956384997886, arb delta=-0.04691796289090888.",
    "reserve100: C={'reserve': 100}; spread 2 seeds 4004-4399, n=88, mean=108.08076947711365, retail=127.98284276584091, arb=-19.90207328876477, failures=0, paired delta=0.06472811470113626, SE=0.047771714550837834, retail delta=0.049062920549999944, arb delta=0.01566519415113632.",
    "scar5: C={'scar': 0.005}; spread 2 seeds 4004-4399, n=88, mean=108.09173108011477, retail=127.74553557481931, arb=-19.653804494738637, failures=0, paired delta=0.0756897177022706, SE=0.18932244713398258, retail delta=-0.18824427047159986, arb delta=0.2639339881772713.",
    "g13: P={'g1': 3}; spread 2 seeds 4004-4399, n=88, mean=108.1079706331375, retail=128.02250389412046, arb=-19.91453326102159, failures=0, paired delta=0.09192927072499998, SE=0.08592573776778097, retail delta=0.08872404882954754, arb delta=0.0032052218943192656.",
    "uni05: P={'uni': 0.05}; spread 2 seeds 4004-4399, n=88, mean=108.20511861937274, retail=127.94666209973296, arb=-19.74154348039318, failures=0, paired delta=0.18907725696022631, SE=0.6108949182883872, retail delta=0.01288225444204727, arb delta=0.17619500252272857.",
    "lowcombo: P={'ammo': 0, 'kLf': 0.3}, mid-price ask risk x2; spread 2 seeds 4004-7998, n=1033, mean=79.46506176983814, retail=100.94016958648402, arb=-21.475107816679284, failures=0, paired delta=0.20140196536582802, SE=0.7239467643099627, retail delta=-5.428819653021108, arb delta=5.630221618384514.",
    "noammo: P={'ammo': 0}; spread 2 seeds 4004-5997, n=534, mean=80.07736898446872, retail=104.55593012362078, arb=-24.478561139192696, failures=0, paired delta=0.2183010629280901, SE=0.22382542005341358, retail delta=-1.0701270400020633, arb delta=1.2884281029307125.",
    "fu5: P={'fu': 0.5, 'Hu': 1000}; spread 2 seeds 4004-4399, n=88, mean=108.26324796999091, retail=128.18149051022272, arb=-19.918242540270455, failures=0, paired delta=0.2472066075784091, SE=0.12258940995211189, retail delta=0.24771066493180172, arb delta=-0.0005040573545471716.",
    "hu1000: P={'Hu': 1000}; spread 2 seeds 4004-4399, n=88, mean=108.26324796999091, retail=128.18149051022272, arb=-19.918242540270455, failures=0, paired delta=0.2472066075784091, SE=0.12258940995211189, retail delta=0.24771066493180172, arb delta=-0.0005040573545471716.",
    "scar5: C={'scar': 0.005}; spread 2 seeds 4004-7998, n=1033, mean=79.52568576835344, retail=106.13894644379555, arb=-26.613260675474926, failures=0, paired delta=0.2620259638811226, SE=0.12971175263419865, retail delta=-0.2300427957095792, arb delta=0.49206875958887153.",
    "bins4: P={'bins': 4}; spread 2 seeds 4004-7998, n=1033, mean=79.6330092079907, retail=106.41911389327231, arb=-26.78610468531975, failures=0, paired delta=0.36934940351839346, SE=0.13261666710303976, retail delta=0.05012465376718467, arb delta=0.31922474974404835.",
    "ask6000: P={'qmax': 6000}, C={'bidcap': 3000}; spread 2 seeds 4004-5997, n=534, mean=80.25575787249026, retail=106.1327914181, arb=-25.877033545651496, failures=0, paired delta=0.39668995094962495, SE=0.14698613245773018, retail delta=0.506734254477152, arb delta=-0.11004430352808825.",
    "bins4scar5: P={'bins': 4}, C={'scar': 0.005}; spread 2 seeds 4004-7998, n=1033, mean=79.8666537341759, retail=106.1773928345394, arb=-26.310739100402323, failures=0, paired delta=0.602993929703582, SE=0.18172811290909321, retail delta=-0.19159640496572194, arb delta=0.7945903346614749. Completed after freeze; not used for selection.",
    "bins4: P={'bins': 4}; spread 2 seeds 4004-4399, n=88, mean=108.63804393970113, retail=127.81057481866932, arb=-19.172530878981817, failures=0, paired delta=0.6220025772886373, SE=0.35461639305597903, retail delta=-0.12320502662159072, arb delta=0.7452076039340909.",
    "lamj10: P={'lam_j': 0.001}; spread 2 seeds 4004-4399, n=88, mean=108.64290676477044, retail=128.03579358947954, arb=-19.39288682472159, failures=0, paired delta=0.6268654023579544, SE=0.5959829765752978, retail delta=0.10201374418862486, arb delta=0.5248516581943186.",
    "ask4500: P={'qmax': 4500}, C={'bidcap': 3000}; spread 2 seeds 4004-4399, n=88, mean=108.68996035497047, retail=128.7215509867841, arb=-20.031590631851138, failures=0, paired delta=0.6739189925579538, SE=0.35422254456699714, retail delta=0.7877711414931952, arb delta=-0.11385214893522999.",
    "ask6000: P={'qmax': 6000}, C={'bidcap': 3000}; spread 2 seeds 4004-4399, n=88, mean=109.24235716065, retail=129.42351235836705, arb=-20.181155197755682, failures=0, paired delta=1.226315798237499, SE=0.7384489918903222, retail delta=1.4897325130761345, arb delta=-0.26341671483977436.",
    "q6000: P={'qmax': 6000}, C={'bidcap': 6000}; spread 2 seeds 4004-4399, n=88, mean=109.30053778785114, retail=129.48200949034887, arb=-20.1814717025375, failures=0, paired delta=1.2844964254386355, SE=0.7401952338382638, retail delta=1.5482296450579582, arb delta=-0.26373321962159224.",
    "ask10000: P={'qmax': 10000}, C={'bidcap': 3000}; spread 2 seeds 4004-4399, n=88, mean=109.39162283870569, retail=129.55762716459205, arb=-20.166004325926135, failures=0, paired delta=1.3755814762931813, SE=0.9477011360914213, retail delta=1.6238473193011345, arb delta=-0.24826584301022692.",
    "Frozen bins4 at 2026-11-06T03:00:09.604699+00:00, SHA-256 99d6ea7cf785661315df84c874ac4578158c1b373bb5a76b5d4fc0e2c537ffb6; final complete training and unseen batches run without subsequent selection or edits. Non-spread-2 full per-run dictionaries exactly equal base: 435/600 scorer-check runs, 2967/4000 training runs, 3002/4000 holdout runs.",
    "Full training batch restarted after its initial launch overlapped freeze completion; the restarted batch loaded the verified frozen file. No partial score was retained. The unseen candidate batch was run once.",
    "Incomplete exploratory training batches (no complete score claimed): tickcap1, tickcap2, tickcaps, ask6hu1, ask6bins4, ask10000, kl04, ask6scar5. Stopped exploratory batches to reserve time for the mandatory full-file training, unseen and equality checks. Completed screening scores remain reported; no partial batch scores are claimed.",
    "Selected best validated policy, kept only after both disjoint training blocks gained: 4000-5999: n=534, paired gain=0.35492505114007544, SE=0.1428747219149962, retail delta=0.09455952366198517, arb delta=0.26036552746385766; 6000-7999: n=499, paired gain=0.3847854840194393, SE=0.2281810073749437, retail delta=0.002573109631256898, arb delta=0.3822123743885726. Whole-file training gain=0.09538448345862512, SE=0.03433125555849978; unseen whole-file gain=0.026186278869049916, SE=0.028480053439220766."
  ],
  "next": "The unseen difference does not exceed two paired standard errors; this item alone is not sufficient evidence to fund a wider constants search. The additive contribution is the spread-2 branch only; copy its reported overrides into the base after self.s inference, using instance-local parameter dictionaries. Combine with the other spread items and assess the aggregate paired gain before funding a wide search. The 50000-53999 holdout is now used and must not become a tuning set. Test any further numerical-grid/scarcity interaction or quoting table on a fresh seed range; judge retail and arbitrage effects separately and retain rare-jump losses."
}