{
 "notes": "EP8: woke on requester note 7 (gate A on recorded replica callbacks, word for word in every T03 brief; restart the T03 batons; T03's code stays unless a guard changes no real-engine edge). Handed 30: 6 new (t4-b/m06, m09; t4-d/m19, m20; t4-e/m21; dz-t03/dz-b), 24 old.\n\nLEARNED.\n1. EP7's capped gate A failed two ways: m06 capped at 15% (not 2%) and hit T03's Panic(0x12); m19 and m21 (2% cap, spot in [25,400]) saw 0.195 and 0.251 bps port-vs-EVM drift on a few sequences near the spot bounds; m09 (spot kept near its start) passed at 0.0012 bps, 0 reverts. The drift lives at synthetic extremes, as note 7 says. m09 (85 markets/s, 8 CPUs with no pool speedup) ran T03 vs IB on 384 fresh seeds 8129024..: +0.754 se 0.042. 0 of 5 t4 results trained; 20 t4 items still run EP7's brief and will mostly block.\n2. dz-b: the culprit is _band's acc[0] (sum of 7 quadrature-node likelihoods) at T03.sol line 462, zero only when every node z exceeds about 5e8 (spot 2.25e8, fastHat about 141, reserve X drained to 0.067); canonical acc[0] min 4.5e-4 on 512 replica markets. T03G = T03 plus one line `if (acc[0] == 0) return (mu, v);`: identical to T03 per seed on 256 real seeds (max abs diff 0.0), peak 235,575 both, 0 OOG, gate C 0.0003 bps. T03G code sha256 26c960d885b46eec181dd12edf56c6bd0a6696e41f81a163028029481c005e85, in dz-b's result (id badeca3a082ac0c48f60c71720189012bf824b0b22d474aeac0f2b967e420cb8, served; no params or port in it). Per note 7 T03 ships unchanged; T03G is the no-edge guard, the requester's to adopt.\n3. k20 (t3-d/k20-s04-h60-p16; id b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9, fetched, hash equal): our first trained T03 child and a complete START (code 1be16eb8..., params with constants as name: value, port_zb64 572bb0e6..., layout in its notes). 196 generations in 62 min (216 markets/s, M 256, sigma0 0.4, half 60, 0.03 rms / 2^(0.02 z)). Holdout 41030000..+8191: +0.021 se 0.004 over T03, +0.789 se 0.010 over IB. Real 8116736..8116991 (n 256): +0.797 se 0.052 over IB, +0.022 se 0.021 over T03; peak 235,406, 0 OOG. The second start.\n4. j5 line: j15 +0.679, j07 +0.669, j18 +0.661 real over IB (n 512 each): about 0.15 behind T03. Parked.\n5. T03 vs IB real: +0.819 (n 1,024), +0.7725 (t03-block-b, n 1,024), +0.754 (m09, n 384), +0.775 (k20's start arm, n 256): about +0.78 on 2,688 seeds.\n\nDECIDED (25 items; 163 of 200 used at most). Round 4: t5-a..t5-e (5 each), keys nNN-sS-hHH-pPP (sigma0 0.S, cap half-life HH min, population PP). n01..n15 START = k09's URL (3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475 = T03), n16..n25 START = k20's URL. TEMPLATE below with notes 3, 6, 7's sentences word for word; gate A = recorded replica callbacks (50 markets, seeds 9200000..9200049, first 2,000 each, replayed in the EVM and the port, < 0.01 bps); gate C the same on 9200100..9200149, < 0.1 bps; gate B 'START minus IB on replica seeds 8588000..8589023 within 0.15 of the real +0.819' (T03; replica gives +0.769) or '8116736..8116991 ... +0.797' (k20); note 4's parameterization (0.05 rms, 2^(0.03 z)); sigma0 0.3..0.7, half-lives 45..90, population 16 (24 on n04, n09, n20, n25); holdout 41070000..41078191 shared by the round, frozen, START and IB arms; real = IB and frozen on 512 fresh seeds (256 under 300 markets/s), START if time remains; under 100 markets/s IB and START on 1,024. Filled brief 2,985 characters (limit 3,000). Not cancelled: t3-a..d (12 running), t4-a..e (20), j11-a (2), dz-t03 (1): cancel frees nothing once items run.\nREAD: the 25 t5 legs and dz-t03/dz-a. Wake: the five t5 batches or 150 minutes.\n\nLEDGER, never reuse. Real engine, 1,024-seed blocks: below 8148480 taken; nNN 8148480+1024(NN-1), NN 01..25; next free 8174080; confirm-t03 8700000..8702047; T03's own 8588000..8589023. Replica train: nNN 600000000+8000000(NN-1), 8,000,000 seeds each (600000000..800000000 taken; earlier 500000000..516000000 and 900000000..1360000000; the sister goal uses 1400000000 up); next free 800000000. Gate A/C recording 9200000..9200149. Holdout: round 4 41070000..41078191; round 5 41090000..+8191. Monitor 30000000..30002047 reused on purpose. ES seeds used: up to 20261425 and 20261501..20261525.\n\nNEXT EPISODE (9 of 10; 37 items left).\n1. Per leg: blocked, replica_only, speed, cpus, M, generations, minutes, gates. Legs blocking at the recorded-callback gate A mean a real port/EVM mismatch at market ranges: read the first divergence and do not relay from that START until explained. Late t4/t3 legs (START T03, holdouts 41050000 or 41030000) rank by frozen_vs_start.\n2. Rank by holdout frozen_vs_IB (se about 0.010; same seeds across the round) and frozen_vs_start; check real frozen_vs_IB (se about 0.04) agrees, valid true, peak <= 245,000, 0 reverts. A replica_only leg ranks by holdout frozen_vs_start only: spawn a Linux freeze item (CAND = the leg's URL: freeze its params into its START's Solidity, gates A (recorded) and C, holdout 41090000, IB and frozen on 512 fresh seeds; the result is a START).\n3. Confirm the best leg vs IB on two fresh 1,024-seed blocks from 8174080 (the confirm-t03 brief with CAND = the leg's URL and code sha256; a T03 arm when time allows); promote at > 2 se over IB; a file >= +0.3 over IB on 2,048 seeds goes to the requester with complete code and sha256.\n4. With the items left (about 30 after step 3), a last round from the best leg (TEMPLATE; holdout 41090000; sigma0 near its final sigma; half 60..90) in batches of 5; EP10 finishes from what has landed.\n5. Write-up: the final file's URL, code and sha256, paired real gain over IB {n, mean_diff, se, worst5, best5}, quartiles, volume deltas, gas, the curve by round (IB 0, J5 +0.55, J11 +0.60, T03 +0.78, k20 +0.80 at n 256, round 4's best), the gate A story (synthetic stress, T03G), the seat mix, what was not checked.\n\nTEMPLATE (t5 leg; vars start, bseeds, bref, esseed, pop, sigma, half, train, real; N3, N6, N7 = requester notes 3, 6, 7's quoted sentences):\nOne relay leg; the next starts from your result. Follow the goal's objective and: 'N3' 'N6' 'N7'\nFILES (check sha256s). START = https://api.imd.fun/artifacts/{{start}}: `code_zb64`, `params`, `port_zb64` (W layout in its `notes`).\n1. SETUP; fetch the files.\n2. Gate A: record the first 2,000 afterSwap callbacks of 50 replica markets (START's port, seeds 9200000..9200049); replay them in the EVM on START's Solidity and on the port, < 0.01 bps. Gate B: START minus IB on replica seeds {{bseeds}} within 0.15 of the real {{bref}}. S = replica markets/s, warmed pool. A failed gate: no search, blocked={step,error}. S < 100: only step 6, IB and START, {{real}}..+1023.\n3. CMA-ES over 219 z, z = 0 at START: weight = start + 0.05 rms(its block) z; constant = start 2^(0.03 z), integers rounded. ES seed {{esseed}}, population {{pop}}, sigma0 {{sigma}} capped at sigma0 x 0.5^(minutes/{{half}}). Each generation scores the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean vs START on seeds 30000000..30002047; keep the best. Stop 30 minutes before your time ends, 45 if S < 300.\n4. Freeze the best point into START's Solidity, only its literals (weights 1e-6, constants WAD). Gate C: as A on the frozen file, seeds 9200100..9200149, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41070000..41078191.\n6. REAL ENGINE: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300), 64-seed commands; START too if time remains.\nRESULT, one JSON object, START's keys: blocked; gates (max bps, reverts, stress); speed; search{generations,minutes,M,curve [minutes, gain, se, sigma]}; params; code_zb64, code_sha256; port_zb64, port_sha256; holdout and real: frozen_vs_start, frozen_vs_IB, start_vs_IB (n, mean_diff, se; real also sum, sumsq, worst5, by_quartile); gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak > 245,000). If nothing beat START, say so.",
 "spawn": [
  {
   "name": "t5-a",
   "brief": "One relay leg; the next starts from your result. Follow the goal's objective and: 'This overrides the objective's 300 markets/s rule: search at any replica speed of at least 100 markets/s, with 256-market blocks below 300 markets/s, for the full time; only below 100 markets/s skip the search and do confirmations or kit work.' 'If the Linux setup fails on this machine, take the replica-only branch: set R=\"$PWD/scratch\" and quote every path; download https://github.com/astral-sh/uv/releases/latest/download/uv-aarch64-apple-darwin.tar.gz, extract it under \"$R\" and use that uv; run uv venv --python 3.12 \"$R/venv\" and uv pip install numpy numba cma; run the CMA search on the replica from the starting file's port and frozen params for the full time; return the trained params, the curve and the replica holdout gain over the start, marked replica_only, without freezing to Solidity or running the real engine.' 'Run gate A on callback sequences recorded from replica market runs (at least 50 markets of 2,000 callbacks); report any synthetic stress sequences separately and do not block on them.'\nFILES (check sha256s). START = https://api.imd.fun/artifacts/{{start}}: `code_zb64`, `params`, `port_zb64` (W layout in its `notes`).\n1. SETUP; fetch the files.\n2. Gate A: record the first 2,000 afterSwap callbacks of 50 replica markets (START's port, seeds 9200000..9200049); replay them in the EVM on START's Solidity and on the port, < 0.01 bps. Gate B: START minus IB on replica seeds {{bseeds}} within 0.15 of the real {{bref}}. S = replica markets/s, warmed pool. A failed gate: no search, blocked={step,error}. S < 100: only step 6, IB and START, {{real}}..+1023.\n3. CMA-ES over 219 z, z = 0 at START: weight = start + 0.05 rms(its block) z; constant = start 2^(0.03 z), integers rounded. ES seed {{esseed}}, population {{pop}}, sigma0 {{sigma}} capped at sigma0 x 0.5^(minutes/{{half}}). Each generation scores the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean vs START on seeds 30000000..30002047; keep the best. Stop 30 minutes before your time ends, 45 if S < 300.\n4. Freeze the best point into START's Solidity, only its literals (weights 1e-6, constants WAD). Gate C: as A on the frozen file, seeds 9200100..9200149, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41070000..41078191.\n6. REAL ENGINE: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300), 64-seed commands; START too if time remains.\nRESULT, one JSON object, START's keys: blocked; gates (max bps, reverts, stress); speed; search{generations,minutes,M,curve [minutes, gain, se, sigma]}; params; code_zb64, code_sha256; port_zb64, port_sha256; holdout and real: frozen_vs_start, frozen_vs_IB, start_vs_IB (n, mean_diff, se; real also sum, sumsq, worst5, by_quartile); gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak > 245,000). If nothing beat START, say so.",
   "items": [
    {
     "key": "n01-s05-h60-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261501",
      "pop": "16",
      "sigma": "0.5",
      "half": "60",
      "train": "600000000",
      "real": "8148480",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n02-s07-h45-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261502",
      "pop": "16",
      "sigma": "0.7",
      "half": "45",
      "train": "608000000",
      "real": "8149504",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n03-s04-h90-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261503",
      "pop": "16",
      "sigma": "0.4",
      "half": "90",
      "train": "616000000",
      "real": "8150528",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n04-s05-h45-p24",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261504",
      "pop": "24",
      "sigma": "0.5",
      "half": "45",
      "train": "624000000",
      "real": "8151552",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n05-s03-h60-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261505",
      "pop": "16",
      "sigma": "0.3",
      "half": "60",
      "train": "632000000",
      "real": "8152576",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 5,
    "brief": "Hand each item's result as it is: each is a relay START. If a merge is made, list per item: key, blocked, replica_only, speed, generations, holdout frozen_vs_start and frozen_vs_IB, real frozen_vs_IB, valid, code_sha256."
   }
  },
  {
   "name": "t5-b",
   "brief": "One relay leg; the next starts from your result. Follow the goal's objective and: 'This overrides the objective's 300 markets/s rule: search at any replica speed of at least 100 markets/s, with 256-market blocks below 300 markets/s, for the full time; only below 100 markets/s skip the search and do confirmations or kit work.' 'If the Linux setup fails on this machine, take the replica-only branch: set R=\"$PWD/scratch\" and quote every path; download https://github.com/astral-sh/uv/releases/latest/download/uv-aarch64-apple-darwin.tar.gz, extract it under \"$R\" and use that uv; run uv venv --python 3.12 \"$R/venv\" and uv pip install numpy numba cma; run the CMA search on the replica from the starting file's port and frozen params for the full time; return the trained params, the curve and the replica holdout gain over the start, marked replica_only, without freezing to Solidity or running the real engine.' 'Run gate A on callback sequences recorded from replica market runs (at least 50 markets of 2,000 callbacks); report any synthetic stress sequences separately and do not block on them.'\nFILES (check sha256s). START = https://api.imd.fun/artifacts/{{start}}: `code_zb64`, `params`, `port_zb64` (W layout in its `notes`).\n1. SETUP; fetch the files.\n2. Gate A: record the first 2,000 afterSwap callbacks of 50 replica markets (START's port, seeds 9200000..9200049); replay them in the EVM on START's Solidity and on the port, < 0.01 bps. Gate B: START minus IB on replica seeds {{bseeds}} within 0.15 of the real {{bref}}. S = replica markets/s, warmed pool. A failed gate: no search, blocked={step,error}. S < 100: only step 6, IB and START, {{real}}..+1023.\n3. CMA-ES over 219 z, z = 0 at START: weight = start + 0.05 rms(its block) z; constant = start 2^(0.03 z), integers rounded. ES seed {{esseed}}, population {{pop}}, sigma0 {{sigma}} capped at sigma0 x 0.5^(minutes/{{half}}). Each generation scores the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean vs START on seeds 30000000..30002047; keep the best. Stop 30 minutes before your time ends, 45 if S < 300.\n4. Freeze the best point into START's Solidity, only its literals (weights 1e-6, constants WAD). Gate C: as A on the frozen file, seeds 9200100..9200149, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41070000..41078191.\n6. REAL ENGINE: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300), 64-seed commands; START too if time remains.\nRESULT, one JSON object, START's keys: blocked; gates (max bps, reverts, stress); speed; search{generations,minutes,M,curve [minutes, gain, se, sigma]}; params; code_zb64, code_sha256; port_zb64, port_sha256; holdout and real: frozen_vs_start, frozen_vs_IB, start_vs_IB (n, mean_diff, se; real also sum, sumsq, worst5, by_quartile); gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak > 245,000). If nothing beat START, say so.",
   "items": [
    {
     "key": "n06-s07-h60-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261506",
      "pop": "16",
      "sigma": "0.7",
      "half": "60",
      "train": "640000000",
      "real": "8153600",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n07-s05-h90-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261507",
      "pop": "16",
      "sigma": "0.5",
      "half": "90",
      "train": "648000000",
      "real": "8154624",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n08-s04-h45-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261508",
      "pop": "16",
      "sigma": "0.4",
      "half": "45",
      "train": "656000000",
      "real": "8155648",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n09-s06-h60-p24",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261509",
      "pop": "24",
      "sigma": "0.6",
      "half": "60",
      "train": "664000000",
      "real": "8156672",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n10-s05-h60-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261510",
      "pop": "16",
      "sigma": "0.5",
      "half": "60",
      "train": "672000000",
      "real": "8157696",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 5,
    "brief": "Hand each item's result as it is: each is a relay START. If a merge is made, list per item: key, blocked, replica_only, speed, generations, holdout frozen_vs_start and frozen_vs_IB, real frozen_vs_IB, valid, code_sha256."
   }
  },
  {
   "name": "t5-c",
   "brief": "One relay leg; the next starts from your result. Follow the goal's objective and: 'This overrides the objective's 300 markets/s rule: search at any replica speed of at least 100 markets/s, with 256-market blocks below 300 markets/s, for the full time; only below 100 markets/s skip the search and do confirmations or kit work.' 'If the Linux setup fails on this machine, take the replica-only branch: set R=\"$PWD/scratch\" and quote every path; download https://github.com/astral-sh/uv/releases/latest/download/uv-aarch64-apple-darwin.tar.gz, extract it under \"$R\" and use that uv; run uv venv --python 3.12 \"$R/venv\" and uv pip install numpy numba cma; run the CMA search on the replica from the starting file's port and frozen params for the full time; return the trained params, the curve and the replica holdout gain over the start, marked replica_only, without freezing to Solidity or running the real engine.' 'Run gate A on callback sequences recorded from replica market runs (at least 50 markets of 2,000 callbacks); report any synthetic stress sequences separately and do not block on them.'\nFILES (check sha256s). START = https://api.imd.fun/artifacts/{{start}}: `code_zb64`, `params`, `port_zb64` (W layout in its `notes`).\n1. SETUP; fetch the files.\n2. Gate A: record the first 2,000 afterSwap callbacks of 50 replica markets (START's port, seeds 9200000..9200049); replay them in the EVM on START's Solidity and on the port, < 0.01 bps. Gate B: START minus IB on replica seeds {{bseeds}} within 0.15 of the real {{bref}}. S = replica markets/s, warmed pool. A failed gate: no search, blocked={step,error}. S < 100: only step 6, IB and START, {{real}}..+1023.\n3. CMA-ES over 219 z, z = 0 at START: weight = start + 0.05 rms(its block) z; constant = start 2^(0.03 z), integers rounded. ES seed {{esseed}}, population {{pop}}, sigma0 {{sigma}} capped at sigma0 x 0.5^(minutes/{{half}}). Each generation scores the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean vs START on seeds 30000000..30002047; keep the best. Stop 30 minutes before your time ends, 45 if S < 300.\n4. Freeze the best point into START's Solidity, only its literals (weights 1e-6, constants WAD). Gate C: as A on the frozen file, seeds 9200100..9200149, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41070000..41078191.\n6. REAL ENGINE: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300), 64-seed commands; START too if time remains.\nRESULT, one JSON object, START's keys: blocked; gates (max bps, reverts, stress); speed; search{generations,minutes,M,curve [minutes, gain, se, sigma]}; params; code_zb64, code_sha256; port_zb64, port_sha256; holdout and real: frozen_vs_start, frozen_vs_IB, start_vs_IB (n, mean_diff, se; real also sum, sumsq, worst5, by_quartile); gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak > 245,000). If nothing beat START, say so.",
   "items": [
    {
     "key": "n11-s07-h45-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261511",
      "pop": "16",
      "sigma": "0.7",
      "half": "45",
      "train": "680000000",
      "real": "8158720",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n12-s04-h60-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261512",
      "pop": "16",
      "sigma": "0.4",
      "half": "60",
      "train": "688000000",
      "real": "8159744",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n13-s05-h75-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261513",
      "pop": "16",
      "sigma": "0.5",
      "half": "75",
      "train": "696000000",
      "real": "8160768",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n14-s06-h45-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261514",
      "pop": "16",
      "sigma": "0.6",
      "half": "45",
      "train": "704000000",
      "real": "8161792",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    },
    {
     "key": "n15-s03-h90-p16",
     "vars": {
      "start": "3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475",
      "esseed": "20261515",
      "pop": "16",
      "sigma": "0.3",
      "half": "90",
      "train": "712000000",
      "real": "8162816",
      "bseeds": "8588000..8589023",
      "bref": "+0.819"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 5,
    "brief": "Hand each item's result as it is: each is a relay START. If a merge is made, list per item: key, blocked, replica_only, speed, generations, holdout frozen_vs_start and frozen_vs_IB, real frozen_vs_IB, valid, code_sha256."
   }
  },
  {
   "name": "t5-d",
   "brief": "One relay leg; the next starts from your result. Follow the goal's objective and: 'This overrides the objective's 300 markets/s rule: search at any replica speed of at least 100 markets/s, with 256-market blocks below 300 markets/s, for the full time; only below 100 markets/s skip the search and do confirmations or kit work.' 'If the Linux setup fails on this machine, take the replica-only branch: set R=\"$PWD/scratch\" and quote every path; download https://github.com/astral-sh/uv/releases/latest/download/uv-aarch64-apple-darwin.tar.gz, extract it under \"$R\" and use that uv; run uv venv --python 3.12 \"$R/venv\" and uv pip install numpy numba cma; run the CMA search on the replica from the starting file's port and frozen params for the full time; return the trained params, the curve and the replica holdout gain over the start, marked replica_only, without freezing to Solidity or running the real engine.' 'Run gate A on callback sequences recorded from replica market runs (at least 50 markets of 2,000 callbacks); report any synthetic stress sequences separately and do not block on them.'\nFILES (check sha256s). START = https://api.imd.fun/artifacts/{{start}}: `code_zb64`, `params`, `port_zb64` (W layout in its `notes`).\n1. SETUP; fetch the files.\n2. Gate A: record the first 2,000 afterSwap callbacks of 50 replica markets (START's port, seeds 9200000..9200049); replay them in the EVM on START's Solidity and on the port, < 0.01 bps. Gate B: START minus IB on replica seeds {{bseeds}} within 0.15 of the real {{bref}}. S = replica markets/s, warmed pool. A failed gate: no search, blocked={step,error}. S < 100: only step 6, IB and START, {{real}}..+1023.\n3. CMA-ES over 219 z, z = 0 at START: weight = start + 0.05 rms(its block) z; constant = start 2^(0.03 z), integers rounded. ES seed {{esseed}}, population {{pop}}, sigma0 {{sigma}} capped at sigma0 x 0.5^(minutes/{{half}}). Each generation scores the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean vs START on seeds 30000000..30002047; keep the best. Stop 30 minutes before your time ends, 45 if S < 300.\n4. Freeze the best point into START's Solidity, only its literals (weights 1e-6, constants WAD). Gate C: as A on the frozen file, seeds 9200100..9200149, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41070000..41078191.\n6. REAL ENGINE: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300), 64-seed commands; START too if time remains.\nRESULT, one JSON object, START's keys: blocked; gates (max bps, reverts, stress); speed; search{generations,minutes,M,curve [minutes, gain, se, sigma]}; params; code_zb64, code_sha256; port_zb64, port_sha256; holdout and real: frozen_vs_start, frozen_vs_IB, start_vs_IB (n, mean_diff, se; real also sum, sumsq, worst5, by_quartile); gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak > 245,000). If nothing beat START, say so.",
   "items": [
    {
     "key": "n16-s03-h60-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261516",
      "pop": "16",
      "sigma": "0.3",
      "half": "60",
      "train": "720000000",
      "real": "8163840",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n17-s04-h60-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261517",
      "pop": "16",
      "sigma": "0.4",
      "half": "60",
      "train": "728000000",
      "real": "8164864",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n18-s05-h45-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261518",
      "pop": "16",
      "sigma": "0.5",
      "half": "45",
      "train": "736000000",
      "real": "8165888",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n19-s03-h90-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261519",
      "pop": "16",
      "sigma": "0.3",
      "half": "90",
      "train": "744000000",
      "real": "8166912",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n20-s04-h45-p24",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261520",
      "pop": "24",
      "sigma": "0.4",
      "half": "45",
      "train": "752000000",
      "real": "8167936",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 5,
    "brief": "Hand each item's result as it is: each is a relay START. If a merge is made, list per item: key, blocked, replica_only, speed, generations, holdout frozen_vs_start and frozen_vs_IB, real frozen_vs_IB, valid, code_sha256."
   }
  },
  {
   "name": "t5-e",
   "brief": "One relay leg; the next starts from your result. Follow the goal's objective and: 'This overrides the objective's 300 markets/s rule: search at any replica speed of at least 100 markets/s, with 256-market blocks below 300 markets/s, for the full time; only below 100 markets/s skip the search and do confirmations or kit work.' 'If the Linux setup fails on this machine, take the replica-only branch: set R=\"$PWD/scratch\" and quote every path; download https://github.com/astral-sh/uv/releases/latest/download/uv-aarch64-apple-darwin.tar.gz, extract it under \"$R\" and use that uv; run uv venv --python 3.12 \"$R/venv\" and uv pip install numpy numba cma; run the CMA search on the replica from the starting file's port and frozen params for the full time; return the trained params, the curve and the replica holdout gain over the start, marked replica_only, without freezing to Solidity or running the real engine.' 'Run gate A on callback sequences recorded from replica market runs (at least 50 markets of 2,000 callbacks); report any synthetic stress sequences separately and do not block on them.'\nFILES (check sha256s). START = https://api.imd.fun/artifacts/{{start}}: `code_zb64`, `params`, `port_zb64` (W layout in its `notes`).\n1. SETUP; fetch the files.\n2. Gate A: record the first 2,000 afterSwap callbacks of 50 replica markets (START's port, seeds 9200000..9200049); replay them in the EVM on START's Solidity and on the port, < 0.01 bps. Gate B: START minus IB on replica seeds {{bseeds}} within 0.15 of the real {{bref}}. S = replica markets/s, warmed pool. A failed gate: no search, blocked={step,error}. S < 100: only step 6, IB and START, {{real}}..+1023.\n3. CMA-ES over 219 z, z = 0 at START: weight = start + 0.05 rms(its block) z; constant = start 2^(0.03 z), integers rounded. ES seed {{esseed}}, population {{pop}}, sigma0 {{sigma}} capped at sigma0 x 0.5^(minutes/{{half}}). Each generation scores the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean vs START on seeds 30000000..30002047; keep the best. Stop 30 minutes before your time ends, 45 if S < 300.\n4. Freeze the best point into START's Solidity, only its literals (weights 1e-6, constants WAD). Gate C: as A on the frozen file, seeds 9200100..9200149, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41070000..41078191.\n6. REAL ENGINE: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300), 64-seed commands; START too if time remains.\nRESULT, one JSON object, START's keys: blocked; gates (max bps, reverts, stress); speed; search{generations,minutes,M,curve [minutes, gain, se, sigma]}; params; code_zb64, code_sha256; port_zb64, port_sha256; holdout and real: frozen_vs_start, frozen_vs_IB, start_vs_IB (n, mean_diff, se; real also sum, sumsq, worst5, by_quartile); gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak > 245,000). If nothing beat START, say so.",
   "items": [
    {
     "key": "n21-s05-h60-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261521",
      "pop": "16",
      "sigma": "0.5",
      "half": "60",
      "train": "760000000",
      "real": "8168960",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n22-s04-h75-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261522",
      "pop": "16",
      "sigma": "0.4",
      "half": "75",
      "train": "768000000",
      "real": "8169984",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n23-s03-h45-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261523",
      "pop": "16",
      "sigma": "0.3",
      "half": "45",
      "train": "776000000",
      "real": "8171008",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n24-s06-h60-p16",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261524",
      "pop": "16",
      "sigma": "0.6",
      "half": "60",
      "train": "784000000",
      "real": "8172032",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    },
    {
     "key": "n25-s04-h60-p24",
     "vars": {
      "start": "b4669de39651a7498c2a914e1d59ff8c4e16fe6cff54fb1a1ef8d288b9e202d9",
      "esseed": "20261525",
      "pop": "24",
      "sigma": "0.4",
      "half": "60",
      "train": "792000000",
      "real": "8173056",
      "bseeds": "8116736..8116991",
      "bref": "+0.797"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 5,
    "brief": "Hand each item's result as it is: each is a relay START. If a merge is made, list per item: key, blocked, replica_only, speed, generations, holdout frozen_vs_start and frozen_vs_IB, real frozen_vs_IB, valid, code_sha256."
   }
  }
 ],
 "read": [
  "t5-a/n01-s05-h60-p16",
  "t5-a/n02-s07-h45-p16",
  "t5-a/n03-s04-h90-p16",
  "t5-a/n04-s05-h45-p24",
  "t5-a/n05-s03-h60-p16",
  "t5-b/n06-s07-h60-p16",
  "t5-b/n07-s05-h90-p16",
  "t5-b/n08-s04-h45-p16",
  "t5-b/n09-s06-h60-p24",
  "t5-b/n10-s05-h60-p16",
  "t5-c/n11-s07-h45-p16",
  "t5-c/n12-s04-h60-p16",
  "t5-c/n13-s05-h75-p16",
  "t5-c/n14-s06-h45-p16",
  "t5-c/n15-s03-h90-p16",
  "t5-d/n16-s03-h60-p16",
  "t5-d/n17-s04-h60-p16",
  "t5-d/n18-s05-h45-p16",
  "t5-d/n19-s03-h90-p16",
  "t5-d/n20-s04-h45-p24",
  "t5-e/n21-s05-h60-p16",
  "t5-e/n22-s04-h75-p16",
  "t5-e/n23-s03-h45-p16",
  "t5-e/n24-s06-h60-p16",
  "t5-e/n25-s04-h60-p24",
  "dz-t03/dz-a"
 ],
 "cancel": [],
 "wake": {
  "batches": [
   "t5-a",
   "t5-b",
   "t5-c",
   "t5-d",
   "t5-e"
  ],
  "afterMinutes": 150
 },
 "finish": false
}