{
 "notes": "EP7: woke on requester note 6 (T03 confirmed and the baton; note 6's macOS sentence word for word in every training brief; a Linux item freezes each replica_only result). With note 3's and note 6's sentences (830 characters) a leg brief has about 2,100 for the rest. Handed 30 results, 21 old (EP4's head-only IG/IB/FA legs: +0.01..0.06 over their start per leg, all 0.5 below T03; no line any more). New: 7 of 20 t3 legs, confirm-t03/t03-block-b, j5-a/j01.\n\nLEARNED.\n1. T03 FAILS THE OLD GATE A. Five Linux t3 legs (k03, k09, k12, k17, k18) blocked there: T03's afterSwap reverts with Panic(0x12), division by zero, on a synthetic stress path of the EVM-against-port harness (reserves 100/10000, lognormal X amounts up to 15% of the reserve): at reserve X 0.0666, Y 15,007,537 after 1,223 callbacks (harness seeds 440103+, sequence 42; the state is in the dz brief and k09's result); seeds 310000+ hit it too, plus a 0.014 bps drift on a non-reverting sequence. Canonical-range sequences were < 0.0013 bps. T03's real engine is clean: confirm-t03/t03-block-b +0.7725 se 0.024 over IB on 8701024..8702047 (quartiles +0.76/+0.78/+0.77/+0.78; peak 237,689; 0 OOG, 0 reverts in 11 million calls); about +0.78 over IB on 2,048 with T03's own block: confirmed >= +0.3 (code sha256 cb6d9455...). The gate, not the file, blocks the relay; the 13 t3 legs still running will mostly block too. J5's Solidity passed the same gate (j01), so the division came with T03's constants.\n2. k02 and k15 blocked on macOS arm64, as note 6 says.\n3. j01 (from J5; 129 markets/s, 199 generations, M 256): +0.003 holdout over J5. Slow seats barely move a joint search; T03 (1,598 generations, sigma at its 0.27 cap, still rising) was limited by the cap, not converged.\n4. k09's result (t3-b; id 3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475, fetched, hash equal) is a complete START: T03's code_zb64 (cb6d9455...), T03's params (constants as name: value, scaling) and port_zb64 732c0fb6... (IA's port with the anchor literals and TH in W; layout in its notes). Its gate B: T03 minus IB +0.769 se 0.027 on replica seeds 8588000..8589023: passes.\n\nDECIDED (27 items; 138 of 200 used at most). Every leg brief carries note 3's and note 6's sentences word for word.\n- t4-a..t4-e (5 each; keys mNN-sS-hHH-pPP: sigma0 0.S in z (s03 = 0.3), cap half-life HH minutes, population PP; NN 01..25): the TEMPLATE below, START = k09's URL (= T03), gate A MENDED: the harness's 50 x 2,000 callbacks with amounts capped at 2% of the reserve and the spot within 4x of its start (< 0.01 bps), plus 10 uncapped stress sequences reported as gates.A.stress, ungated; gate C the same way. Parameterization as J5 (note 4: 0.05 rms, 2^(0.03 z)); sigma0 0.2..0.7, half-lives 45..90 (T03 wanted a slower cap); holdout 41050000..41058191, fresh and shared by the round. A macOS seat returns replica_only params in START's layout.\n- dz-t03 (2: dz-a, dz-b; slow seats fine): find T03's dividing expression and zero state, reproduce the panic, measure each divisor's margin on 512 canonical replica markets, build T03G = T03 with the smallest guard, proven equal to T03 per seed on 256 real seeds and non-reverting on uncapped stress paths; returns T03G code_zb64 and sha256.\n- Left t3-a..d (13 running) and j11-a (3 running from J11) alone: cancel frees nothing once items run.\nREAD: the 27 new items plus j5-c/j15-s04-h40-p16, j5-b/j07-s07-h45-p16, j5-d/j18-s03-h60-p16 (note 6's second line; never had their ids). Wake: the six batches or 150 minutes.\n\nLEDGER, never reuse. Real engine, 1,024-seed blocks: below 8120832 taken; mNN 8120832+1024(NN-1), NN 01..25; dz-a 8146432..+255, dz-b 8147456..+255; confirm-t03 8700000..8702047; next free 8148480. Replica train, 2,000,000-seed blocks: mNN 1308000000+2000000(NN-1); dz margins 1358000000, 1359000000 (512 each); next free 1360000000 (stay below the sister goal's 1400000000). Holdout: round 3 41050000..41058191; round 4 41070000..+8191; then +20000 a round. ES seeds used: up to 20261425. Monitor 30000000..30002047 reused on purpose.\n\nNEXT EPISODE (8 of 10; about 62 items left).\n1. Per leg: blocked, replica_only, speed, cpus, M, generations, minutes, gates.A.stress. If legs still block at the mended gate A, read dz: the mend was wrong or T03 needs T03G; then relay from T03G.\n2. Rank legs by holdout frozen_vs_IB (se about 0.011; same seeds); check real frozen_vs_IB (se about 0.04) agrees, valid true, peak <= 245,000. A replica_only leg ranks by holdout frozen_vs_start only: spawn Linux freeze items (CAND = the leg's URL: freeze its params into T03's Solidity, gates A (capped) and C, holdout, IB and frozen on 512 fresh seeds; the result is a START).\n3. Round 4 (about 20 legs in batches of 5): TEMPLATE with START = the best leg's URL (it has code_zb64, params, port_zb64); gate B 'START minus IB on replica seeds <its real seeds> within 0.15 of the real <its frozen_vs_IB>'; holdout 41070000..+8191; sigma0 near the leg's final sigma, half 60..90; 3..5 legs from the second best, 3 from the best j5 continuation if handed. Same episode: confirm the best leg vs IB on two fresh 1,024-seed blocks (the confirm-t03 brief with CAND = the leg's URL and code sha256; promote at > 2 se; >= +0.3 over IB on 2,048 seeds goes to the requester with complete code and sha256).\n4. EP9: the final 2,048-seed confirmation of the best file (4 items of 512) plus any last legs; EP10 finish. When nothing new has landed, keep the running batches and set the wake; never spawn a round twice. Filled leg briefs are 2,945 characters: a longer var breaks the limit.\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, round 3 best), the gate A finding, what was not checked.\n\nTEMPLATE (t4 leg; vars esseed, pop, sigma, half, train, real; N3, N6 = the requester's sentences):\nOne relay leg from T03; the next starts from your result. Follow the goal's objective and: 'N3' 'N6'\nFILES (check sha256s). START = <k09 URL>: `code_zb64` (T03's Solidity), `params`, `port_zb64` (layout in its notes). IB: the goal's IB file in its own port.\n1. SETUP; fetch the files.\n2. Gate A (T03 reverts only far outside market ranges): 50 x 2,000 callbacks in 10-sequence commands, amounts capped at 2% of the reserve, spot within 4x of start, < 0.01 bps; plus 10 uncapped sequences, reported as gates.A.stress, ungated. Gate B: START minus IB on replica seeds 8588000..8589023 within 0.15 of the real +0.819. S = replica markets/s on the warmed search 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, population, sigma0 capped at sigma0 x 0.5^(minutes/half). Each generation: all proposals on the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean on monitor 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, changing only its literals (weights 1e-6, constants WAD). Gate C as A, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41050000..41058191, paired.\n6. REAL ENGINE, once: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300) in 64-seed commands; START too if time remains.\nRESULT, one JSON object under 60,000 bytes, START's keys: blocked; gates; speed; search{generations,minutes,M,curve}; 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, retail/arb volume deltas, by_quartile of IB's retail volume}; gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak over 245,000); notes. If nothing beat START, say so.\n",
 "spawn": [
  {
   "name": "t4-a",
   "brief": "One relay leg from T03; 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.'\n\nFILES (check sha256s). START = https://api.imd.fun/artifacts/3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475: `code_zb64` (T03's Solidity), `params`, `port_zb64` (layout in its notes). IB: the goal's IB file in its own port.\n\n1. SETUP; fetch the files.\n2. Gate A (T03 reverts only far outside market ranges): 50 x 2,000 callbacks in 10-sequence commands, amounts capped at 2% of the reserve, spot within 4x of start, < 0.01 bps; plus 10 uncapped sequences, reported as gates.A.stress, ungated. Gate B: START minus IB on replica seeds 8588000..8589023 within 0.15 of the real +0.819. S = replica markets/s on the warmed search 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: all proposals on the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean on monitor 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, changing only its literals (weights 1e-6, constants WAD). Gate C as A, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41050000..41058191, paired.\n6. REAL ENGINE, once: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300) in 64-seed commands; START too if time remains.\n\nRESULT, one JSON object under 60,000 bytes, START's keys: blocked; gates; speed; search{generations,minutes,M,curve}; 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, retail/arb volume deltas, by_quartile of IB's retail volume}; gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak over 245,000); notes. If nothing beat START, say so.",
   "items": [
    {
     "key": "m01-s03-h60-p16",
     "vars": {
      "esseed": "20261401",
      "pop": "16",
      "sigma": "0.3",
      "half": "60",
      "train": "1308000000",
      "real": "8120832"
     }
    },
    {
     "key": "m02-s03-h90-p16",
     "vars": {
      "esseed": "20261402",
      "pop": "16",
      "sigma": "0.3",
      "half": "90",
      "train": "1310000000",
      "real": "8121856"
     }
    },
    {
     "key": "m03-s05-h60-p16",
     "vars": {
      "esseed": "20261403",
      "pop": "16",
      "sigma": "0.5",
      "half": "60",
      "train": "1312000000",
      "real": "8122880"
     }
    },
    {
     "key": "m04-s04-h90-p16",
     "vars": {
      "esseed": "20261404",
      "pop": "16",
      "sigma": "0.4",
      "half": "90",
      "train": "1314000000",
      "real": "8123904"
     }
    },
    {
     "key": "m05-s02-h90-p16",
     "vars": {
      "esseed": "20261405",
      "pop": "16",
      "sigma": "0.2",
      "half": "90",
      "train": "1316000000",
      "real": "8124928"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 25,
    "brief": "Table of the legs: key, blocked step, replica_only, speed, cpus, M, generations, minutes, holdout frozen_vs_IB and frozen_vs_start (mean, se), real frozen_vs_IB (n, mean, se), afterSwap peak, valid; then the best leg's URL id and code_sha256."
   }
  },
  {
   "name": "t4-b",
   "brief": "One relay leg from T03; 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.'\n\nFILES (check sha256s). START = https://api.imd.fun/artifacts/3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475: `code_zb64` (T03's Solidity), `params`, `port_zb64` (layout in its notes). IB: the goal's IB file in its own port.\n\n1. SETUP; fetch the files.\n2. Gate A (T03 reverts only far outside market ranges): 50 x 2,000 callbacks in 10-sequence commands, amounts capped at 2% of the reserve, spot within 4x of start, < 0.01 bps; plus 10 uncapped sequences, reported as gates.A.stress, ungated. Gate B: START minus IB on replica seeds 8588000..8589023 within 0.15 of the real +0.819. S = replica markets/s on the warmed search 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: all proposals on the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean on monitor 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, changing only its literals (weights 1e-6, constants WAD). Gate C as A, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41050000..41058191, paired.\n6. REAL ENGINE, once: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300) in 64-seed commands; START too if time remains.\n\nRESULT, one JSON object under 60,000 bytes, START's keys: blocked; gates; speed; search{generations,minutes,M,curve}; 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, retail/arb volume deltas, by_quartile of IB's retail volume}; gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak over 245,000); notes. If nothing beat START, say so.",
   "items": [
    {
     "key": "m06-s03-h60-p24",
     "vars": {
      "esseed": "20261406",
      "pop": "24",
      "sigma": "0.3",
      "half": "60",
      "train": "1318000000",
      "real": "8125952"
     }
    },
    {
     "key": "m07-s05-h45-p16",
     "vars": {
      "esseed": "20261407",
      "pop": "16",
      "sigma": "0.5",
      "half": "45",
      "train": "1320000000",
      "real": "8126976"
     }
    },
    {
     "key": "m08-s03-h90-p24",
     "vars": {
      "esseed": "20261408",
      "pop": "24",
      "sigma": "0.3",
      "half": "90",
      "train": "1322000000",
      "real": "8128000"
     }
    },
    {
     "key": "m09-s04-h60-p16",
     "vars": {
      "esseed": "20261409",
      "pop": "16",
      "sigma": "0.4",
      "half": "60",
      "train": "1324000000",
      "real": "8129024"
     }
    },
    {
     "key": "m10-s06-h60-p16",
     "vars": {
      "esseed": "20261410",
      "pop": "16",
      "sigma": "0.6",
      "half": "60",
      "train": "1326000000",
      "real": "8130048"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 25,
    "brief": "Table of the legs: key, blocked step, replica_only, speed, cpus, M, generations, minutes, holdout frozen_vs_IB and frozen_vs_start (mean, se), real frozen_vs_IB (n, mean, se), afterSwap peak, valid; then the best leg's URL id and code_sha256."
   }
  },
  {
   "name": "t4-c",
   "brief": "One relay leg from T03; 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.'\n\nFILES (check sha256s). START = https://api.imd.fun/artifacts/3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475: `code_zb64` (T03's Solidity), `params`, `port_zb64` (layout in its notes). IB: the goal's IB file in its own port.\n\n1. SETUP; fetch the files.\n2. Gate A (T03 reverts only far outside market ranges): 50 x 2,000 callbacks in 10-sequence commands, amounts capped at 2% of the reserve, spot within 4x of start, < 0.01 bps; plus 10 uncapped sequences, reported as gates.A.stress, ungated. Gate B: START minus IB on replica seeds 8588000..8589023 within 0.15 of the real +0.819. S = replica markets/s on the warmed search 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: all proposals on the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean on monitor 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, changing only its literals (weights 1e-6, constants WAD). Gate C as A, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41050000..41058191, paired.\n6. REAL ENGINE, once: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300) in 64-seed commands; START too if time remains.\n\nRESULT, one JSON object under 60,000 bytes, START's keys: blocked; gates; speed; search{generations,minutes,M,curve}; 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, retail/arb volume deltas, by_quartile of IB's retail volume}; gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak over 245,000); notes. If nothing beat START, say so.",
   "items": [
    {
     "key": "m11-s03-h60-p16",
     "vars": {
      "esseed": "20261411",
      "pop": "16",
      "sigma": "0.3",
      "half": "60",
      "train": "1328000000",
      "real": "8131072"
     }
    },
    {
     "key": "m12-s03-h90-p16",
     "vars": {
      "esseed": "20261412",
      "pop": "16",
      "sigma": "0.3",
      "half": "90",
      "train": "1330000000",
      "real": "8132096"
     }
    },
    {
     "key": "m13-s05-h60-p16",
     "vars": {
      "esseed": "20261413",
      "pop": "16",
      "sigma": "0.5",
      "half": "60",
      "train": "1332000000",
      "real": "8133120"
     }
    },
    {
     "key": "m14-s04-h90-p16",
     "vars": {
      "esseed": "20261414",
      "pop": "16",
      "sigma": "0.4",
      "half": "90",
      "train": "1334000000",
      "real": "8134144"
     }
    },
    {
     "key": "m15-s02-h90-p16",
     "vars": {
      "esseed": "20261415",
      "pop": "16",
      "sigma": "0.2",
      "half": "90",
      "train": "1336000000",
      "real": "8135168"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 25,
    "brief": "Table of the legs: key, blocked step, replica_only, speed, cpus, M, generations, minutes, holdout frozen_vs_IB and frozen_vs_start (mean, se), real frozen_vs_IB (n, mean, se), afterSwap peak, valid; then the best leg's URL id and code_sha256."
   }
  },
  {
   "name": "t4-d",
   "brief": "One relay leg from T03; 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.'\n\nFILES (check sha256s). START = https://api.imd.fun/artifacts/3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475: `code_zb64` (T03's Solidity), `params`, `port_zb64` (layout in its notes). IB: the goal's IB file in its own port.\n\n1. SETUP; fetch the files.\n2. Gate A (T03 reverts only far outside market ranges): 50 x 2,000 callbacks in 10-sequence commands, amounts capped at 2% of the reserve, spot within 4x of start, < 0.01 bps; plus 10 uncapped sequences, reported as gates.A.stress, ungated. Gate B: START minus IB on replica seeds 8588000..8589023 within 0.15 of the real +0.819. S = replica markets/s on the warmed search 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: all proposals on the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean on monitor 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, changing only its literals (weights 1e-6, constants WAD). Gate C as A, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41050000..41058191, paired.\n6. REAL ENGINE, once: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300) in 64-seed commands; START too if time remains.\n\nRESULT, one JSON object under 60,000 bytes, START's keys: blocked; gates; speed; search{generations,minutes,M,curve}; 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, retail/arb volume deltas, by_quartile of IB's retail volume}; gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak over 245,000); notes. If nothing beat START, say so.",
   "items": [
    {
     "key": "m16-s03-h60-p24",
     "vars": {
      "esseed": "20261416",
      "pop": "24",
      "sigma": "0.3",
      "half": "60",
      "train": "1338000000",
      "real": "8136192"
     }
    },
    {
     "key": "m17-s05-h45-p16",
     "vars": {
      "esseed": "20261417",
      "pop": "16",
      "sigma": "0.5",
      "half": "45",
      "train": "1340000000",
      "real": "8137216"
     }
    },
    {
     "key": "m18-s03-h90-p24",
     "vars": {
      "esseed": "20261418",
      "pop": "24",
      "sigma": "0.3",
      "half": "90",
      "train": "1342000000",
      "real": "8138240"
     }
    },
    {
     "key": "m19-s04-h60-p16",
     "vars": {
      "esseed": "20261419",
      "pop": "16",
      "sigma": "0.4",
      "half": "60",
      "train": "1344000000",
      "real": "8139264"
     }
    },
    {
     "key": "m20-s06-h60-p16",
     "vars": {
      "esseed": "20261420",
      "pop": "16",
      "sigma": "0.6",
      "half": "60",
      "train": "1346000000",
      "real": "8140288"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 25,
    "brief": "Table of the legs: key, blocked step, replica_only, speed, cpus, M, generations, minutes, holdout frozen_vs_IB and frozen_vs_start (mean, se), real frozen_vs_IB (n, mean, se), afterSwap peak, valid; then the best leg's URL id and code_sha256."
   }
  },
  {
   "name": "t4-e",
   "brief": "One relay leg from T03; 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.'\n\nFILES (check sha256s). START = https://api.imd.fun/artifacts/3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475: `code_zb64` (T03's Solidity), `params`, `port_zb64` (layout in its notes). IB: the goal's IB file in its own port.\n\n1. SETUP; fetch the files.\n2. Gate A (T03 reverts only far outside market ranges): 50 x 2,000 callbacks in 10-sequence commands, amounts capped at 2% of the reserve, spot within 4x of start, < 0.01 bps; plus 10 uncapped sequences, reported as gates.A.stress, ungated. Gate B: START minus IB on replica seeds 8588000..8589023 within 0.15 of the real +0.819. S = replica markets/s on the warmed search 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: all proposals on the same M fresh markets (512 if S >= 300, else 256) from seed {{train}} up, never reused. Every 5 minutes score the ES mean on monitor 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, changing only its literals (weights 1e-6, constants WAD). Gate C as A, < 0.1 bps.\n5. Holdout, once: frozen, START, IB on seeds 41050000..41058191, paired.\n6. REAL ENGINE, once: IB and frozen, each alone, seeds {{real}}..+511 (+255 if S < 300) in 64-seed commands; START too if time remains.\n\nRESULT, one JSON object under 60,000 bytes, START's keys: blocked; gates; speed; search{generations,minutes,M,curve}; 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, retail/arb volume deltas, by_quartile of IB's retail volume}; gas{afterSwap_peak, oog}; valid (false on OOG, revert or peak over 245,000); notes. If nothing beat START, say so.",
   "items": [
    {
     "key": "m21-s03-h60-p16",
     "vars": {
      "esseed": "20261421",
      "pop": "16",
      "sigma": "0.3",
      "half": "60",
      "train": "1348000000",
      "real": "8141312"
     }
    },
    {
     "key": "m22-s03-h90-p16",
     "vars": {
      "esseed": "20261422",
      "pop": "16",
      "sigma": "0.3",
      "half": "90",
      "train": "1350000000",
      "real": "8142336"
     }
    },
    {
     "key": "m23-s05-h60-p16",
     "vars": {
      "esseed": "20261423",
      "pop": "16",
      "sigma": "0.5",
      "half": "60",
      "train": "1352000000",
      "real": "8143360"
     }
    },
    {
     "key": "m24-s04-h90-p16",
     "vars": {
      "esseed": "20261424",
      "pop": "16",
      "sigma": "0.4",
      "half": "90",
      "train": "1354000000",
      "real": "8144384"
     }
    },
    {
     "key": "m25-s07-h45-p16",
     "vars": {
      "esseed": "20261425",
      "pop": "16",
      "sigma": "0.7",
      "half": "45",
      "train": "1356000000",
      "real": "8145408"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 25,
    "brief": "Table of the legs: key, blocked step, replica_only, speed, cpus, M, generations, minutes, holdout frozen_vs_IB and frozen_vs_start (mean, se), real frozen_vs_IB (n, mean, se), afterSwap peak, valid; then the best leg's URL id and code_sha256."
   }
  },
  {
   "name": "dz-t03",
   "brief": "Diagnose T03's division-by-zero revert; no search. Follow the goal's objective (SETUP, REAL ENGINE) and the requester's rule: '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.'\n\nFILES (check sha256s). START = https://api.imd.fun/artifacts/3d001532cce4c2885307bb007a5170f77dd4b2f8151d041696e04a1c60a0f475: `code_zb64` (T03's Solidity, sha256 cb6d9455...), `params`, `port_zb64` (732c0fb6...: IA's port with the anchor literals and TH in W; layout in its notes). Replica: the IB file's `hashes.artifact_urls.rep`.\n\nFACT. Five relay legs ran the EVM-against-port callback harness (fresh deployment, reserves 100/10000, elapsed steps from [0,0,0,1,1,2,8,13], lognormal(-2,1.5) X amounts capped at 15% of reserve X). T03's afterSwap reverted with Panic(0x12) at a sell of amount_x 0.011758797438930166, amount_y 2256212.1895594997, reserves X 0.06663318548727094, Y 15007537.050604152, timestamp 3939, gas_used 62659, after 1,223 callbacks of one sequence; another seat saw it at reserves of the same order, and a 0.014 bps fee drift on a non-reverting stress sequence. On the real engine T03 ran 3,072 seeds (33 million afterSwap calls) with no revert and no OOG.\n\n1. SETUP; fetch and check the files.\n2. List every division and modulo in T03's afterSwap path with the condition that makes its divisor zero. Reproduce the panic in the EVM (pyrevm) at the state above, or the nearest state your harness reaches; name the culprit expression and the zero variable, and why such reserves produce it.\n3. Margin on canonical paths: run the port on 512 replica markets, seeds {{rep}}..+511 (configs per MatchRunner._build_configs, 10,000 steps), recording each divisor's minimum absolute value and the ranges of reserve X, reserve Y and spot; report them next to the failing state.\n4. Guard: T03G = T03's Solidity with the smallest change that avoids the revert (the previous fee, or the divisor clamped to 1, when it is zero), nothing else changed. Gate C: T03G against the port, 50 x 2,000 callbacks in 10-sequence commands, amounts capped at 2% of the reserve and spot within 4x of start, < 0.1 bps; then 10 uncapped sequences: T03G must not revert. REAL ENGINE: T03 and T03G each alone, seeds {{real}}..+255, in 64-seed commands; per-seed edges should be identical; gas_stats per arm.\n\nRESULT, one JSON object under 60,000 bytes: blocked; divisions [expression, location, zero_when]; culprit; reproduction{state, output}; margins{per divisor: min_abs; reserve and spot ranges}; guard{diff, gate_C, stress{sequences, reverts, max_bps}}; real{n, mean_diff, se, max_abs_per_seed_diff}; gas{afterSwap_peak per arm, oog}; code_zb64, code_sha256 (T03G); valid (false on any OOG, revert or peak over 245,000); notes. Report only what you measured.",
   "items": [
    {
     "key": "dz-a",
     "vars": {
      "rep": "1358000000",
      "real": "8146432"
     }
    },
    {
     "key": "dz-b",
     "vars": {
      "rep": "1359000000",
      "real": "8147456"
     }
    }
   ],
   "output": {
    "format": "json",
    "maxBytes": 64000
   },
   "merge": {
    "groupSize": 25,
    "brief": "Table: key, culprit, margin, guard gate C, stress reverts, real max per-seed diff, gas peaks, T03G code_sha256."
   }
  }
 ],
 "read": [
  "t4-a/m01-s03-h60-p16",
  "t4-a/m02-s03-h90-p16",
  "t4-a/m03-s05-h60-p16",
  "t4-a/m04-s04-h90-p16",
  "t4-a/m05-s02-h90-p16",
  "t4-b/m06-s03-h60-p24",
  "t4-b/m07-s05-h45-p16",
  "t4-b/m08-s03-h90-p24",
  "t4-b/m09-s04-h60-p16",
  "t4-b/m10-s06-h60-p16",
  "t4-c/m11-s03-h60-p16",
  "t4-c/m12-s03-h90-p16",
  "t4-c/m13-s05-h60-p16",
  "t4-c/m14-s04-h90-p16",
  "t4-c/m15-s02-h90-p16",
  "t4-d/m16-s03-h60-p24",
  "t4-d/m17-s05-h45-p16",
  "t4-d/m18-s03-h90-p24",
  "t4-d/m19-s04-h60-p16",
  "t4-d/m20-s06-h60-p16",
  "t4-e/m21-s03-h60-p16",
  "t4-e/m22-s03-h90-p16",
  "t4-e/m23-s05-h60-p16",
  "t4-e/m24-s04-h90-p16",
  "t4-e/m25-s07-h45-p16",
  "dz-t03/dz-a",
  "dz-t03/dz-b",
  "j5-c/j15-s04-h40-p16",
  "j5-b/j07-s07-h45-p16",
  "j5-d/j18-s03-h60-p16"
 ],
 "cancel": [],
 "wake": {
  "batches": [
   "t4-a",
   "t4-b",
   "t4-c",
   "t4-d",
   "t4-e",
   "dz-t03"
  ],
  "afterMinutes": 150
 },
 "finish": false
}