{
  "notes": "Credit Taylor (gtmcknight): replica, Gaussian/lattice filters, dynamic program and qm tables; github.com/gtmcknight/amm-sim @4812a6382311624e1506aca131ca35c378f930d9, research/solved/README.md first.\n\nEPISODE 5: ACCELERATION BEFORE MORE TRAINING (requester note 5).\nAuthoritative input: 36/200 items used, 16 unsettled batches, 30 running, 6 accepted, 0 failed, no refusals, effects.pending=0. Keep all existing batches running, including e02 classifiers and six e04 residual pilots; no retries/cancels. No more classifier items and no new slow head training. Spawn e05-fast-sim (numba-tape,numba-rng), two independent implementations; e05-head-cost (cost8), one bounded feasibility benchmark. If accepted: 39 used,161 remaining; keep >=40 for final checks/ports. Episodes 6..10 remain. finish=false. No simulations/contracts run here.\n\nLOCAL EVIDENCE CHECKS.\nVerified handed-byte SHA256:\ne02-residual-head/eight-output a2d5a0dea7982a84bd2238f143f045b44600c35ac5638d2307fdeadc15bfc757\ne02-residual-head/sixteen-output f970c3e1976559de37242c49258571be5edfe1432f6c12ce3164cd474b2ed980.\nDecoded bundles in memory as DATA; all 9 source-file hashes and Python ASTs pass. Recomputed supplied paired means/SEs from sums within 1e-6. Both P tables agree with pinned README and prior evidence. No simulations independently rerun.\nP rows (seed: perfect,Gaussian/plain,Gaussian/qm,lattice/qm):\n10000:448.261189,443.455598,443.522608,443.663520\n10001:576.779199,571.463409,571.623551,571.977293\n10002:531.886497,525.168028,525.865859,526.411631.\nActual qt1 = compressed QMRef, not RealPolicy; three edges 443.101741,571.454483,525.908441. COMBO 444.195330,572.172682,526.274760.\n\nHEAD8 (eight-output): zero-start 8-input/8-hidden-tanh head, fixed hidden projection and 18 learned output parameters; corrections bounded at 8bps per side, corrected fees stored. Choose full1024: M6-COMBO +.080720 SE .012550, M6-qt1 +.690379 SE .018802; M6 selected on choose only. Frozen report full2048: HEAD8-COMBO +.076499 SE .008473 (1220 wins); HEAD8-qt1 +.673867 SE .013783 (1802 wins); COMBO-qt1 +.597368 SE .013384. Six sep-CMA generations at sigma0=.04 improved choose; sigma0=.3 hurt (-.7 to -4 per candidate). This supports more compute, not a proven eventual large gain.\nCRITICAL REPRODUCIBILITY LIMIT: head.py SHA 59c01d85aff6c712b65bf84f98068c6088e7aca47ce12b7b23ef7255292396c3 and drive.py 1c30173a4fa6a2fa0a08eb8999d988bd941e55c903f10f78051024eaacc9e2a2 are embedded completely. FROZEN_W.json SHA 6aa54280e9b31560d0fb9134e122a2b923a032083bc457c526774729448206d9 is named but its bytes are NOT supplied; W_frozen is rounded to9dp. Do not claim that vector reproduces the original frozen policy/hash. It is sufficient for a separately labelled hook/cost test. Future training outputs must include full-precision weights, normalizers, optimizer and RNG checkpoints in delivered bundles. Report +.674 passes numeric contract threshold but is not a deployable/reproduced head contract.\nSmall cross-platform reference drift (+.597368 vs +.597391) is disclosed, cause unproven. Fast-port parity must use same-machine CPython, not relaxed thresholds or external cached edges.\n\nHEAD16 (sixteen-output): only one mirrored pair, sigma0=.05, 256 choose seeds. Both lose to zero (-.725521 SE .038399, -.516533 SE .036154). Selected zero head = unchanged COMBO; not a negative conclusion about trained residuals. Full choose qt1 pairing absent; report +.597391 SE .013388 uses published qt1 per-seed edges with only3 local checks. This is incomplete Q, not independent head improvement. Do not promote its statistics as a new candidate.\n\nSOURCES: all four baseline artifact URLs and the HEAD8 artifact in the new briefs were fetched and byte-hash checked here. Keep using their pinned bytes/extracted hashes (episode2 and handed HEAD8). qt1 is QMRef. No source code was executed during this audit.\n\nCP-C FOUND WITHOUT REQUESTER INPUT.\nNamed external goal full UUID from its public GitHub commit:5b196d0a-64d6-4a13-a41f-e43ad373553d. Public /goals/<uuid>/items identifies e4-combo-port/cp-c result artifact ffd2b2488b92fe51e639af36007feabbf15c3df3c119bf957d460e1be42efa34. Base raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/contracts/Candidate.sol SHA b87234c89e094f4955578417c1266129b0f96e6dfda68e3fb8866e00eeda71a2. Applying cp-c diff IN MEMORY yields 47295-byte source SHA 1cbd726f3a1f48950c60f0dafaae5d4e36c20481c5714efa72b82cae699dd064, exactly requester's hash. Exact ComboG Python reference is embedded in cp-c.\nIMPORTANT: cp-c uses GATE=4 (mixed quotes only if dt<=4), not ungated COMBO. Gate chosen by gas rule. External e4-combo-gate/gate-report artifact 70ece52dd649c2b5f1085dfca6e77046a53ab8929f0e3e11875fd33a9fe0c2e4, full2048 paired G4-qt1 +.601755886 SE .013533815. G4 is fixed in advance here, not picked by report comparisons. Original choose there was60000..61023; cost8 must score fixed G4 on this goal's64000..65023. cp-c claims runtime22370B, F max3.087157e-6bps/100000callbacks, engine peak229596,0OOG on16 seeds9803170..9803185. External claims; not locally rerun.\n\nDISPATCH AND NEXT EPISODE.\nm: two independent complete accelerated modules, run(seed,policy,head_params)->edge; exact CPython stochastic stream/arithmetic, no fastmath. P first. Require every per-seed error<=1e-6 for QMRef,TwoComp,Combo on10000..10063 AND64000..64063 (384 pairs); nonzero rounded HEAD8 hook checked separately on128 seeds. Single-worker full10000-step throughput, inclusive of random generation, target>=50/core; no hidden truth in policy. Code/tests/setup line and all input/output hashes required. A speed pass cannot compensate for parity failure. Parity use of report seeds is implementation checking, never policy selection.\nn: price full HEAD8 feature/math/state cost alongside already eligible cp-c in a diagnostic harness; preserve G4 fee decisions. Rounded weights are benchmark constants only. Charge storage/normalization/packing and prevent dead-code elimination. Extra cost target<=12000. Base F50x2000, head numerical check, sizes and engine base control required. This is NOT a new scored head strategy or integrated engine certification for one. Do not duplicate external COMBO port. Any actual head/G4 stack needs its own full Q before contract work and then F/engine.\nReserve engine9900000..9900015 exclusively for cost8's paired cp-c/qt1 control; next free9900016 even if unused until ledger reconciled. No engine seeds consumed by this orchestrator.\n\nOnce m passes, launch requester's THREE c++ head items, sigma0=.04, zero start, eight-output features plus both components' moments, 8x8/16x16 architectures. Training512-seed blocks rotate within64000..65023; final choose1024, freeze complete bytes, report10000..12047 once, paired vs immediate base AND qt1. Plan100+ generations but benchmark honestly: 100*13*512=665600 runs; at50/s this is3.70h, not a one-hour item. Require sufficient measured head throughput or resumable <=1h training stages with full optimizer/RNG/model checkpoints; do not pretend50/s suffices or shrink scoring windows/steps silently. Intermediate training stages need no report; final chosen frozen policy does. Every new model uses observables only; true flag only labelled oracle ablations.\nRead new three results and known pending e02/e04 results; small unknown-key batches hand results automatically, never guess keys. Wake on the two new batches settling,75min fallback via scheduler, not local sleep. Reconcile refusals/coverage first. Rank/select ONLY on choose; report is frozen audit/eligibility, correcting episode4's mistaken report-ranking suggestion. Prior true-flag COMBO +3.167510 vsqt1 is oracle-only; classifier pilots suggest little remaining first-call information. No #1 result, no board-score conversion or submission claimed. Requester must ask user before public submission.",
  "spawn": [
    {
      "name": "e05-fast-sim",
      "mode": "research",
      "brief": "Credit Taylor (gtmcknight) in every header. One independent item, <1h; python3 -I, state scratch/, checkpoint commands <8min. Benchmark first; return partial evidence if time-limited.\nSources: https://github.com/gtmcknight/amm-sim @4812a6382311624e1506aca131ca35c378f930d9, research/solved/README.md first; gates.py,replica2.py,evalpol.py,real.py,latt.py,pol_mid.json,qm_k1e-5.json. Verify commit. Fetch artifacts, SHA256 must equal URL suffix; check extracted hashes in them:\nqt1 https://api.imd.fun/artifacts/8a6e303b662e1a5ea9bb47f31acedd3988ef65b3ddb66d074517aa59ad41ca40\nTC https://api.imd.fun/artifacts/d3c849db2ac31e567b57e52b80b86e8c24c842e5b4125b9d75c78e3cb07115b9\nCOMBO https://api.imd.fun/artifacts/d360bea6c8c982717b7b43a8069a87013169c89ee3e4da25622db4d880b936d4\nQMS1 https://api.imd.fun/artifacts/17d249ab0c33fc44931d9b105cf3f9e3846a560bd518b67310c2a56defacdecc\nHEAD8 https://api.imd.fun/artifacts/a2d5a0dea7982a84bd2238f143f045b44600c35ac5638d2307fdeadc15bfc757\nRun unmodified gates.py first; require all README values at 6dp.\nPort replica2.run AND QMRef,TwoComp,Combo with a residual-head hook. {{method}} API run(seed,policy,head_params)->edge; 10000 steps/default configs. Match CPython RNG (including gauss cache/draw order), routing, clamps, arithmetic order; no fastmath. Speed must include stochastic-input generation and policy callbacks, not replay cached edges.\nParity gate: all 3 policies on EVERY seed 10000..10063 and 64000..64063, same-machine CPython vs accelerated abs edge error <=1e-6. These are implementation checks, never policy tuning. Stop promotion on any failure; show first divergence. Zero head must equal Combo; test nonzero HEAD8 on the same 128 seeds using the supplied rounded vector as a separately labelled hook test. Expose both components' moments for later heads. Keep live policy independent of true arb,p,s2,j and init run parameters; check hidden-input invariance.\nBenchmark warmed single-thread end-to-end runs/s (target >=50/core), separately JIT/startup, memory, per-policy and nonzero-head speed. No training/contracts/engine. Publish complete importable module, driver/tests, exact versions, venv+numba setup line; include rng generation and all custom code, not local paths. JSON: hashes,P stdout,384 baseline plus 128 head parity rows/max errors,hook/invariance checks,timings,commands,limitations; source bundle base64/zlib+SHA256 allowed, <=64000B. State parity pass and speed pass separately.",
      "items": [
        {
          "key": "numba-tape",
          "vars": {
            "method": "Use a Numba scalar kernel with exact CPython-generated random tapes; preserve conditional draw consumption and include tape generation in timing."
          }
        },
        {
          "key": "numba-rng",
          "vars": {
            "method": "Independently implement a Numba kernel with CPython-compatible seeded RNG/state, including cached Gaussian draws. Preserve stream consumption exactly."
          }
        }
      ],
      "output": {
        "format": "json",
        "maxBytes": 64000
      },
      "merge": {
        "groupSize": 5,
        "brief": "Preserve independent source bundles and hashes. Compare per-policy parity, nonzero-head parity and inclusive serial throughput. Any mismatch blocks promotion regardless of speed; keep failure evidence and limitations."
      }
    },
    {
      "name": "e05-head-cost",
      "mode": "research",
      "brief": "Credit Taylor (gtmcknight) in every header. One gas-cost item, <1h; benchmark first, state scratch/, commands <8min, checkpoint.\nTaylor: github.com/gtmcknight/amm-sim @4812a6382311624e1506aca131ca35c378f930d9 research/solved (README first), gates.py and its imports/tables; verify commit, run P before changes.\nArtifacts https://api.imd.fun/artifacts/<h>; verify every byte SHA256=h and all extracted hashes:\ncp-c ffd2b2488b92fe51e639af36007feabbf15c3df3c119bf957d460e1be42efa34\nHEAD8 a2d5a0dea7982a84bd2238f143f045b44600c35ac5638d2307fdeadc15bfc757\nG4 report 70ece52dd649c2b5f1085dfca6e77046a53ab8929f0e3e11875fd33a9fe0c2e4\nTC-A base: https://raw.githubusercontent.com/identity-md-launches/goal-3170-beat-network-s-amm-entry/4eb3e985fd31e3cd17832501b95b6d2491aca73d/contracts/Candidate.sol (sha256 b87234c89e094f4955578417c1266129b0f96e6dfda68e3fb8866e00eeda71a2). Apply cp-c diff: require 1cbd726f3a1f48950c60f0dafaae5d4e36c20481c5714efa72b82cae699dd064. cp-c contains exact ComboG reference. Same repo/commit: reference/qt1/{Strategy.sol,qmref.py,blob.bin},reference/twocomp/twocomp.py; verify their hashes in HEAD8.\nUse goal's EXACT Linux SETUP script once as scratch/setup.sh in workspace clone benedictbrady/amm-challenge @6b6921f8d463314aa7c96234e1be25a25245f704; later commands prefix '. scratch/env.sh && '. No substitute repo setup; failure -> blocked={step,error}.\nPrice HEAD8 arithmetic on frozen cp-c (ComboG GATE=4, NOT ungated Combo). G4 report n2048 +.601755886 se .013533815 vs qt1 qualifies this base; verify cited row. Also score unchanged G4 paired qt1 on 64000..65023; never tune on report.\nBuild separate instrumented callback harness around cp-c: all eight features, normalization, 8x8 tanh, two outputs, clamps and required retained state. Use HEAD8's rounded vector as benchmark constants, not its missing exact frozen weights. Keep G4 fee decisions unchanged; expose computed head outputs so optimizer cannot erase work. Replay identical callbacks through baseline and harness; report full extra cost including storage, packing and features, separating harness overhead. Target <=12000 added gas at peak. This is feasibility, not a scored head policy.\nF: 50x2000 replica callbacks, base fees and head outputs vs their Python references <=.01bps. Record size<=24576, all peaks/OOG. Engine base control: each cp-c/qt1 alone vs30bps VanillaStrategy, amm_sim_rs.run_batch(X,VanillaStrategy,configs,8), configs per MatchRunner._build_configs, seeds9900000..9900015 only, peak<=245000, zero OOG.\nJSON: complete source/patch/ref/test bundle+hashes, P/Q/F, gas deltas/worst inputs, sizes, engine paired{n,mean_diff,se,worst5}, seed ledger, commands, limitations. No submission or new fee policy; a future head requires Q and integrated engine checks.",
      "items": [
        {
          "key": "cost8",
          "vars": {}
        }
      ],
      "output": {
        "format": "json",
        "maxBytes": 64000
      },
      "merge": {
        "groupSize": 2,
        "brief": "Preserve exact source, reconstruction and seed ledger. Separate diagnostic head overhead, base-policy Q/F and engine control. Do not certify a changed head policy or infer its edge from the ungated HEAD8 result."
      }
    }
  ],
  "read": [
    "e05-fast-sim/numba-tape",
    "e05-fast-sim/numba-rng",
    "e05-head-cost/cost8",
    "e02-baselines/references",
    "e04-residual-a/res-a",
    "e04-residual-a/res-b",
    "e04-residual-a/res-c",
    "e04-residual-b/res-d",
    "e04-residual-b/res-e",
    "e04-residual-b/res-f",
    "e04-belief-solve/bs-a",
    "e04-belief-solve/bs-b",
    "e04-price-loss/loss-a",
    "e04-smoothing-b2/smoothing-b2",
    "e03-smoothing/smoothing-a",
    "e02-observable-data/data-a"
  ],
  "cancel": [],
  "wake": {
    "batches": [
      "e05-fast-sim",
      "e05-head-cost"
    ],
    "afterMinutes": 75
  },
  "finish": false
}