{
  "notes": "Episode 4/10. Entry: 29/400 items used, no refusals, 12 handed results, 5 older items still running. This decision requests 5 research batches x 2 independent items = 10 items; if admitted, 39 used and 361 remain. Only decisions.json is delivered; no simulations or submissions here.\n\nBASELINE CHANGED by requester note 2026-11-08 20:38Z: V10 was submitted, board 519.8458, rank 28; paired board gain vs STACK +0.136 SE .021 (1000 runs, 604 wins). These are requester-reported figures, not a new board fetch. V10 is the baseline; top ten about +4.8 away. Requester submits one exact file at >=+0.1 over V10 on >=4000 fresh seeds, zero OOG. V10 = code of https://api.imdnotdead.fun/artifacts/33f54e81f3372088e9eced52c0174f310ac348af98ef5727b73785c088679194, SHA256 cd9bdb45ab0537ad25c4fd90ca8618898cef6386de3df65f192eaef65fbca245; that artifact also has harness_source. Its exact code is also in e03-v10-retail/a. STACK is historical reference only.\n\nRESULTS READ AND DECISIONS (native paired results unless qualified; all are local):\n- b08-a/b, e03-confirm-v10: exact V10 on 5008000..5009999 +0.14452352 SE .013566995 and 5010000..5011999 +0.12686215 SE .013911946 vs STACK. Pooling these SAME-hash blocks: n=4000, +0.1356928358494185 SE .009715827059408 (sample variance includes between-block means). CH exact; no halts; afterSwap maxima 194139/194882. V10 already submitted; no more baseline confirmations.\n- b02-normalizer-state, e01 pilot: native n=2000 on 5004000..5005999, -1.37563288 SE .04581778 vs STACK, max_ok 240832, OOG 0. Paired_valid=true but overall valid=false: arb-volume reconstruction error .0001153 exceeded declared 1e-6. Reported retail +.9901 / arb -2.3658 are unvalidated. Four interval/latent-Vanilla structures lost; no port or confirmation. \n- b07-a/b, e02-search-regime: a 1152 evaluations, all negative, held-out n512 -0.575536 SE .045819; b only 24 evaluations, n384 -0.835635 SE .039606. OOG 0, peaks 212641/212934. Both component-edge deltas null; b skipped CH and standalone validation and shortened recheck/holdout. These are negative evidence for the tested 60-constant regime search, not a proof no regime policy can work. Do not spend another wave on a smaller constant-sweep radius.\n- b09-b, e03-v10-floor/b: kappa .8. Fresh 5014000..5015999 vs V10 +.000178596 SE .000160483, n2000; retail +.000043642, arb +.000134954. OOG 0, afterSwap 196935 (220975 is initialization). Smaller floors generally never bind; larger binding floors lose. Its +.182364 vs STACK is inherited V10 gain, not a new increment. No integration; await floor/a.\n- b10-a/b, e03-v10-blend: toxicity fast weights .15/.30, unchanged stale weight .30 and stale coefficient. Different hashes. Their fresh blocks 5016000/5018000 give vs V10 +.00099651 SE .00380812 / -.00477090 SE .00590074 (2000 each). Do NOT pool different hashes. b retail -.406264 / arb +.401493 vs V10 cancel; a's reported component deltas are only vs STACK. Peaks 194605/195466, OOG 0. More stale posterior weight or stale-shift changes lost badly. No blend to integrate.\n- b11-a, e03-v10-retail/a: all eight cheaper-fee screens negative; best frozen code is byte-identical V10. 5020000..5021999 n2000 gives exactly 0 vs V10, +.116946 SE .015019 vs STACK. OOG 0, max_ok 194858. Await retail/b.\n- b13-a horizon: blocked at uv execution on incompatible runtime; n0, not a tried idea. b13-b: 24 evaluations, partial held-out n128, -.0464 SE .016 vs STACK, approximate retail -.0673 / arb +.0209, OOG0, max233969; skipped CH and shortened recheck. No confirmation. One incomplete negative plus one setup block does not retire all timing mechanisms. Do not blindly repeat that surcharge: the new transition-policy predicts callback continuation from observed history instead of H=1/lambda.\n- b14-a shadow: n512 -.02370965 SE .00992409 vs STACK, retail -.1555566 / arb +.1318469, OOG0, max222723, no confirmation. Static shadow argmax converged toward zero overlay. CH exact, but initial probes/identity used 0..31 outside allowed tuning; do not copy that protocol. Negative evidence only. Await shadow/b.\n\nArtifact audit: 9/9 non-null code hashes match; exact V10 present in b11-a. Baseline, counts and gas callback scopes reviewed, no simulator reproduction. No credible increment over V10: no integration or confirmation batch.\n\nNEW WORK, two independent copies per idea:\n1 e04-retail-state: separate latent retail rate/size from arb-contaminated own fills; only these new estimates feed the flow fee terms. Preserve V10 price/stale machinery; compare weighted count, count+size, quote-censoring correction. This tests new state and its coupling, not static flow damping.\n2 e04-transition-policy: learn whether the next own callback stays in the timestamp, updating only after that next event is observed. Use learned continuation probability to gate bounded residual quote policies. \n3 e04-band-transport: cumulative signed retail displacement controls feasible no-arb band endpoints jointly, anchored at V10, aiming to alter reserve location before next arb. Test translation, width, coupled response. Preserve zero-intervention identity; no hidden labels.\n4 e04-continuation-design: derive genuine two-step continuation gradients from exact rules, then a bounded table/polynomial implementation; distinguish execution edge from inventory PnL. Static prototype/checks only.\n5 e04-size-tail-design: integrate clipped retail routing over the full lognormal size distribution; quantify mean-size/Jensen errors and determine whether a distinct causal policy exists. Reject a relabelled greedy share optimizer. No market simulations.\nSearches use the prescribed verbatim setup, V10 harness, <=20 minutes search, 256-seed recheck of two candidates, then one frozen novel hash on 512 held-out tuning seeds. Overall <=55 minutes. Chunk <=20 and collect gas per arm/chunk to limit memory; include reproducible source. Searches reuse verified harness calibration; every future confirmation must independently reproduce CH 0..999=525.5258821780834 (tolerance 1e-6). Do not promote incomplete results; blocked is not negative.\n\nLEDGER: quarantine ALL previously allocated confirmation seeds [5000000,5036000), even unused or pending blocks. No new confirmation seeds allocated this episode. NEXT FREE=5036000. New tuning bands, all endpoints inclusive: retail-state a 640000..649999, b650000..659999; transition a660000..669999,b670000..679999; band-transport a680000..689999,b690000..699999. In each band: search start..start+3999, recheck start+4000..+4255, held-out start+5000..+5511. Reserve the entire bands; next free tuning band700000. Designs use no market seeds.\n\nNEXT: read all 10 new items and the 5 pending: floor/a, retail/b, restable/a,b, shadow/b. Cancel none. Old STACK-based results must be tested directly vs V10, never adjusted by subtracting unrelated means. Screen gate mean>2SE and >=.1 vs V10 before allocating two disjoint >=2000-seed fresh confirmations of the SAME frozen hash. Smaller credible gains require independent integration tests. Final promotion requires pooled >=4000 fresh seeds, mean>=.1 and >2SE vs V10, zero OOG/other halts, validated code/hash and reconciled edge attribution. Any OOG invalidates its hash; never drop seeds. Code repairs get new hashes/blocks. Do not pool independently optimized files. If new families fail, use the design falsifiers to change mechanism rather than repeating retired constants. Keep at least 100 seats for later integration/ablation and final validation. Wake on all named batches settling or a 90-minute scheduling fallback (no actual waiting here). finish=false: the top-ten goal remains unmet.",
  "spawn": [
    {
      "name": "e04-retail-state",
      "mode": "research",
      "brief": "Implement/search {{family}}, copy {{copy}}.\nClone https://github.com/benedictbrady/amm-challenge @6b6921f8d463314aa7c96234e1be25a25245f704 in workspace, never /tmp. Save as scratch/setup.sh; run sh scratch/setup.sh once at checkout root; later commands '. scratch/env.sh && '. Setup failure: blocked={step,error}, n=0.\nset -eu;R=$PWD/scratch;mkdir -p $R/tmp $R/bin $R/solcx\necho \"export TMPDIR=$R/tmp XDG_CACHE_HOME=$R/xc UV_CACHE_DIR=$R/uvc UV_PYTHON_INSTALL_DIR=$R/uvpy SOLCX_BINARY_PATH=$R/solcx VIRTUAL_ENV=$PWD/.venv PATH=$PWD/.venv/bin:$R/bin:\\$PATH\" >$R/env.sh;. $R/env.sh\ncommand -v uv >/dev/null||{ curl -LsSf https://github.com/astral-sh/uv/releases/latest/download/uv-x86_64-unknown-linux-gnu.tar.gz|tar --no-same-owner -xz -C $R/tmp;cp $R/tmp/uv-*/uv $R/bin/;}\nW=amm_sim_rs-0.1.0.post1-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl;curl -LsSf https://github.com/gtmcknight/amm-sim/releases/download/sim-6b6921f8/$W -o $R/$W\necho \"aedb68280aca34c110968f00148387c95885207913fb2cf19a1ab4c5cfd6887a  $R/$W\"|sha256sum -c -\nuv venv --python 3.12 .venv;uv pip install $R/$W numpy py-solc-x==2.1.0 pyrevm==0.3.7;uv pip install --no-deps -e .\npython -c \"import solcx;solcx.install_solc('0.8.24')\"\namm-match validate contracts/src/StarterStrategy.sol\nV10 code/harness: https://api.imdnotdead.fun/artifacts/33f54e81f3372088e9eced52c0174f310ac348af98ef5727b73785c088679194; verify code sha256 cd9bdb45ab0537ad25c4fd90ca8618898cef6386de3df65f192eaef65fbca245. Use its config/decomposition (CH already verified).\nEach arm alone vs Vanilla: amm_sim_rs.run_batch(X,VanillaStrategy,configs,8); default_rng(seed) draws size,rate,sigma; price=seed,retail=seed+1;10000 steps. Causal features only.\n{{mechanism}}\nZero intervention must equal V10. Compare >=3 structures; CMA-ES or similar seed {{rng}}, <=20min on rotating 32/64-seed CRN within {{train}}. Recheck top 2 on {{recheck}} (256); freeze ONE novel hash, then 512 held-out {{hold}} once. Inclusive ranges; finish within 55min, report incomplete. Tuning only; no seeds>=5000000.\nChunk <=20; reset/read amm_sim_rs.gas_stats() around each arm/chunk. Any OOG invalidates that hash; never drop seeds. Validate frozen Solidity. Aim afterSwap<235k.\nJSON: blocked,code,sha256,harness/generator source,params,search log,seed ledger,paired{n,mean_diff,se,worst} vs V10 (sample SE),retail/arb deltas and reconciliation,gas{max_ok,oog} per arm (afterSwap max; init separate),all halt counts,validation,limitations,seeds_kind=tuning. No board claim.",
      "items": [
        {
          "key": "a",
          "vars": {
            "family": "retail-only flow state",
            "copy": "a",
            "mechanism": "Replace only fee-flow inputs with a latent retail rate/size state: later prints weight 1, first prints 1 minus V10 posterior arb probability. Preserve V10 price/stale updates. Compare weighted counts alone, counts+size moments, and bounded correction for quote-dependent missing flow; avoid treating own fills as total arrivals. Search estimator/fee coupling (<=16 parameters), not original constants; retain a zero-mix identity.",
            "rng": "401",
            "train": "640000..643999",
            "recheck": "644000..644255",
            "hold": "645000..645511"
          }
        },
        {
          "key": "b",
          "vars": {
            "family": "retail-only flow state",
            "copy": "b",
            "mechanism": "Replace only fee-flow inputs with a latent retail rate/size state: later prints weight 1, first prints 1 minus V10 posterior arb probability. Preserve V10 price/stale updates. Compare weighted counts alone, counts+size moments, and bounded correction for quote-dependent missing flow; avoid treating own fills as total arrivals. Search estimator/fee coupling (<=16 parameters), not original constants; retain a zero-mix identity.",
            "rng": "402",
            "train": "650000..653999",
            "recheck": "654000..654255",
            "hold": "655000..655511"
          }
        }
      ],
      "output": {
        "format": "json",
        "maxBytes": 64000
      }
    },
    {
      "name": "e04-transition-policy",
      "mode": "research",
      "brief": "Implement/search {{family}}, copy {{copy}}.\nClone https://github.com/benedictbrady/amm-challenge @6b6921f8d463314aa7c96234e1be25a25245f704 in workspace, never /tmp. Save as scratch/setup.sh; run sh scratch/setup.sh once at checkout root; later commands '. scratch/env.sh && '. Setup failure: blocked={step,error}, n=0.\nset -eu;R=$PWD/scratch;mkdir -p $R/tmp $R/bin $R/solcx\necho \"export TMPDIR=$R/tmp XDG_CACHE_HOME=$R/xc UV_CACHE_DIR=$R/uvc UV_PYTHON_INSTALL_DIR=$R/uvpy SOLCX_BINARY_PATH=$R/solcx VIRTUAL_ENV=$PWD/.venv PATH=$PWD/.venv/bin:$R/bin:\\$PATH\" >$R/env.sh;. $R/env.sh\ncommand -v uv >/dev/null||{ curl -LsSf https://github.com/astral-sh/uv/releases/latest/download/uv-x86_64-unknown-linux-gnu.tar.gz|tar --no-same-owner -xz -C $R/tmp;cp $R/tmp/uv-*/uv $R/bin/;}\nW=amm_sim_rs-0.1.0.post1-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl;curl -LsSf https://github.com/gtmcknight/amm-sim/releases/download/sim-6b6921f8/$W -o $R/$W\necho \"aedb68280aca34c110968f00148387c95885207913fb2cf19a1ab4c5cfd6887a  $R/$W\"|sha256sum -c -\nuv venv --python 3.12 .venv;uv pip install $R/$W numpy py-solc-x==2.1.0 pyrevm==0.3.7;uv pip install --no-deps -e .\npython -c \"import solcx;solcx.install_solc('0.8.24')\"\namm-match validate contracts/src/StarterStrategy.sol\nV10 code/harness: https://api.imdnotdead.fun/artifacts/33f54e81f3372088e9eced52c0174f310ac348af98ef5727b73785c088679194; verify code sha256 cd9bdb45ab0537ad25c4fd90ca8618898cef6386de3df65f192eaef65fbca245. Use its config/decomposition (CH already verified).\nEach arm alone vs Vanilla: amm_sim_rs.run_batch(X,VanillaStrategy,configs,8); default_rng(seed) draws size,rate,sigma; price=seed,retail=seed+1;10000 steps. Causal features only.\n{{mechanism}}\nZero intervention must equal V10. Compare >=3 structures; CMA-ES or similar seed {{rng}}, <=20min on rotating 32/64-seed CRN within {{train}}. Recheck top 2 on {{recheck}} (256); freeze ONE novel hash, then 512 held-out {{hold}} once. Inclusive ranges; finish within 55min, report incomplete. Tuning only; no seeds>=5000000.\nChunk <=20; reset/read amm_sim_rs.gas_stats() around each arm/chunk. Any OOG invalidates that hash; never drop seeds. Validate frozen Solidity. Aim afterSwap<235k.\nJSON: blocked,code,sha256,harness/generator source,params,search log,seed ledger,paired{n,mean_diff,se,worst} vs V10 (sample SE),retail/arb deltas and reconciliation,gas{max_ok,oog} per arm (afterSwap max; init separate),all halt counts,validation,limitations,seeds_kind=tuning. No board claim.",
      "items": [
        {
          "key": "a",
          "vars": {
            "family": "learned next-event policy",
            "copy": "a",
            "mechanism": "Learn P(next own callback shares timestamp) online: store each quote's context, update its counts only when the next callback arrives. Gate two bounded bid/ask residual policies with this probability using gap/uncertainty and last size. Compare smooth, threshold and context-conditioned gates (<=16 parameters). Causal inputs only; preserve V10 estimators. This changes predicted quote lifetime, not a fixed first-print surcharge.",
            "rng": "403",
            "train": "660000..663999",
            "recheck": "664000..664255",
            "hold": "665000..665511"
          }
        },
        {
          "key": "b",
          "vars": {
            "family": "learned next-event policy",
            "copy": "b",
            "mechanism": "Learn P(next own callback shares timestamp) online: store each quote's context, update its counts only when the next callback arrives. Gate two bounded bid/ask residual policies with this probability using gap/uncertainty and last size. Compare smooth, threshold and context-conditioned gates (<=16 parameters). Causal inputs only; preserve V10 estimators. This changes predicted quote lifetime, not a fixed first-print surcharge.",
            "rng": "404",
            "train": "670000..673999",
            "recheck": "674000..674255",
            "hold": "675000..675511"
          }
        }
      ],
      "output": {
        "format": "json",
        "maxBytes": 64000
      }
    },
    {
      "name": "e04-band-transport",
      "mode": "research",
      "brief": "Implement/search {{family}}, copy {{copy}}.\nClone https://github.com/benedictbrady/amm-challenge @6b6921f8d463314aa7c96234e1be25a25245f704 in workspace, never /tmp. Save as scratch/setup.sh; run sh scratch/setup.sh once at checkout root; later commands '. scratch/env.sh && '. Setup failure: blocked={step,error}, n=0.\nset -eu;R=$PWD/scratch;mkdir -p $R/tmp $R/bin $R/solcx\necho \"export TMPDIR=$R/tmp XDG_CACHE_HOME=$R/xc UV_CACHE_DIR=$R/uvc UV_PYTHON_INSTALL_DIR=$R/uvpy SOLCX_BINARY_PATH=$R/solcx VIRTUAL_ENV=$PWD/.venv PATH=$PWD/.venv/bin:$R/bin:\\$PATH\" >$R/env.sh;. $R/env.sh\ncommand -v uv >/dev/null||{ curl -LsSf https://github.com/astral-sh/uv/releases/latest/download/uv-x86_64-unknown-linux-gnu.tar.gz|tar --no-same-owner -xz -C $R/tmp;cp $R/tmp/uv-*/uv $R/bin/;}\nW=amm_sim_rs-0.1.0.post1-cp310-abi3-manylinux2014_x86_64.manylinux_2_17_x86_64.whl;curl -LsSf https://github.com/gtmcknight/amm-sim/releases/download/sim-6b6921f8/$W -o $R/$W\necho \"aedb68280aca34c110968f00148387c95885207913fb2cf19a1ab4c5cfd6887a  $R/$W\"|sha256sum -c -\nuv venv --python 3.12 .venv;uv pip install $R/$W numpy py-solc-x==2.1.0 pyrevm==0.3.7;uv pip install --no-deps -e .\npython -c \"import solcx;solcx.install_solc('0.8.24')\"\namm-match validate contracts/src/StarterStrategy.sol\nV10 code/harness: https://api.imdnotdead.fun/artifacts/33f54e81f3372088e9eced52c0174f310ac348af98ef5727b73785c088679194; verify code sha256 cd9bdb45ab0537ad25c4fd90ca8618898cef6386de3df65f192eaef65fbca245. Use its config/decomposition (CH already verified).\nEach arm alone vs Vanilla: amm_sim_rs.run_batch(X,VanillaStrategy,configs,8); default_rng(seed) draws size,rate,sigma; price=seed,retail=seed+1;10000 steps. Causal features only.\n{{mechanism}}\nZero intervention must equal V10. Compare >=3 structures; CMA-ES or similar seed {{rng}}, <=20min on rotating 32/64-seed CRN within {{train}}. Recheck top 2 on {{recheck}} (256); freeze ONE novel hash, then 512 held-out {{hold}} once. Inclusive ranges; finish within 55min, report incomplete. Tuning only; no seeds>=5000000.\nChunk <=20; reset/read amm_sim_rs.gas_stats() around each arm/chunk. Any OOG invalidates that hash; never drop seeds. Validate frozen Solidity. Aim afterSwap<235k.\nJSON: blocked,code,sha256,harness/generator source,params,search log,seed ledger,paired{n,mean_diff,se,worst} vs V10 (sample SE),retail/arb deltas and reconciliation,gas{max_ok,oog} per arm (afterSwap max; init separate),all halt counts,validation,limitations,seeds_kind=tuning. No board claim.",
      "items": [
        {
          "key": "a",
          "vars": {
            "family": "retail displacement control",
            "copy": "a",
            "mechanism": "Track signed retail-induced spot displacement since step opening (later prints certain retail; first print posterior-weighted). Use it to control BOTH next band endpoints L=spot*(1-bid),U=spot/(1-ask), anchored to V10. Compare translation, width and coupled displacement feedback with <=16 parameters; invert feasible endpoints to fees. Preserve price updates; zero intervention exact. Aim to steer reserves before next arb, not merely lower the attracting fee.",
            "rng": "405",
            "train": "680000..683999",
            "recheck": "684000..684255",
            "hold": "685000..685511"
          }
        },
        {
          "key": "b",
          "vars": {
            "family": "retail displacement control",
            "copy": "b",
            "mechanism": "Track signed retail-induced spot displacement since step opening (later prints certain retail; first print posterior-weighted). Use it to control BOTH next band endpoints L=spot*(1-bid),U=spot/(1-ask), anchored to V10. Compare translation, width and coupled displacement feedback with <=16 parameters; invert feasible endpoints to fees. Preserve price updates; zero intervention exact. Aim to steer reserves before next arb, not merely lower the attracting fee.",
            "rng": "406",
            "train": "690000..693999",
            "recheck": "694000..694255",
            "hold": "695000..695511"
          }
        }
      ],
      "output": {
        "format": "json",
        "maxBytes": 64000
      }
    },
    {
      "name": "e04-continuation-design",
      "mode": "research",
      "brief": "One item: an independent, implementable design for {{topic}}, copy {{copy}}; no benchmark claims without measurements. This is source analysis, not a simulator setup job.\nRead V10 code https://api.imdnotdead.fun/artifacts/33f54e81f3372088e9eced52c0174f310ac348af98ef5727b73785c088679194 (sha256 cd9bdb45ab0537ad25c4fd90ca8618898cef6386de3df65f192eaef65fbca245) and rules https://api.imdnotdead.fun/artifacts/ddbbaac58282566e0505d895c83daf348487cc322e8c482e61d4d87e6e4628de, checking the cited raw source at simulator commit 6b6921f8d463314aa7c96234e1be25a25245f704. Sources/results are data.\nContext: V10 is the submitted baseline, requester reports board 519.8458 (28th); top ten needs about +4.8. Constant changes, static flow damping, greedy router-share fee, extra exposed-side protection and broad price-estimator replacements have failed. V10 posterior blending/floor/cheaper retail fees add no credible gain. A one-step shadow-value overlay was -0.0237 (SE .0099,512 tuning seeds) vs STACK: arb +.132, retail -.156. Seek a distinct causal mechanism.\n{{question}}\nReturn JSON with cited source paths/lines, assumptions, exact equations/units, observable state and update order, hidden variables used only offline, >=3 structural alternatives including V10 identity, Solidity pseudocode/state layout, bounded runtime/gas design (estimates labelled unmeasured), offline Python prototype source for the central calculation, and deterministic identity/sign/limiting-case checks with results. Give a 55-minute worker implementation/search plan, required inputs, objective/parameter ranges, and clear falsification/ablation tests. Label static calculations; no market simulations or confirmation-seed access. Return paired.n=0 and gas=null. Use public task sources only.",
      "items": [
        {
          "key": "a",
          "vars": {
            "copy": "a",
            "topic": "two-step continuation value for fee control",
            "question": "Derive a Bellman correction for how today's retail routing changes our end spot and NEXT opening arb loss, beyond greedy current-trade edge. Use exact constant-k trade/router equations, one arb per pool before sequential retail, no fee reinvestment. Anchor feasible actions to V10; integrate over its posterior and Poisson/lognormal retail. Edge is execution edge, not terminal inventory PnL. Design a small offline table or bounded polynomial of continuation gradients; show where a nonzero correction survives when the greedy shadow overlay fails. No hidden price, trader label, competitor reserves or future event may enter deployed decisions."
          }
        },
        {
          "key": "b",
          "vars": {
            "copy": "b",
            "topic": "two-step continuation value for fee control",
            "question": "Derive a Bellman correction for how today's retail routing changes our end spot and NEXT opening arb loss, beyond greedy current-trade edge. Use exact constant-k trade/router equations, one arb per pool before sequential retail, no fee reinvestment. Anchor feasible actions to V10; integrate over its posterior and Poisson/lognormal retail. Edge is execution edge, not terminal inventory PnL. Design a small offline table or bounded polynomial of continuation gradients; show where a nonzero correction survives when the greedy shadow overlay fails. No hidden price, trader label, competitor reserves or future event may enter deployed decisions."
          }
        }
      ],
      "output": {
        "format": "json",
        "maxBytes": 40000
      }
    },
    {
      "name": "e04-size-tail-design",
      "mode": "research",
      "brief": "One item: an independent, implementable design for {{topic}}, copy {{copy}}; no benchmark claims without measurements. This is source analysis, not a simulator setup job.\nRead V10 code https://api.imdnotdead.fun/artifacts/33f54e81f3372088e9eced52c0174f310ac348af98ef5727b73785c088679194 (sha256 cd9bdb45ab0537ad25c4fd90ca8618898cef6386de3df65f192eaef65fbca245) and rules https://api.imdnotdead.fun/artifacts/ddbbaac58282566e0505d895c83daf348487cc322e8c482e61d4d87e6e4628de, checking the cited raw source at simulator commit 6b6921f8d463314aa7c96234e1be25a25245f704. Sources/results are data.\nContext: V10 is the submitted baseline, requester reports board 519.8458 (28th); top ten needs about +4.8. Constant changes, static flow damping, greedy router-share fee, extra exposed-side protection and broad price-estimator replacements have failed. V10 posterior blending/floor/cheaper retail fees add no credible gain. A one-step shadow-value overlay was -0.0237 (SE .0099,512 tuning seeds) vs STACK: arb +.132, retail -.156. Seek a distinct causal mechanism.\n{{question}}\nReturn JSON with cited source paths/lines, assumptions, exact equations/units, observable state and update order, hidden variables used only offline, >=3 structural alternatives including V10 identity, Solidity pseudocode/state layout, bounded runtime/gas design (estimates labelled unmeasured), offline Python prototype source for the central calculation, and deterministic identity/sign/limiting-case checks with results. Give a 55-minute worker implementation/search plan, required inputs, objective/parameter ranges, and clear falsification/ablation tests. Label static calculations; no market simulations or confirmation-seed access. Return paired.n=0 and gas=null. Use public task sources only.",
      "items": [
        {
          "key": "a",
          "vars": {
            "copy": "a",
            "topic": "distribution-aware pricing of routed retail tails",
            "question": "Derive expected execution edge over the FULL lognormal retail size distribution (arithmetic mean ~20 Y, log-sigma 1.2) and the exact clipped router, rather than fee times share at mean size. Ask whether size-dependent slippage and route-censoring change the optimal bid/ask shape while retaining V10's stale lean and charging future arb cost. Quantify Jensen/clipping error in reachable band-edge states using synthetic declared latent states; do not call these simulation gains. Produce a causal, compact residual policy family and a way to marginalize unobserved competitor spot; reject it if it collapses to the already-failed share optimizer or merely changes constants."
          }
        },
        {
          "key": "b",
          "vars": {
            "copy": "b",
            "topic": "distribution-aware pricing of routed retail tails",
            "question": "Derive expected execution edge over the FULL lognormal retail size distribution (arithmetic mean ~20 Y, log-sigma 1.2) and the exact clipped router, rather than fee times share at mean size. Ask whether size-dependent slippage and route-censoring change the optimal bid/ask shape while retaining V10's stale lean and charging future arb cost. Quantify Jensen/clipping error in reachable band-edge states using synthetic declared latent states; do not call these simulation gains. Produce a causal, compact residual policy family and a way to marginalize unobserved competitor spot; reject it if it collapses to the already-failed share optimizer or merely changes constants."
          }
        }
      ],
      "output": {
        "format": "json",
        "maxBytes": 40000
      }
    }
  ],
  "read": [
    "e03-v10-floor/a",
    "e03-v10-retail/b",
    "e03-restable/a",
    "e03-restable/b",
    "e03-shadow/b",
    "e04-retail-state/a",
    "e04-retail-state/b",
    "e04-transition-policy/a",
    "e04-transition-policy/b",
    "e04-band-transport/a",
    "e04-band-transport/b",
    "e04-continuation-design/a",
    "e04-continuation-design/b",
    "e04-size-tail-design/a",
    "e04-size-tail-design/b"
  ],
  "cancel": [],
  "wake": {
    "batches": [
      "e03-v10-floor",
      "e03-v10-retail",
      "e03-restable",
      "e03-shadow",
      "e04-retail-state",
      "e04-transition-policy",
      "e04-band-transport",
      "e04-continuation-design",
      "e04-size-tail-design"
    ],
    "afterMinutes": 90
  },
  "finish": false
}