```json
{
"rows": [
{"key":"item-arb-by-order-class","measurement":"Ran B (sha baef955e...) on seeds 230000..230999 with default ChallengeConfig/ParameterVariance, one run_batch per seed, serial in-process (several OS processes on disjoint seed ranges). Instrumentation: a copy of B's source with tag-only edits (each out.append(PlaceOrder(...)) wrapped by an identity function that records its class; ammo branch label recorded in a dict), plus wrappers on PredictionMarket.place_order (map new order_id -> class) and record_participant_fills (recompute each fill's edge with the simulator's own formula, split by aggressor retail/arb, then call the original). Outcomes unchanged: total/retail/arb/failed identical on seeds 230000..230019 with and without instrumentation; per-seed class sums reconcile to total_edge within 4e-9 on all 1000 seeds. count = number of participant fills in the class across all 1000 sims. Source: .imd/reads/artifacts/item-arb-by-order-class (SHA-256 8fc7f952ebb4fe7fcf175eab2c0ecafecdb954f41763792157eca477dee7f2cc); all row fields copied from this item except next truncated in suggests. Instrumented/uninstrumented equality reported for total, retail, arb and failed on 230000..230019. Class edges are rounded as supplied; probes is an overlapping combined row. Attribution does not measure indirect inventory value or removal gains.","seeds":"230000..230999","n":1000,"complete":true,"incumbent":{"mean":87.289,"retail_mean":112.406,"arb_mean":-25.117,"se":4.828},"findings":[{"sims_with_fills":993,"shares_per_sim":3943.67,"mean":14.487,"se":0.623,"retail_mean":21.929,"retail_se":0.7,"arb_mean":-7.442,"arb_se":0.265,"share_of_total":0.166,"share_of_retail":0.1951,"share_of_arb":0.2963,"class":"main_bid","name":"main bid","count":200626},{"sims_with_fills":994,"shares_per_sim":6481.88,"mean":78.74,"se":4.935,"retail_mean":90.001,"retail_se":4.769,"arb_mean":-11.262,"arb_se":1.487,"share_of_total":0.9021,"share_of_retail":0.8007,"share_of_arb":0.4484,"class":"main_ask","name":"main ask","count":204910},{"sims_with_fills":100,"shares_per_sim":91.45,"mean":-0.757,"se":0.207,"retail_mean":0.0,"retail_se":0.0,"arb_mean":-0.758,"arb_se":0.207,"share_of_total":-0.0087,"share_of_retail":0.0,"share_of_arb":0.0302,"class":"premium_cover","name":"premium cover purchase (ammo branch 2: pays up to ammo_maxpay above p)","count":1750},{"sims_with_fills":157,"shares_per_sim":203.3,"mean":-0.389,"se":0.043,"retail_mean":0.015,"retail_se":0.008,"arb_mean":-0.404,"arb_se":0.043,"share_of_total":-0.0045,"share_of_retail":0.0001,"share_of_arb":0.0161,"class":"cross_at_tick","name":"crossing purchase at the tick p just crossed (ammo branch 1)","count":555},{"sims_with_fills":251,"shares_per_sim":434.98,"mean":-0.157,"se":0.046,"retail_mean":0.347,"retail_se":0.039,"arb_mean":-0.504,"arb_se":0.045,"share_of_total":-0.0018,"share_of_retail":0.0031,"share_of_arb":0.0201,"class":"cross_rest_below","name":"crossing purchase resting one tick under p (ammo branch 3)","count":2016},{"sims_with_fills":355,"shares_per_sim":3764.17,"mean":-4.178,"se":0.669,"retail_mean":0.086,"retail_se":0.039,"arb_mean":-4.263,"arb_se":0.668,"share_of_total":-0.0479,"share_of_retail":0.0008,"share_of_arb":0.1697,"class":"tick1_bank","name":"tick-1 bank (q1)","count":664},{"sims_with_fills":1000,"shares_per_sim":22.38,"mean":-0.224,"se":0.004,"retail_mean":0.013,"retail_se":0.0,"arb_mean":-0.238,"arb_se":0.004,"share_of_total":-0.0026,"share_of_retail":0.0001,"share_of_arb":0.0095,"class":"probe_bid","name":"probe bids","count":2238249},{"sims_with_fills":1000,"shares_per_sim":22.97,"mean":-0.234,"se":0.004,"retail_mean":0.013,"retail_se":0.0,"arb_mean":-0.247,"arb_se":0.005,"share_of_total":-0.0027,"share_of_retail":0.0001,"share_of_arb":0.0098,"class":"probe_ask","name":"probe asks","count":2297010},{"sims_with_fills":0,"shares_per_sim":0.0,"mean":0.0,"se":0.0,"retail_mean":0.0,"retail_se":0.0,"arb_mean":0.0,"arb_se":0.0,"share_of_total":0.0,"share_of_retail":0.0,"share_of_arb":-0.0,"class":"other","name":"other (pre branch; disabled, pre=0)","count":0},{"sims_with_fills":1000,"shares_per_sim":45.35,"mean":-0.458,"se":0.008,"retail_mean":0.026,"retail_se":0.0,"arb_mean":-0.484,"arb_se":0.008,"share_of_total":-0.0052,"share_of_retail":0.0002,"share_of_arb":0.0193,"class":"probes","name":"probes, bid+ask combined","count":4535259}],"paired":null,"suggests":"[\"Remove or gate the tick-1 bank (ydf1=0, or only when the competitor spread s>1): it shows -4.18 +/- 0.67 per sim directly (arb -4.26, retail +0.09), 17% of all arbitrage loss for 0.1% of retail. Its indirect value (YES it supplies to cover low main asks) is not measured here, so a paired A/B is needed; at stake up to ~4 per sim.\",\"Cut adverse selection on the main quotes, which carry 75% of arb loss: main ask -11.26/sim (45%) and main bid -7.44/sim (30%). A jump/stale-quote guard (pull or shri","failures":0,"flag":null},
{"key":"item-arb-jump-vs-diffusion","measurement":"Measurement only; no candidate or oracle. Run the verified incumbent with the pinned simulator and default ChallengeConfig()/ParameterVariance(), 2000 steps. Observe the original process Poisson sampler return (without extra RNG draws), pre-arbitrage participant resting orders, and changes in the original rounded fill statistics. Split steps by sampled jump_count > 0 and abs(p_after - p_before)/0.01. All counts and loss decompositions are computed from these observed runs. Source: .imd/reads/artifacts/item-arb-jump-vs-diffusion (SHA-256 9e831b8ddd223445b0d255d071274a756388cb571399981f842527057bb47ce8); all row fields copied from this item except next truncated in suggests. Full SimulationResult equality on 231000..231019 is documented in tried/instrumentation_invariance. Six partition rows are exhaustive; jump_marginal, move_marginal and total overlap them. A jump step includes simultaneous diffusion; loss is not causal jump damage. Exposure is remaining share-step quantity before arbitrage, including probes and orders behind competitor liquidity; it is not unique shares or exclusively fillable stale size. Bucket means include zero contributions; SE uses simulation-level totals.","seeds":{"start":231000,"end_inclusive":231999,"selection":"Only 231000..231999; first 20 also used for timing and invariance, included once in the measurement. No finalist or tuning seeds used."},"n":1000,"complete":true,"incumbent":{"mean":104.8837684753613,"retail_mean":131.8803069620652,"arb_mean":-26.9965384866824,"se":5.407865958515319},"findings":[{"name":"jump/under_1_tick","group":"partition","count":783,"mean":0.11921374386430028,"retail_mean":0.19349065066209997,"arb_mean":-0.07427690679790001,"se":0.07772616626287002,"retail_se":0.06820735257100603,"arb_se":0.03906530781974436,"loss_per_simulation":0.07427690679790001,"loss_se":0.03906530781974436,"loss_total":74.27690679790001,"arb_fill_steps":783,"arb_fill_count":1589,"arb_filled_shares_total":38558.61,"exposed_shares_total":1667456.05,"exposed_shares_per_simulation":1667.45605,"exposed_shares_per_simulation_se":229.90046822437813,"exposed_shares_per_bucket_step":2129.5734993614305,"bid_exposed_shares_total":1128086.56,"ask_exposed_shares_total":539369.49,"exposed_reserved_cash_total":25951.607,"exposed_reserved_cash_per_bucket_step":33.14381481481482,"mean_abs_move_ticks":0.29948880249015847,"fraction_of_arb_loss":0.00275134928259567,"fraction_of_steps":0.0003915},{"name":"jump/1_to_3_ticks","group":"partition","count":587,"mean":-2.8402300387161,"retail_mean":0.016602402015099944,"arb_mean":-2.8568324407311,"se":0.6152018420920318,"retail_se":0.0060686346907739205,"arb_se":0.6152721009525788,"loss_per_simulation":2.8568324407311,"loss_se":0.6152721009525788,"loss_total":2856.8324407311,"arb_fill_steps":587,"arb_fill_count":1502,"arb_filled_shares_total":415666.4,"exposed_shares_total":1641120.09,"exposed_shares_per_simulation":1641.12009,"exposed_shares_per_simulation_se":261.7061694030458,"exposed_shares_per_bucket_step":2795.77528109029,"bid_exposed_shares_total":1522748.91,"ask_exposed_shares_total":118371.18000000001,"exposed_reserved_cash_total":24353.671,"exposed_reserved_cash_per_bucket_step":41.48836626916525,"mean_abs_move_ticks":1.9225741390871467,"fraction_of_arb_loss":0.10582217576302969,"fraction_of_steps":0.0002935},{"name":"jump/over_3_ticks","group":"partition","count":2429,"mean":-10.583925657796,"retail_mean":0.128442871021,"arb_mean":-10.7123685288176,"se":1.3219879934759777,"retail_se":0.024421927773468466,"arb_se":1.3229250183845678,"loss_per_simulation":10.7123685288176,"loss_se":1.3229250183845678,"loss_total":10712.3685288176,"arb_fill_steps":2427,"arb_fill_count":6282,"arb_filled_shares_total":233957.51,"exposed_shares_total":1071415.43,"exposed_shares_per_simulation":1071.41543,"exposed_shares_per_simulation_se":172.50302127356994,"exposed_shares_per_bucket_step":441.09321943186495,"bid_exposed_shares_total":966433.78,"ask_exposed_shares_total":104981.65,"exposed_reserved_cash_total":33161.0708,"exposed_reserved_cash_per_bucket_step":13.652149361877317,"mean_abs_move_ticks":13.786545475027834,"fraction_of_arb_loss":0.39680526205617417,"fraction_of_steps":0.0012145},{"name":"diffusion_only/under_1_tick","group":"partition","count":1696953,"mean":115.6263539296799,"retail_mean":125.8990984814123,"arb_mean":-10.2727445517218,"se":5.367810255104521,"retail_se":5.665158629381075,"arb_se":0.5619592052739708,"loss_per_simulation":10.2727445517218,"loss_se":0.5619592052739708,"loss_total":10272.7445517218,"arb_fill_steps":1696123,"arb_fill_count":3679306,"arb_filled_shares_total":7939691.879999912,"exposed_shares_total":2192913440.0199203,"exposed_shares_per_simulation":2192913.4400199205,"exposed_shares_per_simulation_se":145582.89966257673,"exposed_shares_per_bucket_step":1292.265277836169,"bid_exposed_shares_total":1781787306.3699563,"ask_exposed_shares_total":411126133.64999855,"exposed_reserved_cash_total":41499737.62970011,"exposed_reserved_cash_per_bucket_step":24.455443155880044,"mean_abs_move_ticks":0.3086847012697273,"fraction_of_arb_loss":0.380520804798342,"fraction_of_steps":0.8484765},{"name":"diffusion_only/1_to_3_ticks","group":"partition","count":282163,"mean":3.007378558073999,"retail_mean":5.447752184472999,"arb_mean":-2.4403736263893,"se":0.18678987637650601,"retail_se":0.23168195289528692,"arb_se":0.08806768024762221,"loss_per_simulation":2.4403736263893,"loss_se":0.08806768024762221,"loss_total":2440.3736263893,"arb_fill_steps":282028,"arb_fill_count":636848,"arb_filled_shares_total":541810.2599999978,"exposed_shares_total":11266047.250000004,"exposed_shares_per_simulation":11266.047250000003,"exposed_shares_per_simulation_se":464.45359741920544,"exposed_shares_per_bucket_step":39.927443534410976,"bid_exposed_shares_total":7391468.770000047,"ask_exposed_shares_total":3874578.4800000535,"exposed_reserved_cash_total":1935737.8233000021,"exposed_reserved_cash_per_bucket_step":6.86035314091501,"mean_abs_move_ticks":1.486112797272648,"fraction_of_arb_loss":0.09039579750541557,"fraction_of_steps":0.1410815},{"name":"diffusion_only/over_3_ticks","group":"partition","count":17085,"mean":-0.44502205974480047,"retail_mean":0.19492037248170035,"arb_mean":-0.6399424322247003,"se":0.04683915922429365,"retail_se":0.02262002598159506,"arb_se":0.057715347548313485,"loss_per_simulation":0.6399424322247003,"loss_se":0.057715347548313485,"loss_total":639.9424322247003,"arb_fill_steps":17081,"arb_fill_count":36619,"arb_filled_shares_total":46761.44999999999,"exposed_shares_total":142190.70999999973,"exposed_shares_per_simulation":142.19070999999974,"exposed_shares_per_simulation_se":11.166427569319405,"exposed_shares_per_bucket_step":8.322546678372825,"bid_exposed_shares_total":85245.44999999991,"ask_exposed_shares_total":56945.25999999991,"exposed_reserved_cash_total":26118.0262,"exposed_reserved_cash_per_bucket_step":1.5287109277143693,"mean_abs_move_ticks":4.756807080750602,"fraction_of_arb_loss":0.023704610594443017,"fraction_of_steps":0.0085425},{"name":"jump","group":"jump_marginal","count":3799,"mean":-13.3049419526478,"retail_mean":0.3385359236981999,"arb_mean":-13.6434778763466,"se":1.46052840506327,"retail_se":0.07261460131358026,"arb_se":1.460653881628571,"loss_per_simulation":13.6434778763466,"loss_se":1.460653881628571,"loss_total":13643.4778763466,"arb_fill_steps":3797,"arb_fill_count":9373,"arb_filled_shares_total":688182.52,"exposed_shares_total":4379991.57,"exposed_shares_per_simulation":4379.99157,"exposed_shares_per_simulation_se":460.5300524618885,"exposed_shares_per_bucket_step":1152.932763885233,"bid_exposed_shares_total":3617269.25,"ask_exposed_shares_total":762722.3200000001,"exposed_reserved_cash_total":83466.34879999999,"exposed_reserved_cash_per_bucket_step":21.9706103711503,"mean_abs_move_ticks":9.173616665132023,"fraction_of_arb_loss":0.5053787871017995,"fraction_of_steps":0.0018995},{"name":"diffusion_only","group":"jump_marginal","count":1996201,"mean":118.18871042800909,"retail_mean":131.541771038367,"arb_mean":-13.3530606103358,"se":5.402332238991651,"retail_se":5.688377013865789,"arb_se":0.5668059865884191,"loss_per_simulation":13.3530606103358,"loss_se":0.5668059865884191,"loss_total":13353.0606103358,"arb_fill_steps":1995232,"arb_fill_count":4352773,"arb_filled_shares_total":8528263.58999991,"exposed_shares_total":2204321677.9799204,"exposed_shares_per_simulation":2204321.6779799205,"exposed_shares_per_simulation_se":145572.5391928795,"exposed_shares_per_bucket_step":1104.2583777785505,"bid_exposed_shares_total":1789264020.5899563,"ask_exposed_shares_total":415057657.3899986,"exposed_reserved_cash_total":43461593.47920011,"exposed_reserved_cash_per_bucket_step":21.772152944117405,"mean_abs_move_ticks":0.513184556096923,"fraction_of_arb_loss":0.4946212128982006,"fraction_of_steps":0.9981005},{"name":"under_1_tick","group":"move_marginal","count":1697736,"mean":115.7455676735442,"retail_mean":126.0925891320744,"arb_mean":-10.3470214585197,"se":5.375932230203285,"retail_se":5.6766049626285895,"arb_se":0.5742051920321283,"loss_per_simulation":10.3470214585197,"loss_se":0.5742051920321283,"loss_total":10347.021458519699,"arb_fill_steps":1696906,"arb_fill_count":3680895,"arb_filled_shares_total":7978250.489999912,"exposed_shares_total":2194580896.0699205,"exposed_shares_per_simulation":2194580.8960699206,"exposed_shares_per_simulation_se":145684.24591616355,"exposed_shares_per_bucket_step":1292.6514464380332,"bid_exposed_shares_total":1782915392.9299562,"ask_exposed_shares_total":411665503.13999856,"exposed_reserved_cash_total":41525689.23670011,"exposed_reserved_cash_per_bucket_step":24.45945025416208,"mean_abs_move_ticks":0.3086804600986946,"fraction_of_arb_loss":0.3832721540809376,"fraction_of_steps":0.848868},{"name":"1_to_3_ticks","group":"move_marginal","count":282750,"mean":0.16714851935789887,"retail_mean":5.464354586488099,"arb_mean":-5.2972060671204,"se":0.6524657601919367,"retail_se":0.2326519365578999,"arb_se":0.6150255928589595,"loss_per_simulation":5.2972060671204,"loss_se":0.6150255928589595,"loss_total":5297.2060671204,"arb_fill_steps":282615,"arb_fill_count":638350,"arb_filled_shares_total":957476.6599999978,"exposed_shares_total":12907167.340000004,"exposed_shares_per_simulation":12907.167340000004,"exposed_shares_per_simulation_se":528.1815771993391,"exposed_shares_per_bucket_step":45.64869085764811,"bid_exposed_shares_total":8914217.680000046,"ask_exposed_shares_total":3992949.6600000532,"exposed_reserved_cash_total":1960091.494300002,"exposed_reserved_cash_per_bucket_step":6.932242243324499,"mean_abs_move_ticks":1.4870189079981833,"fraction_of_arb_loss":0.19621797326844523,"fraction_of_steps":0.141375},{"name":"over_3_ticks","group":"move_marginal","count":19514,"mean":-11.0289477175408,"retail_mean":0.32336324350270035,"arb_mean":-11.352310961042301,"se":1.3218281579263844,"retail_se":0.03425357095121604,"arb_se":1.325505037046787,"loss_per_simulation":11.352310961042301,"loss_se":1.325505037046787,"loss_total":11352.3109610423,"arb_fill_steps":19508,"arb_fill_count":42901,"arb_filled_shares_total":280718.96,"exposed_shares_total":1213606.1399999997,"exposed_shares_per_simulation":1213.6061399999999,"exposed_shares_per_simulation_se":172.42691337516828,"exposed_shares_per_bucket_step":62.1915619555191,"bid_exposed_shares_total":1051679.23,"ask_exposed_shares_total":161926.90999999992,"exposed_reserved_cash_total":59279.097,"exposed_reserved_cash_per_bucket_step":3.0377727272727273,"mean_abs_move_ticks":5.880781384312116,"fraction_of_arb_loss":0.4205098726506171,"fraction_of_steps":0.009757},{"name":"all_steps","group":"total","count":2000000,"mean":104.8837684753613,"retail_mean":131.8803069620652,"arb_mean":-26.9965384866824,"se":5.407865958515319,"retail_se":5.70484283158216,"arb_se":1.6782203403036364,"loss_per_simulation":26.9965384866824,"loss_se":1.6782203403036364,"loss_total":26996.5384866824,"arb_fill_steps":1999029,"arb_fill_count":4362146,"arb_filled_shares_total":9216446.10999991,"exposed_shares_total":2208701669.5499206,"exposed_shares_per_simulation":2208701.6695499206,"exposed_shares_per_simulation_se":145826.8204643449,"exposed_shares_per_bucket_step":1104.3508347749603,"bid_exposed_shares_total":1792881289.8399563,"ask_exposed_shares_total":415820379.7099986,"exposed_reserved_cash_total":43545059.82800011,"exposed_reserved_cash_per_bucket_step":21.772529914000057,"mean_abs_move_ticks":0.5296350468880351,"fraction_of_arb_loss":1.0,"fraction_of_steps":1.0}],"paired":null,"suggests":"[{\"change\":\"Tune the Gaussian/sub-tick-estimation loss penalty in AB/qsize separately from the jump-tail penalty, reducing resting size when belief uncertainty puts the quote near the true-price crossing. Test that any saved arbitrage loss exceeds retail edge surrendered.\",\"supported_by\":\"diffusion_only/under_1_tick\",\"edge_at_stake_per_simulation\":10.2727445517218,\"edge_at_stake_se\":0.5619592052739708,\"interpretation\":\"Observed arbitrage-loss pool, an upper bound on gross savings; no net strateg","failures":[],"flag":null},
{"key":"item-edge-by-parameters","measurement":"Measure only incumbent B, with no candidate or oracle. Run the unmodified simulator at b244530ee2a6247b5f930830eeca9dd950da0e7e using load_strategy_factory and exactly one run_batch simulation per seed, default ChallengeConfig() (2000 steps), default ParameterVariance(), workers=1 and no sandbox. Read the sampled parameters already exposed by SimulationResult.regime; no hidden-state patch or changed simulator is needed. Compare unconditional per-simulation total, retail and arbitrage edge across competitor spreads 1..4 and empirical terciles of each continuous parameter. Source: .imd/reads/artifacts/item-edge-by-parameters (SHA-256 06a6f950a1828799dca4fb412a2076f9ab8f459ddf779c79240aba27b2c80a04); all row fields copied from this item except next truncated in suggests. No instrumentation: post-run regime extraction; full replay equality on 232000..232019. Continuous buckets are empirical ranks (334/333/333), independently formed per parameter; these are marginal, unadjusted regime comparisons, not paired gains. Reported contrasts (high minus low, or spread 4 minus 1): [{\"parameter\":\"competitor_spread_ticks\",\"comparison\":\"4 minus 1\",\"mean_diff\":131.0935780273441,\"se\":14.87376399009396,\"retail_diff\":135.74251451723,\"retail_se\":15.496860323845187,\"arb_diff\":-4.648936489922658,\"arb_se\":5.108363320786533},{\"parameter\":\"retail_arrival_rate\",\"comparison\":\"high minus low\",\"mean_diff\":56.176113342923614,\"se\":13.096169456481284,\"retail_diff\":64.61873440661785,\"retail_se\":13.530743998742016,\"arb_diff\":-8.442621063619917,\"arb_se\":4.3897015114025875},{\"parameter\":\"retail_mean_notional\",\"comparison\":\"high minus low\",\"mean_diff\":49.79535316190703,\"se\":13.058537591145374,\"retail_diff\":55.50247719235145,\"retail_se\":13.794827033882973,\"arb_diff\":-5.7071240305340005,\"arb_se\":3.3125168594083236},{\"parameter\":\"jump_intensity\",\"comparison\":\"high minus low\",\"mean_diff\":-16.81015454297436,\"se\":13.259279793508007,\"retail_diff\":-16.455813360604424,\"retail_se\":14.137785761292585,\"arb_diff\":-0.35434118248069524,\"arb_se\":3.3226077238006564},{\"parameter\":\"jump_sigma\",\"comparison\":\"high minus low\",\"mean_diff\":-33.688143856658485,\"se\":12.913489970696236,\"retail_diff\":-32.16848945581218,\"retail_se\":13.798723859423829,\"arb_diff\":-1.5196544009374264,\"arb_se\":3.5751523261152864}]","seeds":{"start":232000,"end_inclusive":232999,"verification_replayed_start":232000,"verification_replayed_end_inclusive":232019,"forbidden_finalist_seeds_run":false},"n":1000,"complete":true,"incumbent":{"mean":98.308080281751,"retail_mean":121.3989136260664,"arb_mean":-23.090833344324,"se":5.30736292666585},"findings":[{"name":"competitor_spread_ticks:1","parameter":"competitor_spread_ticks","bucket":"1","sample_min":1,"sample_max":1,"attempted":260,"failures":0,"count":260,"mean":39.52276107669692,"se":7.008355130308519,"retail_mean":60.59958368858538,"retail_se":7.815288276984682,"arb_mean":-21.076822611870384,"arb_se":4.2979096447434735},{"name":"competitor_spread_ticks:2","parameter":"competitor_spread_ticks","bucket":"2","sample_min":2,"sample_max":2,"attempted":250,"failures":0,"count":250,"mean":71.7659088850952,"se":7.617734657988405,"retail_mean":93.2407364520572,"retail_se":8.414715776487153,"arb_mean":-21.4748275669524,"arb_se":2.4431444345925155},{"name":"competitor_spread_ticks:3","parameter":"competitor_spread_ticks","bucket":"3","sample_min":3,"sample_max":3,"attempted":217,"failures":0,"count":217,"mean":108.35218712042764,"se":11.234423190441198,"retail_mean":132.40297209139308,"retail_se":12.027725220872485,"arb_mean":-24.050784971014284,"arb_se":2.501080909761385},{"name":"competitor_spread_ticks:4","parameter":"competitor_spread_ticks","bucket":"4","sample_min":4,"sample_max":4,"attempted":273,"failures":0,"count":273,"mean":170.61633910404103,"se":13.119139209585898,"retail_mean":196.34209820581538,"retail_se":13.381851480433975,"arb_mean":-25.72575910179304,"arb_se":2.7610411990367414},{"name":"retail_arrival_rate:low","parameter":"retail_arrival_rate","bucket":"low","sample_min":0.15443989293514482,"sample_max":0.21916290059771437,"attempted":334,"failures":0,"count":334,"mean":66.06069019426107,"se":6.2737369801983744,"retail_mean":86.42020577804041,"retail_se":6.760014894332707,"arb_mean":-20.359515583832934,"arb_se":2.273779647645315},{"name":"retail_arrival_rate:middle","parameter":"retail_arrival_rate","bucket":"middle","sample_min":0.2193696884664271,"sample_max":0.28771501984569015,"attempted":333,"failures":0,"count":333,"mean":106.72358612307897,"se":8.815026425851864,"retail_mean":126.8426360802093,"retail_se":9.66889238901041,"arb_mean":-20.119049957123124,"arb_se":1.723666659953332},{"name":"retail_arrival_rate:high","parameter":"retail_arrival_rate","bucket":"high","sample_min":0.287935927817049,"sample_max":0.35193269318462606,"attempted":333,"failures":0,"count":333,"mean":122.23680353718468,"se":11.495646077370541,"retail_mean":151.03894018465826,"retail_se":11.721059328742136,"arb_mean":-28.80213664745285,"arb_se":3.754917505507159},{"name":"retail_mean_notional:low","parameter":"retail_mean_notional","bucket":"low","sample_min":2.6452857620506944,"sample_max":3.9262247798901484,"attempted":334,"failures":0,"count":334,"mean":68.11309839704222,"se":6.991826075819572,"retail_mean":86.62213578533203,"retail_se":7.185599545075426,"arb_mean":-18.509037388222154,"arb_se":2.2992026797664127},{"name":"retail_mean_notional:middle","parameter":"retail_mean_notional","bucket":"middle","sample_min":3.9282269322812957,"sample_max":5.094086281721342,"attempted":333,"failures":0,"count":333,"mean":108.99336651053693,"se":8.913789495439584,"retail_mean":135.55442688347418,"retail_se":9.33360112123878,"arb_mean":-26.56106037300901,"arb_se":3.3631708364322597},{"name":"retail_mean_notional:high","parameter":"retail_mean_notional","bucket":"high","sample_min":5.09968489148911,"sample_max":6.329676759574152,"attempted":333,"failures":0,"count":333,"mean":117.90845155894925,"se":11.029042213394883,"retail_mean":142.12461297768348,"retail_se":11.775585423772371,"arb_mean":-24.216161418756155,"arb_se":2.38462470448063},{"name":"jump_intensity:low","parameter":"jump_intensity","bucket":"low","sample_min":0.000805597859855233,"sample_max":0.001548516396877783,"attempted":334,"failures":0,"count":334,"mean":107.42737229453653,"se":10.719835892687295,"retail_mean":129.29043309722874,"retail_se":11.450837155634366,"arb_mean":-21.863060802670358,"arb_se":2.1035584851617277},{"name":"jump_intensity:middle","parameter":"jump_intensity","bucket":"middle","sample_min":0.0015493788082731937,"sample_max":0.002335101129155772,"attempted":333,"failures":0,"count":333,"mean":96.85226553785465,"se":8.808773649577882,"retail_mean":122.04798978767597,"retail_se":9.066331397069737,"arb_mean":-25.19572424978018,"arb_se":3.3663725558609974},{"name":"jump_intensity:high","parameter":"jump_intensity","bucket":"high","sample_min":0.0023356809684818612,"sample_max":0.002999967173767041,"attempted":333,"failures":0,"count":333,"mean":90.61721775156217,"se":7.803436363319875,"retail_mean":112.83461973662432,"retail_se":8.291882456194783,"arb_mean":-22.217401985151053,"arb_se":2.5719183085323443},{"name":"jump_sigma:low","parameter":"jump_sigma","bucket":"low","sample_min":0.20011205593936066,"sample_max":0.3302169013210605,"attempted":334,"failures":0,"count":334,"mean":117.07727275212515,"se":9.81144848001626,"retail_mean":139.7238287596464,"retail_se":10.531821748659302,"arb_mean":-22.646556007462575,"arb_se":1.652254133495155},{"name":"jump_sigma:middle","parameter":"jump_sigma","bucket":"middle","sample_min":0.3310836477965312,"sample_max":0.46575487961144846,"attempted":333,"failures":0,"count":333,"mean":94.40147525630871,"se":9.241874873094424,"retail_mean":116.86254303954264,"retail_se":9.515718098762841,"arb_mean":-22.461067783286186,"arb_se":3.1009040444450298},{"name":"jump_sigma:high","parameter":"jump_sigma","bucket":"high","sample_min":0.465884928061146,"sample_max":0.599652885814436,"attempted":333,"failures":0,"count":333,"mean":83.38912889546667,"se":8.396052759913966,"retail_mean":107.55533930383423,"retail_se":8.915464699223444,"arb_mean":-24.1662104084,"arb_se":3.1704527174010524}],"paired":null,"suggests":"[{\"change\":\"Test spread-conditioned adverse-selection sizing: raise the arbitrage-loss multiplier kA for inferred competitor spread 1, while retaining tiny probability probes. Tune the multiplier on separate seeds, checking that saved arbitrage loss exceeds sacrificed retail edge.\",\"support\":\"Narrow-spread markets have a much larger arbitrage-loss share of gross retail edge than wide-spread markets. This is a descriptive regime comparison, not evidence that reducing size improves score.\",\"edge_a","failures":[],"flag":null},
{"key":"item-edge-by-price-and-time","measurement":"Measurement only: B unchanged; partition every participant fill by post-process-step true probability used for edge scoring, crossed with its 0-based fill step. Twenty cross-bucket rows followed by five probability and four step marginals. Default ChallengeConfig() and ParameterVariance(), 2000 steps; one serial, unsandboxed run_batch call per seed. Separate OS processes run disjoint seed ranges. No candidate and no oracle. Source: .imd/reads/artifacts/item-edge-by-price-and-time (SHA-256 2ca81d4fd458e51dd96161b3e6b5a374b2f4d60daa7993368bde3fd736253977); all row fields copied from this item except next truncated in suggests. Full SimulationResult equality on 233000..233019 is documented in tried. Counts are participant fills, not simulations; means divide bucket sums by all 1000 simulations, including zeros. SE is across per-simulation bucket sums. Twenty cross rows are disjoint; probability and time marginals overlap them. True probability is post-advance at scoring, unavailable to B when quoting; bucket sums use unrounded edges and reconcile within 1e-6. Probability intervals: [0,0.05), [0.05,0.20), [0.20,0.80], (0.80,0.95], (0.95,1]; step intervals inclusive.","seeds":{"start":233000,"end_inclusive":233999,"allowed_end_inclusive":233999,"finalist_seeds_used":false},"n":1000,"complete":true,"incumbent":{"mean":100.4765965316917,"retail_mean":127.1401405735393,"arb_mean":-26.6635440418441,"se":5.23909038504197},"findings":[{"name":"below_5c x 0-199","count":222,"retail_count":41,"arb_count":181,"step_count":73,"simulations_with_steps":2,"mean":0.006855577491567738,"retail_mean":0.014365423415548063,"arb_mean":-0.007509845923980326,"se":0.004848916653813814,"retail_se":0.010216996324606402,"arb_se":0.005472523369017816},{"name":"below_5c x 200-999","count":49204,"retail_count":6919,"arb_count":42285,"step_count":19378,"simulations_with_steps":106,"mean":3.882741386220933,"retail_mean":5.536056792308257,"arb_mean":-1.6533154060873239,"se":0.8494905121452835,"retail_se":0.9304849091162757,"arb_se":0.39275297163000294},{"name":"below_5c x 1000-1799","count":307956,"retail_count":39769,"arb_count":268187,"step_count":136328,"simulations_with_steps":368,"mean":40.4855636546564,"retail_mean":47.648967734137074,"arb_mean":-7.163404079480674,"se":3.176032168928636,"retail_se":3.3940775570264665,"arb_se":0.686703534367906},{"name":"below_5c x 1800-1999","count":166906,"retail_count":22915,"arb_count":143991,"step_count":76836,"simulations_with_steps":523,"mean":29.815404316220164,"retail_mean":32.481671248980156,"arb_mean":-2.666266932759995,"se":1.469334965164831,"retail_se":1.5440976580633496,"arb_se":0.2557929556899085},{"name":"5_to_20c x 0-199","count":11753,"retail_count":1485,"arb_count":10268,"step_count":4453,"simulations_with_steps":73,"mean":0.13921729854555367,"retail_mean":0.24442375845072317,"arb_mean":-0.1052064599051695,"se":0.040870694316552235,"retail_se":0.05133544658938006,"arb_se":0.031745214691970766},{"name":"5_to_20c x 200-999","count":269021,"retail_count":35702,"arb_count":233319,"step_count":100364,"simulations_with_steps":347,"mean":5.996527396593474,"retail_mean":7.1791759583416885,"arb_mean":-1.1826485617482148,"se":0.5302070145001169,"retail_se":0.575311936572953,"arb_se":0.13401721745243214},{"name":"5_to_20c x 1000-1799","count":302239,"retail_count":38063,"arb_count":264176,"step_count":116730,"simulations_with_steps":474,"mean":5.151183700570551,"retail_mean":8.953995686258637,"arb_mean":-3.802811985688084,"se":0.8778408227291201,"retail_se":0.6366330660631273,"arb_se":0.7222358587466211},{"name":"5_to_20c x 1800-1999","count":33558,"retail_count":3530,"arb_count":30028,"step_count":13078,"simulations_with_steps":262,"mean":-0.9809580456786521,"retail_mean":0.6356100387621051,"arb_mean":-1.6165680844407573,"se":0.4932155356702947,"retail_se":0.0760270785231271,"arb_se":0.4988924957996158},{"name":"20_to_80c x 0-199","count":490155,"retail_count":59633,"arb_count":430522,"step_count":191300,"simulations_with_steps":1000,"mean":3.122603220506682,"retail_mean":3.8627701802108834,"arb_mean":-0.7401669597042011,"se":0.1345833041606478,"retail_se":0.1304334454556669,"arb_se":0.06378472579475183},{"name":"20_to_80c x 200-999","count":1394465,"retail_count":166073,"arb_count":1228392,"step_count":561874,"simulations_with_steps":974,"mean":8.318745732500096,"retail_mean":10.648816105014264,"arb_mean":-2.3300703725141676,"se":0.35284762704785433,"retail_se":0.3791831722328163,"arb_se":0.149746877554575},{"name":"20_to_80c x 1000-1799","count":790580,"retail_count":83540,"arb_count":707040,"step_count":295852,"simulations_with_steps":692,"mean":1.6903016218124411,"retail_mean":4.8560682227818734,"arb_mean":-3.1657666009694325,"se":0.5592883477516292,"retail_se":0.25444298096687473,"arb_se":0.5280895921371291},{"name":"20_to_80c x 1800-1999","count":58300,"retail_count":5674,"arb_count":52626,"step_count":23249,"simulations_with_steps":279,"mean":-0.5909176593015093,"retail_mean":0.16559661959494287,"arb_mean":-0.7565142788964522,"se":0.34468442275014927,"retail_se":0.019829892645979043,"arb_se":0.3449006740375586},{"name":"80_to_95c x 0-199","count":10973,"retail_count":1356,"arb_count":9617,"step_count":4154,"simulations_with_steps":68,"mean":0.027444311835372628,"retail_mean":0.04425664736787143,"arb_mean":-0.016812335532498803,"se":0.012070147514704083,"retail_se":0.009282794267889792,"arb_se":0.008874779290477001},{"name":"80_to_95c x 200-999","count":247963,"retail_count":32829,"arb_count":215134,"step_count":96017,"simulations_with_steps":353,"mean":0.736919806080671,"retail_mean":1.0009317616485864,"arb_mean":-0.2640119555679154,"se":0.07122294694688334,"retail_se":0.07596142161873903,"arb_se":0.03135048970853827},{"name":"80_to_95c x 1000-1799","count":269716,"retail_count":33920,"arb_count":235796,"step_count":105987,"simulations_with_steps":456,"mean":0.7888986323464348,"retail_mean":1.0219062135471966,"arb_mean":-0.23300758120076182,"se":0.06754600682965527,"retail_se":0.07359981513151664,"arb_se":0.030984100537623276},{"name":"80_to_95c x 1800-1999","count":34873,"retail_count":3849,"arb_count":31024,"step_count":12870,"simulations_with_steps":244,"mean":-0.264275705250895,"retail_mean":0.10293615986633822,"arb_mean":-0.36721186511723325,"se":0.2934956583450346,"retail_se":0.0130019311196289,"arb_se":0.2933417657021454},{"name":"above_95c x 0-199","count":61,"retail_count":4,"arb_count":57,"step_count":20,"simulations_with_steps":1,"mean":-0.000824646798327617,"retail_mean":0.00013132595524224325,"arb_mean":-0.0009559727535698602,"se":0.0008246467983276171,"retail_se":0.00013132595524224325,"arb_se":0.0009559727535698602},{"name":"above_95c x 200-999","count":57876,"retail_count":7362,"arb_count":50514,"step_count":22367,"simulations_with_steps":116,"mean":0.24734530689915807,"retail_mean":0.29135694631229625,"arb_mean":-0.04401163941313821,"se":0.042778965947857475,"retail_se":0.04484498306184281,"arb_se":0.010965178428460638},{"name":"above_95c x 1000-1799","count":326449,"retail_count":42021,"arb_count":284428,"step_count":145103,"simulations_with_steps":357,"mean":1.5564867158284512,"retail_mean":1.6653567759287848,"arb_mean":-0.10887006010033366,"se":0.11751613091819464,"retail_se":0.12073084632245701,"arb_se":0.011742860167248053},{"name":"above_95c x 1800-1999","count":157658,"retail_count":20264,"arb_count":137394,"step_count":73967,"simulations_with_steps":497,"mean":0.3473339106433988,"retail_mean":0.7857469746501069,"arb_mean":-0.4384130640067081,"se":0.4140755897890107,"retail_se":0.04211665142807186,"arb_se":0.4115569197765718},{"name":"below_5c x all_steps","count":524288,"retail_count":69644,"arb_count":454644,"step_count":232615,"simulations_with_steps":535,"mean":74.19056493458906,"retail_mean":85.68106119884104,"arb_mean":-11.490496264251973,"se":4.695645918293742,"retail_se":5.12902105583206,"arb_se":0.8946531678662225},{"name":"5_to_20c x all_steps","count":616571,"retail_count":78780,"arb_count":537791,"step_count":234625,"simulations_with_steps":614,"mean":10.305970350030927,"retail_mean":17.013205441813152,"arb_mean":-6.707235091782225,"se":1.2339703956918473,"retail_se":1.0836392651412328,"arb_se":0.9355188259346796},{"name":"20_to_80c x all_steps","count":2733500,"retail_count":314920,"arb_count":2418580,"step_count":1072275,"simulations_with_steps":1000,"mean":12.54073291551771,"retail_mean":19.533251127601964,"arb_mean":-6.992518212084254,"se":0.8341306879247998,"retail_se":0.6819668783057375,"arb_se":0.6591560915441962},{"name":"80_to_95c x all_steps","count":563525,"retail_count":71954,"arb_count":491571,"step_count":219028,"simulations_with_steps":596,"mean":1.2889870450115835,"retail_mean":2.1700307824299925,"arb_mean":-0.8810437374184092,"se":0.3160144097433705,"retail_se":0.12739069562066005,"arb_se":0.29661409832581587},{"name":"above_95c x all_steps","count":542044,"retail_count":69651,"arb_count":472393,"step_count":241457,"simulations_with_steps":505,"mean":2.1503412865726803,"retail_mean":2.74259202284643,"arb_mean":-0.5922507362737498,"se":0.4481939554356783,"retail_se":0.1805712654131943,"arb_se":0.4117763193205693},{"name":"all_probabilities x 0-199","count":513164,"retail_count":62519,"arb_count":450645,"step_count":200000,"simulations_with_steps":1000,"mean":3.2952957615808485,"retail_mean":4.1659473354002685,"arb_mean":-0.8706515738194195,"se":0.14397027005599156,"retail_se":0.14440427204981307,"arb_se":0.07226172278399492},{"name":"all_probabilities x 200-999","count":2018529,"retail_count":248885,"arb_count":1769644,"step_count":800000,"simulations_with_steps":1000,"mean":19.18227962829433,"retail_mean":24.65633756362509,"arb_mean":-5.47405793533076,"se":1.1371525739641328,"retail_se":1.2536964449647459,"arb_se":0.44504731645941575},{"name":"all_probabilities x 1000-1799","count":1996940,"retail_count":237313,"arb_count":1759627,"step_count":800000,"simulations_with_steps":1000,"mean":49.67243432521428,"retail_mean":64.14629463265356,"arb_mean":-14.473860307439287,"se":3.329887026489231,"retail_se":3.466765475461729,"arb_se":1.148413480749737},{"name":"all_probabilities x 1800-1999","count":451295,"retail_count":56232,"arb_count":395063,"step_count":200000,"simulations_with_steps":1000,"mean":28.326586816632506,"retail_mean":34.17156104185365,"arb_mean":-5.844974225221145,"se":1.658710153974373,"retail_se":1.5238586762505621,"arb_se":0.8366348309269026}],"paired":null,"suggests":"[{\"change\":\"Test halving main quote sizes (keep tiny probes) during steps 1800-1999 when B estimates a 5-80 cent probability. Apply the endgame gate only to this estimated-probability range so below-5-cent retail capture remains available.\",\"edge_at_stake\":{\"scope\":\"(5_to_20c or 20_to_80c) x 1800-1999\",\"mean\":-1.5718757049801613,\"se\":0.6077257043319831,\"retail_mean\":0.801206658357048,\"retail_se\":0.08102777724151644,\"arb_mean\":-2.3730823633372093,\"arb_se\":0.6117593159530497,\"gross_arb_loss_per_si","failures":{"n":0,"seeds":[]},"flag":null},
{"key":"item-oracle-last-probability","measurement":"Oracle on B (sha baef955e...). Instrumented the unmodified simulator by subclassing engine.JumpDiffusionScoreProcess so the strategy can read process.current_true_probability() at on_step, i.e. the true probability after the previous step's move (p_{t-1}), the state B's sub-tick belief estimates. The oracle copy of B replaces its belief with that value: phat=p_{t-1} (clamped to [1e-4,1-1e-4] instead of B's [0.002,0.998]), var_t=0, belief grid collapsed to the point, and the below-tick-1 time-decay override skipped since p is known. Everything else (sizing, ammo, probes, order management) unchanged. Instrumentation check: B's per-seed total/retail/arb edge on seeds 234000..234019 was byte-identical with and without the hook. Then B and oracle were run on all 1000 seeds 234000..234999 (8 OS processes each over disjoint seed ranges), paired. Source: .imd/reads/artifacts/item-oracle-last-probability (SHA-256 cae9a4e50d8d464a63b25dd1118410f0b186850eedf81e23b6aaac9a820c2851); all row fields copied from this item except next truncated in suggests. Hook invariance on 234000..234019 is reported for exact total/retail/arb edges. Buckets selected by B edge are subject to regression to the mean; overall paired result is not. This is the tested substitution, not an optimal-information upper bound; its clamp and below-tick override also change. No next-step-probability measurement is included in these inputs.","seeds":"234000..234999","n":1000,"complete":true,"incumbent":{"mean":93.127,"retail_mean":119.287,"arb_mean":-26.16,"se":5.206},"findings":[{"name":"B total bottom third: B","count":333,"mean":-10.802,"retail_mean":15.756,"arb_mean":-26.557,"se":4.994},{"name":"B total bottom third: oracle","count":333,"mean":-1.762,"retail_mean":19.972,"arb_mean":-21.734,"se":4.765},{"name":"B total bottom third: oracle minus B","count":333,"mean":9.04,"retail_mean":4.217,"arb_mean":4.823,"se":2.557},{"name":"B total middle third: B","count":333,"mean":35.059,"retail_mean":47.43,"arb_mean":-12.371,"se":0.829},{"name":"B total middle third: oracle","count":333,"mean":40.197,"retail_mean":52.05,"arb_mean":-11.853,"se":1.25},{"name":"B total middle third: oracle minus B","count":333,"mean":5.139,"retail_mean":4.62,"arb_mean":0.518,"se":0.913},{"name":"B total top third: B","count":334,"mean":254.641,"retail_mean":294.151,"arb_mean":-39.511,"se":9.858},{"name":"B total top third: oracle","count":334,"mean":257.366,"retail_mean":294.837,"arb_mean":-37.472,"se":9.731},{"name":"B total top third: oracle minus B","count":334,"mean":2.725,"retail_mean":0.686,"arb_mean":2.039,"se":2.036}],"paired":{"n":1000,"mean_diff":5.632,"se":1.133,"retail_diff":3.172,"arb_diff":2.46},"suggests":"[\"Better current-state estimation is worth at most ~+5.6 per simulation (SE 1.1) for B as built: about +3.2 retail (quoting tighter/larger when the belief is uncertain) and +2.5 arbitrage. Spend it on the filter (e.g. more informative probes or using fill quantities/competitor moves to tighten the sub-tick belief), but expect at most ~+5; most of the +24 wave 3 measured for knowing the NEXT step lies in jump/next-move prediction, not in the current state.\",\"The gain concentrates where B does wor","failures":{"incumbent":0,"oracle":0},"flag":null},
{"key":"item-oracle-jump-parameters","measurement":"Diagnostic oracle only, no deployable candidate: replace only B constants lam_j and sig_j with each simulation's sampled jump_intensity and jump_sigma, including all uses in variance, probability transformation and quote sizing. Leave jump mean, diffusion, retail parameters, beliefs and market mechanics unchanged. Pinned simulator b244530ee2a6247b5f930830eeca9dd950da0e7e; default ChallengeConfig and ParameterVariance, 2000 steps. No finalist seeds used. Source: .imd/reads/artifacts/item-oracle-jump-parameters (SHA-256 66c8d2e960de6467bd3da7ff5d922c80ee2c1c3574db9d0646bc6f6e52168a11); all row fields copied from this item except next truncated in suggests. Full SimulationResult invariance on 235000..235019 is documented in tried. Complete refers to the explicitly selected first-500 timing fallback, not all 1000 requested seeds. This measures the exact substitution into B, not optimal use of known jump parameters. All extremes retained; no finalist evidence.","seeds":{"start":235000,"end_inclusive":235499,"requested_end_inclusive":235999,"selection":"first 500, pilot timing fallback; pilot seeds included exactly once"},"n":500,"complete":true,"incumbent":{"mean":99.564405548491,"retail_mean":121.377638276109,"arb_mean":-21.8132327276214,"se":7.074809839777905},"findings":[{"name":"incumbent/all","count":500,"mean":99.564405548491,"retail_mean":121.377638276109,"arb_mean":-21.8132327276214,"se":7.074809839777905,"paired":{"n":500,"mean_diff":-1.2217662607308004,"se":1.16723731739015,"retail_diff":0.1370086056474002,"arb_diff":-1.358774866365}},{"name":"oracle/all","count":500,"mean":98.34263928776019,"retail_mean":121.5146468817564,"arb_mean":-23.1720075939864,"se":7.1980302606514535,"paired":{"n":500,"mean_diff":-1.2217662607308004,"se":1.16723731739015,"retail_diff":0.1370086056474002,"arb_diff":-1.358774866365}},{"name":"incumbent/lambda<0.0019;sigma<0.4","count":129,"mean":103.75884097994573,"retail_mean":124.31516033672868,"arb_mean":-20.556319356758138,"se":14.343583035322201,"paired":{"n":129,"mean_diff":-2.930324313507753,"se":4.395025325080178,"retail_diff":-0.10752879496666547,"arb_diff":-2.8227955185596896}},{"name":"oracle/lambda<0.0019;sigma<0.4","count":129,"mean":100.82851666643798,"retail_mean":124.20763154176201,"arb_mean":-23.37911487531783,"se":15.34128925136312,"paired":{"n":129,"mean_diff":-2.930324313507753,"se":4.395025325080178,"retail_diff":-0.10752879496666547,"arb_diff":-2.8227955185596896}},{"name":"incumbent/lambda<0.0019;sigma>=0.4","count":124,"mean":102.46486542658549,"retail_mean":121.21909966080807,"arb_mean":-18.75423423421129,"se":15.26055770544542,"paired":{"n":124,"mean_diff":0.027713380157258338,"se":0.4707270425072072,"retail_diff":1.2127497591387086,"arb_diff":-1.1850363790169351}},{"name":"oracle/lambda<0.0019;sigma>=0.4","count":124,"mean":102.49257880674274,"retail_mean":122.43184941994677,"arb_mean":-19.939270613228224,"se":15.250168214384932,"paired":{"n":124,"mean_diff":0.027713380157258338,"se":0.4707270425072072,"retail_diff":1.2127497591387086,"arb_diff":-1.1850363790169351}},{"name":"incumbent/lambda>=0.0019;sigma<0.4","count":131,"mean":109.14942837343817,"retail_mean":133.635919141229,"arb_mean":-24.48649076785038,"se":13.916525358918104,"paired":{"n":131,"mean_diff":-0.3198787825343523,"se":0.6975452638072988,"retail_diff":-0.21321364960152653,"arb_diff":-0.1066651328610689}},{"name":"oracle/lambda>=0.0019;sigma<0.4","count":131,"mean":108.82954959090381,"retail_mean":133.42270549162748,"arb_mean":-24.59315590071145,"se":14.012250278159335,"paired":{"n":131,"mean_diff":-0.3198787825343523,"se":0.6975452638072988,"retail_diff":-0.21321364960152653,"arb_diff":-0.1066651328610689}},{"name":"incumbent/lambda>=0.0019;sigma>=0.4","count":116,"mean":80.97494705185775,"retail_mean":104.43698007909741,"arb_mean":-23.462033027226724,"se":12.799545214085764,"paired":{"n":116,"mean_diff":-1.6758933840551724,"se":0.803530510831718,"retail_diff":-0.34546952293965477,"arb_diff":-1.3304238610810344}},{"name":"oracle/lambda>=0.0019;sigma>=0.4","count":116,"mean":79.29905366780258,"retail_mean":104.09151055615776,"arb_mean":-24.792456888307758,"se":12.518551366673151,"paired":{"n":116,"mean_diff":-1.6758933840551724,"se":0.803530510831718,"retail_diff":-0.34546952293965477,"arb_diff":-1.3304238610810344}}],"paired":{"n":500,"mean_diff":-1.2217662607308004,"se":1.16723731739015,"retail_diff":0.1370086056474002,"arb_diff":-1.358774866365},"suggests":"[{\"change\":\"Keep B jump constants as the default and deprioritize a jump-parameter estimator based only on this substitution. Any later adaptive version should shrink toward these constants and must beat them on disjoint paired seeds.\",\"edge_at_stake\":{\"n\":500,\"mean_diff\":-1.2217662607308004,\"se\":1.16723731739015,\"retail_diff\":0.1370086056474002,\"arb_diff\":-1.358774866365},\"approximate_95_percent_interval\":[-3.509551402815495,1.0660188813538938],\"caveat\":\"No clear gain from inserting exact param","failures":{"incumbent":0,"oracle":0,"validation":0,"errors":[]},"flag":null},
{"key":"item-oracle-retail-parameters","measurement":"Oracle diagnostic, no candidate. B (sha baef955e..., file unmodified) is loaded twice via load_strategy_factory; for the oracle copy the harness overwrites B's module-level P['lam_r'] and P['m'] before each simulation with that simulation's true retail arrival_rate and mean_notional, obtained from runner.sample_config(ChallengeConfig(), ParameterVariance(), seed=s) (a pure function using its own random.Random(seed)). B's size_sigma assumption (sig_n=1.2) already equals the true, unvaried value 1.2, and buy_probability is fixed at 0.5, so lam_r and m are the only retail parameters B lacks. Each seed: run_batch(factory, base_config=ChallengeConfig(), variance=ParameterVariance(), n_simulations=1, seed_start=s, workers=1), serial in-process, simulator at b244530 unmodified; 6 OS processes on disjoint seed ranges. Instrumentation check: on seeds 236000..236019, B via plain run_batch and B via the harness path (P set by the harness to B's own 0.25/5.0) gave identical total/retail/arb edge on all 20 seeds (exact float equality). Source: .imd/reads/artifacts/item-oracle-retail-parameters (SHA-256 a5e6a28c57874f9d2ad591a2697ba6a0e4142917a8db9c9e8cd655219622ee03); all row fields copied from this item except next truncated in suggests. Exact total/retail/arb invariance on 236000..236019 is documented in approach/instrumentation_check. Buckets overlap across parameters. This measures the specified substitution, not an optimal-information bound; the reported overall paired gain does not exceed twice its SE.","seeds":"236000..236999","n":1000,"complete":true,"incumbent":{"mean":95.152,"retail_mean":121.143,"arb_mean":-25.99,"se":5.873},"findings":[{"name":"all","count":1000,"B_mean":95.152,"B_retail":121.143,"B_arb":-25.99,"B_se":5.873,"oracle_mean":96.212,"oracle_retail":120.5,"oracle_arb":-24.288,"diff":1.06,"diff_se":0.557,"retail_diff":-0.643,"arb_diff":1.703},{"name":"lam_r in [0.154,0.22)","count":340,"B_mean":65.229,"B_retail":85.587,"B_arb":-20.358,"B_se":5.525,"oracle_mean":65.556,"oracle_retail":82.423,"oracle_arb":-16.866,"diff":0.327,"diff_se":0.369,"retail_diff":-3.164,"arb_diff":3.492},{"name":"lam_r in [0.22,0.286)","count":336,"B_mean":77.371,"B_retail":109.955,"B_arb":-32.584,"B_se":11.105,"oracle_mean":79.264,"oracle_retail":108.736,"oracle_arb":-29.473,"diff":1.893,"diff_se":1.422,"retail_diff":-1.219,"arb_diff":3.112},{"name":"lam_r in [0.286,0.352)","count":324,"B_mean":144.993,"B_retail":170.056,"B_arb":-25.063,"B_se":12.305,"oracle_mean":145.957,"oracle_retail":172.656,"oracle_arb":-26.699,"diff":0.964,"diff_se":0.794,"retail_diff":2.6,"arb_diff":-1.636},{"name":"m in [2.64,3.872)","count":336,"B_mean":67.226,"B_retail":90.276,"B_arb":-23.05,"B_se":6.93,"oracle_mean":69.382,"oracle_retail":86.54,"oracle_arb":-17.158,"diff":2.156,"diff_se":1.025,"retail_diff":-3.736,"arb_diff":5.892},{"name":"m in [3.872,5.104)","count":356,"B_mean":98.796,"B_retail":124.717,"B_arb":-25.921,"B_se":9.398,"oracle_mean":98.703,"oracle_retail":123.112,"oracle_arb":-24.41,"diff":-0.093,"diff_se":0.62,"retail_diff":-1.605,"arb_diff":1.512},{"name":"m in [5.104,6.336)","count":308,"B_mean":121.405,"B_retail":150.683,"B_arb":-29.278,"B_se":13.571,"oracle_mean":122.601,"oracle_retail":154.526,"oracle_arb":-31.925,"diff":1.196,"diff_se":1.226,"retail_diff":3.843,"arb_diff":-2.647},{"name":"lam_r*m in [0,0.9)","count":313,"B_mean":53.049,"B_retail":78.734,"B_arb":-25.685,"B_se":6.294,"oracle_mean":55.523,"oracle_retail":74.514,"oracle_arb":-18.991,"diff":2.474,"diff_se":1.111,"retail_diff":-4.22,"arb_diff":6.694},{"name":"lam_r*m in [0.9,1.25)","count":358,"B_mean":91.607,"B_retail":113.682,"B_arb":-22.075,"B_se":7.842,"oracle_mean":91.959,"oracle_retail":111.713,"oracle_arb":-19.754,"diff":0.352,"diff_se":0.549,"retail_diff":-1.969,"arb_diff":2.321},{"name":"lam_r*m in [1.25,1.7)","count":245,"B_mean":119.172,"B_retail":150.904,"B_arb":-31.732,"B_se":15.956,"oracle_mean":118.814,"oracle_retail":152.975,"oracle_arb":-34.16,"diff":-0.358,"diff_se":1.442,"retail_diff":2.071,"arb_diff":-2.428},{"name":"lam_r*m in [1.7,9)","count":84,"B_mean":197.088,"B_retail":224.157,"B_arb":-27.068,"B_se":29.189,"oracle_mean":200.028,"oracle_retail":234.579,"oracle_arb":-34.551,"diff":2.94,"diff_se":1.883,"retail_diff":10.423,"arb_diff":-7.483},{"name":"lam_r <0.25, m <5.0","count":338,"B_mean":54.249,"B_retail":77.266,"B_arb":-23.017,"B_se":5.723,"oracle_mean":55.275,"oracle_retail":73.393,"oracle_arb":-18.118,"diff":1.026,"diff_se":0.627,"retail_diff":-3.872,"arb_diff":4.899},{"name":"lam_r <0.25, m >=5.0","count":165,"B_mean":80.685,"B_retail":113.136,"B_arb":-32.452,"B_se":18.244,"oracle_mean":79.061,"oracle_retail":112.778,"oracle_arb":-33.717,"diff":-1.624,"diff_se":1.891,"retail_diff":-0.358,"arb_diff":-1.266},{"name":"lam_r >=0.25, m <5.0","count":329,"B_mean":113.987,"B_retail":140.608,"B_arb":-26.621,"B_se":10.603,"oracle_mean":115.387,"oracle_retail":139.077,"oracle_arb":-23.69,"diff":1.4,"diff_se":1.033,"retail_diff":-1.531,"arb_diff":2.931},{"name":"lam_r >=0.25, m >=5.0","count":168,"B_mean":154.77,"B_retail":179.163,"B_arb":-24.393,"B_se":17.177,"oracle_mean":157.865,"oracle_retail":186.476,"oracle_arb":-28.611,"diff":3.095,"diff_se":1.352,"retail_diff":7.313,"arb_diff":-4.218}],"paired":{"n":1000,"mean_diff":1.06,"se":0.557,"retail_diff":-0.643,"arb_diff":1.703},"suggests":"[\"Little to gain here: perfect knowledge of lam_r and m is worth about +1.06 (SE 0.56) per simulation, versus +24 measured in wave 3 for next-step probability. Put rounds into probability/jump estimation and arbitrage loss instead.\",\"If anything: an online estimate of retail notional flow (count and size of retail fills on B's own resting quotes) that scales the quote-size rule's rho*E[notional] down when flow is low. The low-flow third of sims (lam_r*m < 0.9) is where this gains, at most about ","failures":{"B":0,"oracle":0,"note":"failed flag false in all 2000 simulations; no errors"},"flag":null}
],
"levers": "Ranked by reported per-simulation stake; overlapping descriptive pools are not additive or achievable gains. 1) item-edge-by-parameters: spread 4-minus-1 total 131.0935780273441; arrival high-minus-low 56.176113342923614; notional 49.79535316190703: regime contrasts, not improvement values. 2) item-arb-jump-vs-diffusion: gross arb loss jump 13.6434778763466, diffusion-only 13.3530606103358; large-jump partition 10.7123685288176 and sub-tick diffusion 10.2727445517218. 3) item-edge-by-price-and-time: below-5c gross arb loss 11.490496264251973 alongside retail 85.68106119884104. 4) item-arb-by-order-class: main ask arb -11.262; main bid -7.442. 5) item-oracle-last-probability: paired +5.632, SE 1.133 (retail +3.172, arb +2.46); strongest positive measured oracle substitution here. 6) item-arb-by-order-class: tick1_bank net -4.178, SE 0.669; indirect inventory benefit unmeasured. 7) item-edge-by-price-and-time next[0]: late 5-80c gross arb loss 2.3730823633372093, net -1.5718757049801613. 8) item-oracle-retail-parameters: paired +1.06, SE 0.557. 9) item-oracle-jump-parameters: paired -1.2217662607308004, SE 1.16723731739015; no demonstrated benefit. Oracle results describe these substitutions only. No candidate promotion or finalist-seed evidence supplied."
}
```