{ "notes": "EPISODE 7. Woken by requester note 7 while round 4 ran. At entry 86 of 400 items used (episode 6's three spawns were refused), no item failed anywhere. TO THE REQUESTER: episodes 8, 9 and 10 are all that is left and every note starts one; a note before round 5 settles leaves none to act on its results.\n\nWHAT WENT WRONG BEFORE (do not repeat)\n- Episode 6's r5-pair, r5-fa-wide and r5-ib-union-x were refused (no value for the key placeholder) and never ran: a placeholder is filled only from the item's `vars`, so every item's vars carry `key` and every other placeholder, as strings. The resume of r4-ib-wide worked.\n- This episode's first attempt was rejected for shape ('spawn.N: Invalid input'). Now: each spawn has only name, brief, items, output, merge; every brief under 2,920 characters filled (measure by script); ASCII; every var a short string; merge briefs under 560; maxBytes 64000; groupSize 5.\n\nNOTE 7 (done). New best CG = r2-continue-x/continue-g: artifact id ebbd90c663c396598965b23341aea97a4501b4c971db183a8fe94a880f399979, `code_zb64` sha256 e1ea8fcb105e00754d17061efbe4b299a634b0fcc1b5c293d65b631654b7204b, `port_zb64` = IA's port b29cd2a078b4c3fc57945a79e927624dd346c44d8cc149dae43f4929aa6d736b unchanged, `params` frozen (W = [1] + 19 multipliers + 19 offsets + 178 weights). Asked: confirm against IB on two blocks of 1,024 from 7400000 with the gain by retail-volume quartile, its code at >= +0.3 over IB, and continue it.\n\nREAD AND CHECKED (23; each file's sha256 is its id; CG, CA, KIT, IB, KB and the sisters answer at their URLs with the same bytes). Holdout 40000000..40008191 (n 8,192) over IA, then over IB (= over IA - 0.287 = over HA - 0.652 = over T - 1.7690); real = 512 fresh seeds against IA.\n- CG: +0.470, over IB +0.183 (over T 1.9519, over HA 0.8351). Real +0.5074 se 0.0243 on 7232768..7233279 (retail +0.17, arb +0.33); afterSwap peak 235,611, 0 OOG. Population 32, 128 markets a generation, sigma0 0.5 on coordinates scaled by `search_settings.CMA_stds` (about 0.16), 1,039 generations in 77 min at 892 markets/s; monitor still rising (0.81 at generation 780, 0.85 at 990).\n- Sisters, same port, scaling and start as CG: continue-c (id aaa42d3f6583965b170fbddd6807024ddb8f4d95425bbec5429a6e1aaf5620e5) +0.420, over IB +0.133, 3,520 generations of population 16 at 2,017 markets/s, flat at the end, no real run (Darwin arm64); continue-h (id a97fa964e707df8aff4feb6a2dd8532d33189b88fe3c217749968d5216efd139) +0.384, real +0.378; continue-a +0.332; continue-f +0.272. Their weights sit 0.6 rms from CG's (CG's own 1.54).\n- CA = r2-joint/const-a (id a9279075abf7398da55fe663698052b77902f1a0e7f81105c1589d474d39b246, port b3cb9f07...e209): IA's head fixed, 33 of T's constants searched in log multiplier, 348 generations at 378 markets/s: +0.238, real +0.231 se 0.034, retail -0.78, arb +1.01. Constants move the arb side, the head mostly retail: they should stack.\n- More inputs on IA: +0.220, +0.178, +0.177. Gating: +0.164 at best. Wider on the diet: +0.157 at best (16 units at peak 136,214: the diet leaves 100k of gas). joint-a, inputs-clock: nothing. At equal compute every structural change lost to plain continuation; population 32 beat 16.\n- r4-confirm/ib-a, 7500000..7501023: IB minus HA +0.6281 se 0.0231 (sum 643.1552, sumsq 963.9682), IB minus T +1.7798, HA minus T +1.1517; peak 237,663, 0 OOG. fa-b, 7530000..7531023: FA minus HA +0.5745 se 0.0204 (sum 588.3314, sumsq 775.0600); peak 236,778, 0 OOG. IB is about +0.05 over FA, as the holdout said.\n- Blocked at SETUP on Darwin arm64 (the wheel is Linux x86_64 only): ib-b, f1, fu-a, continue-c's real run: one item in eight, nothing a brief can mend, so lines get spare copies. u2 did no work.\n\nWHERE THE GOAL STANDS. Board: IB 522.00 (20th); expected score = 522.00 + gain over IB; +0.05 is 19th, +0.40 14th, +1.82 11th, +2.66 10th. CG is +0.18 (holdout) to +0.25 (real, through IA) over IB: 15th to 19th, under the requester's +0.3 line unless the confirmation says otherwise. The top 10 is out of reach at this rate: aim for 14th and say so in the write-up.\n\nDECIDED: 46 items in 4 batches, all from CG's frozen params (132 of 400 used after this). Round 4 (39 items from IB and FA) keeps running.\n- r5-cg-confirm: cf-a 7400000..7401023, cf-b 7410000..7411023, cf-c 7420000..7421023 (a spare). Arms CG, IB, HA. Fields cg_vs_ib, cg_vs_ha, ib_vs_ha (with sum, sumsq), quartiles, diffs_cg_minus_ib, gas, cg_code_zb64.\n- r5-cg-continue (k01..k30, merged in groups of 5, canary k01..k05): CMA from CG on IA's port, at least 40 min, sigma under sigma0 x 0.5^(minutes/40). Settings (population / markets a generation / sigma0): A 32/128/0.13 (CG's own recipe carried on), B 32/512/0.06, C 16/512/0.06, D 32/256/0.10, E 16/1024/0.03; k01..k30 = A B C D A A B E A D A B C A D A B C A E A B D A C A B D A A. Real: candidate, IB on 1,024 seeds; CG, HA on 512. Under 200 markets/s: real seeds only.\n- r5-cg-joint (q01..q10, merged in groups of 5; mine): CG's W on CA's port, a five-point line from T's constants to CA's scored on the monitor, then CMA from the best point over weights and the 33 constants together (q01, q02, q03, q05, q06, q07, q09; constant step 0.03 or 0.02, population 32) or the constants alone (q04, q08, q10). Real: candidate and CG on 1,024 (no room for the IB arm: over IB = over CG + the confirmed CG minus IB).\n- r5-cg-soup (m1..m3, mine): CG mixed with continue-c and continue-h (nine monitor points), then CMA from the best: a cheap test of weight averaging.\n- Each merge gives `rows` (with result_sha256: the item's file is at /artifacts/) and `best` (weights, code_zb64, code_sha256).\n- Gate B for CG: replica CG minus T on 7232768..7233279 within 0.15 of +2.00.\n- Not spawned: episode 6's refused FA and union batches (FA trails IB; extra inputs lost to continuation; 7 such items still run); learned memory (too few rounds left).\nSEEDS. Real: item i has 8000000 + 4000*i, i = 0..42 in the order k01..k30, q01..q10, m1..m3 (last 8169023); confirm 7400000..7421023. Train: 1500000000 + 10000000*i. ES seeds 601 + i. Never run: 7800000..7902015. NEXT: real from 8300000; train from 2000000000 in steps of 2000000 (stay under 2147483647). Monitor and holdout never change.\n\nNEXT EPISODE (8)\n1. If woken early by a note, respawn nothing that runs; do what it asks; keep the wake. A refused spawn is mended and resent first. If a wide batch paused on its canary, read `failures`: resume, or mend the brief and rerun with itemsFrom both.\n2. Pool CG minus IB over the cf items from sum and sumsq (never an average of se). At >= +0.3 it is the requester's file: `code_zb64` of CG's id, sha256 e1ea8fcb...204b. Report the quartiles. IB minus HA pools ib-a with the cf items.\n3. One scale: holdout over IB = over_T - 1.7690. Rank CG, CG's children (r5 merges' `best`) and IB's children (r4-ib-wide merges, c1..c5, j1..j3, u1, u3, u4). Drop any failed gate, OOG, peak over 245,000 or replica-real gap over 0.15. The best is base B6: fetch /artifacts/ and see that it holds code and weights.\n4. Round 6 from B6, about 100 items: (a) three confirm items of 1,024 fresh seeds, B6 against IB and HA; (b) the wide continuation on the settings that won, each item checking 1,024 real seeds against IB; (c) if the joint line beat plain continuation, join it with the best weights and give it half the items; if the soup's mix beat CG, mix round 5's children too.\n5. Episode 9: confirm episode 8's winner on 2,048 fresh seeds against IB and HA, plus a last continuation. Episode 10: finish. Write-up: best confirmed file with code and sha256, gain over IB, HA and T, gas, expected board place, distance from the top 10, the plane's unexplained `sources` flags, the Darwin losses.\n6. Reads asked (30): cf-a..c, r5-cg-continue merge-01..06, r5-cg-joint merge-01, 02, m1..m3, r4-ib-wide merge-01..04, c1..c5, j1..j3, u1, u3, u4, kit-c.", "spawn": [ { "name": "r5-cg-confirm", "brief": "Item {{key}}: measure fee policy CG against IB and HA on fresh real-engine seeds. No search; change no code and no weight.\nGoal rules apply (SETUP, REAL ENGINE; HA is named there). Check every sha256.\nFILES. CG = `code_zb64` (base64 then zlib) of https://api.imd.fun/artifacts/ebbd90c663c396598965b23341aea97a4501b4c971db183a8fe94a880f399979, sha256 e1ea8fcb105e00754d17061efbe4b299a634b0fcc1b5c293d65b631654b7204b. IB = `code_zb64` of https://api.imd.fun/artifacts/afd5183e9ff3235334e041c00b0cd19079599a2c6464db95f8c1586712105557, sha256 301941829a44bb60977bb28181a5e4bfa6544f3696763f987054789b2611d686. KIT = https://api.imd.fun/artifacts/0d8194e9f6e0017dc4e515cdb04c048efc292935bb1d18e3336091fe81154786: decode it per its `decode_instructions`, run its unit tests, use `harness.py real` and its decompose function for the retail and arb split.\nWORK. Real seeds {{s0}}..{{s1}} (1,024, fresh, this item's only), in ascending chunks of 64 with each chunk's state saved under scratch/, so that no command runs over 8 minutes. Arms CG, IB, HA: each alone against the 30 bps VanillaStrategy on the same configs. Time the first chunk; if the block cannot finish in your time, do its first 512 seeds and say so.\nFor CG minus IB, CG minus HA and IB minus HA give n, mean_diff, se, sum, sumsq, wins, worst5, retail_delta, arb_delta. Then order the seeds by retail volume (the IB arm's retail volume in that market as the engine or the kit's decomposition gives it; say which) and cut them into four quartiles of equal size: per quartile n, the range of that volume, and mean_diff and se of CG minus IB and of CG minus HA.\nGas per arm from amm_sim_rs.gas_stats(), reset before each arm: afterSwap and afterInitialize calls and peak, and every OOG, revert or other failure count.\nRESULT (JSON): item; hashes; seeds {start, end, n}; cg_vs_ib, cg_vs_ha, ib_vs_ha (the nine values each); quartiles (four rows); diffs_cg_minus_ib (per-seed differences in seed order, 4 decimals); mean_edge per arm with retail and arb; gas per arm; valid (true when CG has 0 OOG and afterSwap peak <= 245,000); cg_code_zb64 (CG's `code_zb64` as fetched) and cg_code_sha256; notes. If SETUP fails return blocked={step,error}.", "items": [ { "key": "cf-a", "vars": { "key": "cf-a", "s0": "7400000", "s1": "7401023" } }, { "key": "cf-b", "vars": { "key": "cf-b", "s0": "7410000", "s1": "7411023" } }, { "key": "cf-c", "vars": { "key": "cf-c", "s0": "7420000", "s1": "7421023" } } ], "output": { "format": "json", "maxBytes": 64000 }, "merge": { "groupSize": 5, "brief": "Merge into one JSON object: one row per item with its seeds, cg_vs_ib, cg_vs_ha, ib_vs_ha, quartiles, gas and valid, copying numbers as given." } }, { "name": "r5-cg-continue", "brief": "Item {{key}}: long training of fee policy CG's 19-8-2 head on the replica from its frozen weights, then a real-engine check.\nGoal rules apply (SETUP, GATES, REAL ENGINE; HA is named there). Check every sha256. Use the ports given.\nFILES. KIT = https://api.imd.fun/artifacts/0d8194e9f6e0017dc4e515cdb04c048efc292935bb1d18e3336091fe81154786 (decode per its `decode_instructions`, run its unit tests: replica sim.py, harness.py train/freeze/real, diff_test.py, T and HA ports). CG = https://api.imd.fun/artifacts/ebbd90c663c396598965b23341aea97a4501b4c971db183a8fe94a880f399979: `code_zb64` (base64 then zlib) sha256 e1ea8fcb105e00754d17061efbe4b299a634b0fcc1b5c293d65b631654b7204b; `port_zb64` sha256 b29cd2a078b4c3fc57945a79e927624dd346c44d8cc149dae43f4929aa6d736b (IA's port; W = [1] + feature_multipliers + feature_offsets + W1 rows + b1 + W2 rows + b2, 217 entries); start from `params`, the frozen policy, never from `restart`. IB = `code_zb64` of https://api.imd.fun/artifacts/afd5183e9ff3235334e041c00b0cd19079599a2c6464db95f8c1586712105557, sha256 301941829a44bb60977bb28181a5e4bfa6544f3696763f987054789b2611d686.\nGATES. A: CG's port and W against CG's code. B: replica CG minus T on 7232768..7233279 within 0.15 of +2.00 (real). C: frozen code against the frozen port.\nSEARCH. Measure markets/s first. Under 200: no search; CG, IB and HA on 1,024 real seeds from {{real}} instead. Otherwise CMA-ES over the 178 head weights starting at CG's, coordinates scaled by CG's `search_settings.CMA_stds`, population {{pop}}, {{mk}} replica markets a generation (the same markets for every proposal; twice as many from 2,000 markets/s), sigma0 {{sig}} and never above sigma0 x 0.5^(minutes/40), ES seed {{es}}, training seeds from {{train}}, monitor markets 30000000..30002047. Segments under 8 minutes; at least 40 minutes, and as long as time allows after keeping 30 for the rest. Every 10 generations score ES mean and generation best on the monitor against CG; freeze the best monitor point (CG if nothing beats it), weights rounded to 1e-6.\nAFTER. Holdout 40000000..40008191 once: over_T, over_CG (paired), over_IB = over_T - 1.7690. Real seeds from {{real}}: candidate and IB on 1,024, CG and HA on the first 512 (fewer only if short of time; say which), gas per arm.\nRESULT (JSON, under 40,000 bytes): item; hashes; speed; gates; search {minutes, generations, settings, final_sigma}; curve (at most 30 rows: generation, minutes, monitor gain over CG); holdout {n, over_T, over_CG, over_IB, se}; real {seeds; vs_IB, vs_CG, vs_HA each n, mean_diff, se, sum, sumsq, worst5, retail_delta, arb_delta}; gas {afterSwap peak, afterInitialize peak, OOG}; valid; code_zb64, code_sha256; params (W1, b1, W2, b2, scaling); weights (the 178 as one flat list); notes. If SETUP fails return blocked={step,error}.", "items": [ { "key": "k01", "vars": { "key": "k01", "pop": "32", "mk": "128", "sig": "0.13", "es": "601", "real": "8000000", "train": "1500000000" } }, { "key": "k02", "vars": { "key": "k02", "pop": "32", "mk": "512", "sig": "0.06", "es": "602", "real": "8004000", "train": "1510000000" } }, { "key": "k03", "vars": { "key": "k03", "pop": "16", "mk": "512", "sig": "0.06", "es": "603", "real": "8008000", "train": "1520000000" } }, { "key": "k04", "vars": { "key": "k04", "pop": "32", "mk": "256", "sig": "0.10", "es": "604", "real": "8012000", "train": "1530000000" } }, { "key": "k05", "vars": { "key": "k05", "pop": "32", "mk": "128", "sig": "0.13", "es": "605", "real": "8016000", "train": "1540000000" } }, { "key": "k06", "vars": { "key": "k06", "pop": "32", "mk": "128", "sig": "0.13", "es": "606", "real": "8020000", "train": "1550000000" } }, { "key": "k07", "vars": { "key": "k07", "pop": "32", "mk": "512", "sig": "0.06", "es": "607", "real": "8024000", "train": "1560000000" } }, { "key": "k08", "vars": { "key": "k08", "pop": "16", "mk": "1024", "sig": "0.03", "es": "608", "real": "8028000", "train": "1570000000" } }, { "key": "k09", "vars": { "key": "k09", "pop": "32", "mk": "128", "sig": "0.13", "es": "609", "real": "8032000", "train": "1580000000" } }, { "key": "k10", "vars": { "key": "k10", "pop": "32", "mk": "256", "sig": "0.10", "es": "610", "real": "8036000", "train": "1590000000" } }, { "key": "k11", "vars": { "key": "k11", "pop": "32", "mk": "128", "sig": "0.13", "es": "611", "real": "8040000", "train": "1600000000" } }, { "key": "k12", "vars": { "key": "k12", "pop": "32", "mk": "512", "sig": "0.06", "es": "612", "real": "8044000", "train": "1610000000" } }, { "key": "k13", "vars": { "key": "k13", "pop": "16", "mk": "512", "sig": "0.06", "es": "613", "real": "8048000", "train": "1620000000" } }, { "key": "k14", "vars": { "key": "k14", "pop": "32", "mk": "128", "sig": "0.13", "es": "614", "real": "8052000", "train": "1630000000" } }, { "key": "k15", "vars": { "key": "k15", "pop": "32", "mk": "256", "sig": "0.10", "es": "615", "real": "8056000", "train": "1640000000" } }, { "key": "k16", "vars": { "key": "k16", "pop": "32", "mk": "128", "sig": "0.13", "es": "616", "real": "8060000", "train": "1650000000" } }, { "key": "k17", "vars": { "key": "k17", "pop": "32", "mk": "512", "sig": "0.06", "es": "617", "real": "8064000", "train": "1660000000" } }, { "key": "k18", "vars": { "key": "k18", "pop": "16", "mk": "512", "sig": "0.06", "es": "618", "real": "8068000", "train": "1670000000" } }, { "key": "k19", "vars": { "key": "k19", "pop": "32", "mk": "128", "sig": "0.13", "es": "619", "real": "8072000", "train": "1680000000" } }, { "key": "k20", "vars": { "key": "k20", "pop": "16", "mk": "1024", "sig": "0.03", "es": "620", "real": "8076000", "train": "1690000000" } }, { "key": "k21", "vars": { "key": "k21", "pop": "32", "mk": "128", "sig": "0.13", "es": "621", "real": "8080000", "train": "1700000000" } }, { "key": "k22", "vars": { "key": "k22", "pop": "32", "mk": "512", "sig": "0.06", "es": "622", "real": "8084000", "train": "1710000000" } }, { "key": "k23", "vars": { "key": "k23", "pop": "32", "mk": "256", "sig": "0.10", "es": "623", "real": "8088000", "train": "1720000000" } }, { "key": "k24", "vars": { "key": "k24", "pop": "32", "mk": "128", "sig": "0.13", "es": "624", "real": "8092000", "train": "1730000000" } }, { "key": "k25", "vars": { "key": "k25", "pop": "16", "mk": "512", "sig": "0.06", "es": "625", "real": "8096000", "train": "1740000000" } }, { "key": "k26", "vars": { "key": "k26", "pop": "32", "mk": "128", "sig": "0.13", "es": "626", "real": "8100000", "train": "1750000000" } }, { "key": "k27", "vars": { "key": "k27", "pop": "32", "mk": "512", "sig": "0.06", "es": "627", "real": "8104000", "train": "1760000000" } }, { "key": "k28", "vars": { "key": "k28", "pop": "32", "mk": "256", "sig": "0.10", "es": "628", "real": "8108000", "train": "1770000000" } }, { "key": "k29", "vars": { "key": "k29", "pop": "32", "mk": "128", "sig": "0.13", "es": "629", "real": "8112000", "train": "1780000000" } }, { "key": "k30", "vars": { "key": "k30", "pop": "32", "mk": "128", "sig": "0.13", "es": "630", "real": "8116000", "train": "1790000000" } } ], "output": { "format": "json", "maxBytes": 64000 }, "merge": { "groupSize": 5, "brief": "Merge this group's results into one JSON object; copy numbers as given, compute nothing new, null where missing. `rows`, one per item: key, result_sha256 (sha256 of its result file), blocked, markets/s, search minutes, generations, settings, holdout over_T, over_CG, over_IB and se, real vs_IB and vs_CG (n, mean_diff, se, sum, sumsq), afterSwap peak, OOG, gates, valid, code_sha256. `best`: the valid item with every gate passed and the highest holdout over_CG: key, result_sha256, weights, code_zb64, code_sha256." } }, { "name": "r5-cg-joint", "brief": "Item {{key}}: search fee policy CG's head and T's constants on the replica, then check the result on the real engine.\nGoal rules apply (SETUP, GATES, REAL ENGINE; HA is named there). Check every sha256. Use the ports given.\nFILES. KIT = https://api.imd.fun/artifacts/0d8194e9f6e0017dc4e515cdb04c048efc292935bb1d18e3336091fe81154786 (decode per its `decode_instructions`, run its unit tests: replica sim.py, harness.py train/freeze/real, diff_test.py, T and HA ports). CG = https://api.imd.fun/artifacts/ebbd90c663c396598965b23341aea97a4501b4c971db183a8fe94a880f399979: `code_zb64` (base64 then zlib) sha256 e1ea8fcb105e00754d17061efbe4b299a634b0fcc1b5c293d65b631654b7204b; `params` = the frozen policy (W = [1] + feature_multipliers + feature_offsets + W1 rows + b1 + W2 rows + b2, 217 entries). CA = https://api.imd.fun/artifacts/a9279075abf7398da55fe663698052b77902f1a0e7f81105c1589d474d39b246: `port_zb64` sha256 b3cb9f073d7a6f1c651215c58f7e897b76bf88a75f72ef9b88dbb1d5cc54e209 = IA's port, constants adjustable; `constants` = name: [T's value, CA's value]; `search.settings` = the 33 searched, their coordinate (log multiplier from T's value), bounds; `code_zb64` = where each sits in Solidity.\nGATES. A: CA's port with CG's W and T's constants against CG's code. B: replica CG minus T on 7232768..7233279 within 0.15 of +2.00 (real). C: frozen code against the frozen port.\nSEARCH. Measure markets/s first. Under 200: no search; CG and HA on 1,024 real seeds from {{real}} instead. Otherwise score on monitor markets 30000000..30002047, with CG's weights, t = 0, 0.25, 0.5, 0.75, 1 on the line from T's constants to CA's in log-multiplier space; start from the best. Then CMA-ES over {{dims}}: weights scaled by CG's `search_settings.CMA_stds`, sigma0 0.06; constants in log multiplier, step {{csig}}, inside CA's bounds; population {{pop}}, 256 markets a generation, steps never above their start x 0.5^(minutes/40), ES seed {{es}}, training seeds from {{train}}. Segments under 8 minutes; at least 40 minutes, and as long as time allows after keeping 30 for the rest. Every 10 generations score ES mean and generation best on the monitor against CG; freeze the best monitor point (CG if nothing beats it), weights rounded to 1e-6.\nAFTER. Holdout 40000000..40008191 once: over_T, over_CG (paired), over_IB = over_T - 1.7690. Real seeds from {{real}}: candidate and CG on 1,024 (512 if short of time), gas per arm.\nRESULT (JSON, under 40,000 bytes): item; hashes; speed; gates; line (t, monitor gain over CG); search {minutes, generations, settings}; curve (30 rows at most); holdout {n, over_T, over_CG, over_IB, se}; real {seeds; vs_CG: n, mean_diff, se, sum, sumsq, worst5, retail_delta, arb_delta}; gas {afterSwap peak, afterInitialize peak, OOG}; valid; code_zb64, code_sha256; weights (the 178, flat); constants (all 33); notes. If SETUP fails return blocked={step,error}.", "items": [ { "key": "q01", "vars": { "key": "q01", "dims": "the 178 head weights and the 33 constants together", "pop": "32", "csig": "0.03", "es": "631", "real": "8120000", "train": "1800000000" } }, { "key": "q02", "vars": { "key": "q02", "dims": "the 178 head weights and the 33 constants together", "pop": "32", "csig": "0.03", "es": "632", "real": "8124000", "train": "1810000000" } }, { "key": "q03", "vars": { "key": "q03", "dims": "the 178 head weights and the 33 constants together", "pop": "32", "csig": "0.02", "es": "633", "real": "8128000", "train": "1820000000" } }, { "key": "q04", "vars": { "key": "q04", "dims": "the 33 constants only, CG's weights fixed", "pop": "16", "csig": "0.05", "es": "634", "real": "8132000", "train": "1830000000" } }, { "key": "q05", "vars": { "key": "q05", "dims": "the 178 head weights and the 33 constants together", "pop": "32", "csig": "0.03", "es": "635", "real": "8136000", "train": "1840000000" } }, { "key": "q06", "vars": { "key": "q06", "dims": "the 178 head weights and the 33 constants together", "pop": "32", "csig": "0.02", "es": "636", "real": "8140000", "train": "1850000000" } }, { "key": "q07", "vars": { "key": "q07", "dims": "the 178 head weights and the 33 constants together", "pop": "32", "csig": "0.03", "es": "637", "real": "8144000", "train": "1860000000" } }, { "key": "q08", "vars": { "key": "q08", "dims": "the 33 constants only, CG's weights fixed", "pop": "16", "csig": "0.05", "es": "638", "real": "8148000", "train": "1870000000" } }, { "key": "q09", "vars": { "key": "q09", "dims": "the 178 head weights and the 33 constants together", "pop": "32", "csig": "0.02", "es": "639", "real": "8152000", "train": "1880000000" } }, { "key": "q10", "vars": { "key": "q10", "dims": "the 33 constants only, CG's weights fixed", "pop": "16", "csig": "0.03", "es": "640", "real": "8156000", "train": "1890000000" } } ], "output": { "format": "json", "maxBytes": 64000 }, "merge": { "groupSize": 5, "brief": "Merge this group's results into one JSON object; copy numbers as given, compute nothing new, null where missing. `rows`, one per item: key, result_sha256 (sha256 of its result file), blocked, markets/s, search minutes, generations, settings, holdout over_T, over_CG, over_IB and se, real vs_IB and vs_CG (n, mean_diff, se, sum, sumsq), afterSwap peak, OOG, gates, valid, code_sha256, line. `best`: the valid item with every gate passed and the highest holdout over_CG: key, result_sha256, weights, code_zb64, code_sha256; its constants." } }, { "name": "r5-cg-soup", "brief": "Item {{key}}: mix fee policy CG with two sister policies, train on from the best mix on the replica, then check it on the real engine.\nGoal rules apply (SETUP, GATES, REAL ENGINE; HA is named there). Check every sha256. Use the ports given.\nFILES. KIT = https://api.imd.fun/artifacts/0d8194e9f6e0017dc4e515cdb04c048efc292935bb1d18e3336091fe81154786 (decode per its `decode_instructions`, run its unit tests: replica sim.py, harness.py train/freeze/real, diff_test.py, T and HA ports). CG = https://api.imd.fun/artifacts/ebbd90c663c396598965b23341aea97a4501b4c971db183a8fe94a880f399979: `code_zb64` (base64 then zlib) sha256 e1ea8fcb105e00754d17061efbe4b299a634b0fcc1b5c293d65b631654b7204b; `port_zb64` sha256 b29cd2a078b4c3fc57945a79e927624dd346c44d8cc149dae43f4929aa6d736b (IA's port; W = [1] + feature_multipliers + feature_offsets + W1 rows + b1 + W2 rows + b2, 217 entries); start from `params`, the frozen policy, never from `restart`. Sisters (CG's own start, port and scaling; take W1, b1, W2, b2 of `params`): S1 = https://api.imd.fun/artifacts/aaa42d3f6583965b170fbddd6807024ddb8f4d95425bbec5429a6e1aaf5620e5, S2 = https://api.imd.fun/artifacts/a97fa964e707df8aff4feb6a2dd8532d33189b88fe3c217749968d5216efd139.\nGATES. A: CG's port and W against CG's code. B: replica CG minus T on 7232768..7233279 within 0.15 of +2.00 (real). C: frozen code against the frozen port.\nMIX. Measure markets/s first. Under 200: no search; CG and HA on 1,024 real seeds from {{real}} instead. Otherwise M1 = mean of CG and S1, M2 = mean of CG, S1 and S2, weight by weight. On monitor markets 30000000..30002047 score CG + t x (M - CG) for M in M1, M2 and t in 0.25, 0.5, 0.75, 1 against CG (t = 0); the best of the nine points is the start.\nSEARCH. CMA-ES over the 178 head weights from that start, coordinates scaled by CG's `search_settings.CMA_stds`, population 32, 256 replica markets a generation, sigma0 0.08 and never above sigma0 x 0.5^(minutes/40), ES seed {{es}}, training seeds from {{train}}. Segments under 8 minutes; at least 40 minutes, and as long as time allows after keeping 30 for the rest. Every 10 generations score ES mean and generation best on the monitor against CG; freeze the best monitor point (CG if nothing beats it), weights rounded to 1e-6.\nAFTER. Holdout 40000000..40008191 once: over_T, over_CG (paired), over_IB = over_T - 1.7690. Real seeds from {{real}}: candidate and CG on 1,024 (512 if short of time), gas per arm.\nRESULT (JSON, under 40,000 bytes): item; hashes; speed; gates; mix (M, t, monitor gain over CG); start; search {minutes, generations, settings}; curve (30 rows at most); holdout {n, over_T, over_CG, over_IB, se}; real {seeds; vs_CG: n, mean_diff, se, sum, sumsq, worst5, retail_delta, arb_delta}; gas {afterSwap peak, afterInitialize peak, OOG}; valid; code_zb64, code_sha256; weights (the 178, flat); notes. If SETUP fails return blocked={step,error}.", "items": [ { "key": "m1", "vars": { "key": "m1", "es": "641", "real": "8160000", "train": "1900000000" } }, { "key": "m2", "vars": { "key": "m2", "es": "642", "real": "8164000", "train": "1910000000" } }, { "key": "m3", "vars": { "key": "m3", "es": "643", "real": "8168000", "train": "1920000000" } } ], "output": { "format": "json", "maxBytes": 64000 }, "merge": { "groupSize": 5, "brief": "Merge this group's results into one JSON object; copy numbers as given, compute nothing new, null where missing. `rows`, one per item: key, result_sha256 (sha256 of its result file), blocked, markets/s, search minutes, generations, settings, holdout over_T, over_CG, over_IB and se, real vs_IB and vs_CG (n, mean_diff, se, sum, sumsq), afterSwap peak, OOG, gates, valid, code_sha256, mix, start. `best`: the valid item with every gate passed and the highest holdout over_CG: key, result_sha256, weights, code_zb64, code_sha256." } } ], "read": [ "r5-cg-confirm/cf-a", "r5-cg-confirm/cf-b", "r5-cg-confirm/cf-c", "r5-cg-continue/merge-01", "r5-cg-continue/merge-02", "r5-cg-continue/merge-03", "r5-cg-continue/merge-04", "r5-cg-continue/merge-05", "r5-cg-continue/merge-06", "r5-cg-joint/merge-01", "r5-cg-joint/merge-02", "r5-cg-soup/m1", "r5-cg-soup/m2", "r5-cg-soup/m3", "r4-ib-wide/merge-01", "r4-ib-wide/merge-02", "r4-ib-wide/merge-03", "r4-ib-wide/merge-04", "r4-ib-continue/c1", "r4-ib-continue/c2", "r4-ib-continue/c3", "r4-ib-continue/c4", "r4-ib-continue/c5", "r4-ib-joint/j1", "r4-ib-joint/j2", "r4-ib-joint/j3", "r4-ib-union/u1", "r4-ib-union/u3", "r4-ib-union/u4", "r4-ib-kit/kit-c" ], "cancel": [], "wake": { "batches": [ "r5-cg-confirm", "r5-cg-continue", "r5-cg-joint", "r5-cg-soup", "r4-ib-wide", "r4-ib-continue", "r4-ib-joint", "r4-ib-union", "r4-ib-kit", "r4-confirm" ], "afterMinutes": 480 }, "finish": false }