id: 69e18c9e84a44742adaec36208c87f2e
parent_id: 4cb7bf22214e46e186544c230b612a86
item_type: 1
item_id: ec1518e71453490f8fe5ab75cff7180c
item_updated_time: 1787219672357
title_diff: "[{\"diffs\":[[0,\"0 — \"],[-1,\"v19 training\"],[1,\"g55 gate failed\"],[0,\")\"]],\"start1\":31,\"start2\":31,\"length1\":17,\"length2\":20}]"
body_diff: "[{\"diffs\":[[0,\"v19 \"],[-1,\"collection DONE, training running\"],[1,\"trained, g55 FAILED gate\"],[0,\")\\\n\\\n>\"]],\"start1\":37,\"start2\":37,\"length1\":41,\"length2\":32},{\"diffs\":[[0,\"sion\"],[-1,\" 2026-08-19, until NN work lands).** v19 corpus collected; oracle table regenerated; RangeNet v19 A/B training running\"],[1,\"), G51 unchanged.** v19 models trained; board-exact arm wins offline; g55 candidate fails Gate 3 vs Gen2 — regression isolated and real\"],[0,\".\\\n\\\n#\"]],\"start1\":95,\"start2\":95,\"length1\":126,\"length2\":143},{\"diffs\":[[0,\"nkt \"],[-1,\"1: v19 Collection — COMPLETE (2026-08-20 06:24\"],[1,\"3: RangeNet v19 A/B — DONE (winner: board-exact\"],[0,\")\\\n- \"]],\"start1\":242,\"start2\":242,\"length1\":54,\"length2\":55},{\"diffs\":[[0,\".2M \"],[-1,\"range\"],[1,\"v19\"],[0,\" samples\"],[-1,\" + 4.0M equity samples, 13.4h runtime, ALL tables healthy (98.9-99.9% flop+)\\\n- `/home/jan/gen5_data/equity_v19` (70G): 6× 9-max (all-8-personalities gold pool) + 4× 6-max (3-loose quorum), light collector (corr/eq_cc off)\\\n- Every sample has raw block: hero/board/opp card ids (rank*4+suit) + per-action chips + faced_chips/pot/bb\"],[1,\", 30 epochs, GPU, both arms same recipe (eps 0.05)\\\n- **Board-exact 449-dim: NLL 4.470, top1 4.92%, top10 25.1%, calErr 0.0491** vs 85-dim: 4.551/4.07%/22.9%/0.0495\\\n- Inference wired: shared `append_board_exact_features` (train/infer identical, layout test), predictor auto-detects 449-dim (commit 95bdc4d)\\\n- Models: `range_v19_board.safetensors`, `range_v19_85d.safetensors`\"],[0,\"\\\n\\\n##\"]],\"start1\":299,\"start2\":299,\"length1\":350,\"length2\":393},{\"diffs\":[[0,\"nkt \"],[-1,\"2: Oracle Table Regen — COMPLETE (commit cab5173)\\\n- **Bug found+fixed**: street_sizes lookup used board length against 0=preflop..3=river index — all calls/folds bucketed \\\"small\\\", medium/large cells empty since v8. Offset fix → all 4 size contexts populated (medium 4-22K/class/street, large 1.5-8K)\\\n- New: `data/oracle_table_v19.json`. Call steepness now size-dependent: Fish 5.3x(small)→8.1x(large), Tag 43-188x\\\n- Old table (data/oracle_table.json, built on pre-sizing-fix pool) superseded\\\n\\\n## Punkt 3: RangeNet v19 A/B — RUNNING (started 2026-08-20 ~07:00)\\\n- Arm 1 (baseline): 85-dim, eps 0.05, 30 epochs → models/range_v19_85d.safetensors\\\n- Arm 2 (board-exact): RANGE_BOARD_EXACT=1 appends hero 2×52 + board 5×52 one-hots from raw block (85→449 dims) → models/range_v19_board.safetensors\\\n- Both on v19 mixed-size data (fixes v17's 9-max-only limitation)\\\n- Model selection: NLL + marginal calErr (v18 trainer)\"],[1,\"4: g55 gates — FAILED (not promoted)\\\n- Gate 1 Harrington (NN path, 449-dim model confirmed loaded): PASS 52/52 (1 known ignore)\\\n- Gate 2 self-play: clean. Gate 3: Gen3 +0.6, G48 +1.9 (g51: +1.7), TAG +1.8 (g51: +1.5), Nit +0.1, **Gen2 −0.27 BB/100 → FAIL** (g51 sanity was +0.6). Gate 4 Mixed: 0.0 (g51: +0.4)\\\n- A/B g55 vs g51: −0.11 BB/100 dead heat over 200K cand-hands\\\n- **Control run (identical seeds, 4×g51+5×Gen2×5000h×5 seeds): g51 +2.80 BB/100 vs g55 −0.27.** Per-seed swing −490…−1140 BB, ALL seeds negative → real regression vs Gen2, not noise.\\\n- **Diagnosis**: sharper board-exact prior wins in-distribution (G48/TAG = pool family) but is exploited by Gen2's off-distribution rollout lines — overconfident wrong reads. Suspects: (1) corrector corr_* knobs tuned for v17-width priors over-concentrate with v19, (2) v19 training pool lacks Gen2-style lines.\"],[0,\"\\\n- \"],[-1,\"**\"],[0,\"Next\"],[-1,\" after training**: compare log-score/calibration → winner becomes g55 candidate → Harrington/KK gates, sanity_check, A/B vs g51\\\n\\\n## Gen 6 (renamed 2026-08-19): Opponent Mirrors + Decision-Time Rollouts\\\n- Old PPO \\\"Gen 6\\\" numbering retired. Gen 6 = Jan's Idea #8 (details in Ideas note f3c42f44): observer stats → personality mirror; range posterior → sample holdings; behavioral oracle → sample actions; EV per hero action. Distilled EV/action NN (revived EquityNet) replaces rollouts for live.\\\n\\\n## Session context / lessons (2026-08-19 collection saga)\\\n- Tightness death spiral: tight-heavy table draws + observer-adaptive tightening → near-zero flops. Fix: loose quorum in compose_table (v19_collect.sh, commit 3d97fd9)\\\n- 3-max unusable: G47 preflop = raise-war at 3-hand\"],[1,\": g55-nc (corr off) + g55-85d isolations; consider corrector re-fit on v19 priors.\\\n\\\n## Punkt 1-2 (done earlier): v19 collection + oracle regen — see commits 1e3144f/3d97fd9/c23dc19/cab5173\\\n- Oracle v19 table: all size contexts populated after street_sizes index fix; superseded old table\\\n\\\n## Gen 6 (renamed): mirrors + rollouts — details in Ideas note f3c42f44. NN-for-speed = distilled EV net (primary) / rollout-policy net (secondary).\\\n\\\n## Session context / lessons\\\n- Live range collection: needs showdown→range-sample adapter (live only reveals per-player at showdown, no all-reveal event); wire with next live rebuild\\\n- Pool realism ladder agre\"],[0,\"ed\"],[1,\":\"],[0,\" (\"],[-1,\"78% raise-first, zero limps, 5-20% flops)\\\n- Parallel CUDA init OOM → 20s launch stagger\\\n- Health validation: per-table street d\"],[1,\"b) dynamic curves w/ shrinkage first → (a) pool v2 from live stats → (c) live oracles; all three draw from live hand h\"],[0,\"ist\"],[1,\"o\"],[0,\"ri\"],[-1,\"bution vs gold {24/17/59}% flop/turn/river-ended, ~15 equity taps/hand\"],[1,\"es → resume live reasonably soon as data engine\"],[0,\"\\\n\\\n##\"]],\"start1\":695,\"start2\":695,\"length1\":1907,\"length2\":1705}]"
metadata_diff: {"new":{},"deleted":[]}
encryption_cipher_text: 
encryption_applied: 0
updated_time: 2026-08-20T09:56:11.804Z
created_time: 2026-08-20T09:56:11.804Z
is_locked: 0
type_: 13