sync: engine.py to hf-space (auto-deploy)

[FRANKENSTEIN] engine: mirror Cat 66 Pace-Norm Per-100 Diffs from mon-ipad (sha256 5e66371c) — Rule #2 parity fix

[FRANKENSTEIN] frankenstein: impl cycle99-pace-norm-per100-cat66 — Cat66 pace-normalized per-100 box-score differentials

feat: /api/promote-config endpoint — ingests Karpathy GPU wins as elite individuals

data: live NBA data refresh + colab notebook cleanup 2026-04-17

chore(env): finish ceec951c8 — canonical HF_TOKEN_NBA in deploy_s11.py

fix(parity): sync hf-space/features/engine.py to mon-ipad canonical (Rule 2)

chore(env): finish ceec951c8 rename — sweep hf-space/deploy.py + deploy_island.py

fix(supabase): remove non-existent columns from cycle INSERT

brain[cycle97]: restore app.py + 2x isotonic_temporal weight (7→14 init, 8→15 mutate; MDPI2026 ~0.199 Brier)

brain[cycle97]: restore app.py + 2x isotonic_temporal calibration weight (7→14)

brain[cycle97]: restore app.py + 2x isotonic_temporal calibration weight (7→14)

brain[cycle97]: 2x isotonic_temporal calibration weight (7→14, MDPI2026 ~0.199 Brier for LR+isotonic)

sync: engine.py to hf-space (auto-deploy)

sync: engine.py to hf-space (auto-deploy)

sync: engine.py to hf-space (auto-deploy)

sync: engine.py to hf-space (auto-deploy)

sync: engine.py to hf-space (auto-deploy)

sync: engine.py to hf-space (auto-deploy)

Revert "fix: replace all /home/termius/ → /home/lahargnedebartoli/ (VM username fix)"

fix: replace all /home/termius/ → /home/lahargnedebartoli/ (VM username fix)

Brain cycle 83: Cat59 opponent graph features (arXiv 2303.16741 GATv2-TCN)

Brain cycle 83: Cat56-58 + engine v3.1-58cat (3 new SOTA 2026 categories)

Brain cycle 83: Cat55 market consensus deviation (MDPI 2026 fused model)

Brain cycle 82: fix calibration mutation bias — venn_abers boosted across all 3 GA impls

brain cycle79: space_id logging + cycle stagnation + hard reset

brain cycle79: lightgbm_brier model type + calibration mutation fix + S14 boost

sync: engine.py to hf-space (auto-deploy)

d1: DART dropout trees on LightGBM in GA loop — expected Brier delta -0.0025

D9 iter10: fix CLAUDE.md + engine.py docstring (35→54 categories, 3-way parity)

fix(engine): Cat15 polymarket fallback to book-implied prob from odds_data

Merge remote-tracking branch 'origin/main'

fix(engine): replace Cat14 constant placeholders with real defensive proxies

sync: engine.py to hf-space (auto-deploy)

brain-cycle-74: add isotonic_temporal calibration to GA

fix(engine): reset _season_spreads/_season_totals at season boundaries (Cat 52/54)

fix(engine): _ats_rate home_only=False was a no-op — ats53_a_away_only returned wrong values

feat(engine): add h_next_is_home + a_next_is_home to Cat6 [brain-cycle-71]

fix(engine): replace last bare except: with except Exception: in CV fitting block

sync: engine.py to hf-space (auto-deploy)

sync: engine.py to hf-space (auto-deploy)

sync: engine.py to hf-space (auto-deploy)

evolution: 4 critical fixes — elitism + CatBoost cap + feature penalty + n_splits=3

feat: MLP meta-learner for stacking (was LR, -0.003 Brier expected)

feat(engine): Add Cat51 Season Era Normalization (v3.1-50cat → v3.1-51cat)

feat: add /api/best endpoint + feature_indices in to_dict

feat(engine): Add Cat50 Temporal Win-Sequence Encoding (v3.1-49cat → v3.1-50cat)

feat: calibration map + predict_today improvements + app.py enhancements

feat: update ENGINE_VERSION v3.1-46cat → v3.1-49cat

feat: add logistic_regression model type to GA (MDPI 2026: best tabular Brier 0.199)