generated from mathias/template-go-web
mathias
c7c182fb4d
CD / Lint / Test / Vet (push) Successful in 5s
Same drift as gitea-mcp: this repo's copy of context-sync.sh was two days stale against dma-cli's canonical (Mathias's Cursor/Aider decision, 2026-09-01) and CLAUDE.md itself was stale enough to need 97 lines of correction on regeneration -- this repo's context:sync was apparently never wired into `task check` at all (no drift assertion existed in its Taskfile), so nothing had been catching it. Found while building the estate-wide context-sync drift gate (ADR-0019). - script synced to canonical hash - .cursorrules, .aider.conventions.md, .aider.conf.yml deleted - stale context:sync:cursor Taskfile shortcut removed (would now hit the canonical script's own `exit 1` on an unknown adapter name) - CLAUDE.md, AGENTS.md, .context/system-prompt.txt regenerated against canonical task check -> exit 0.
105 lines
4.3 KiB
Markdown
105 lines
4.3 KiB
Markdown
# jepa-fx-risk
|
||
|
||
## Identity
|
||
|
||
- **Name**: jepa-fx-risk
|
||
- **Owner**: Mathias
|
||
- **Client**: personal research
|
||
- **Repo**: gitea.d-ma.be/mathias/jepa-fx-risk
|
||
- **Status**: active — Phase 0
|
||
|
||
## Purpose
|
||
|
||
Research project: apply JEPA-based self-supervised representation learning to
|
||
FX risk management for a corporate bank with an internal global FX trading desk.
|
||
|
||
Primary tasks: FX volatility forecasting and VaR/CVaR estimation.
|
||
Target output: internal PoC for the trading desk.
|
||
|
||
## Architecture decision (see DECISIONS.md ADR-001)
|
||
|
||
**TS-JEPA + SIGReg** — TS-JEPA temporal patchwise architecture (Ennadir et al.,
|
||
arXiv:2509.25449) with EMA replaced by Sketched Isotropic Gaussian Regularization
|
||
(SIGReg, Balestriero & LeCun, arXiv:2511.08544). Single search axis: λ ∈ [0.01, 1.0].
|
||
|
||
Phase 2 hypothesis: MTS-JEPA multi-resolution objective (arXiv:2602.04643).
|
||
|
||
## Stack
|
||
|
||
**Go** (`src/`): data pipeline (DUKASCopy fetch + hourly processing), evaluation
|
||
harness (silhouette, linear probe R², collapse diagnostic, Kupiec/Christoffersen),
|
||
results dashboard (Templ + HTMX + CDN Tailwind).
|
||
|
||
**Python** (`model/`): all training and embedding export only. PyTorch cu130
|
||
(Blackwell sm_120 compatible). No evaluation logic in Python.
|
||
|
||
**Infra**: koala (Arch Linux, Blackwell GPU 12 GB VRAM) for training.
|
||
iguana (Mac Studio M2 Ultra) + LiteLLM on piguard for autoresearch agent LLM.
|
||
|
||
## Repository layout
|
||
|
||
```
|
||
jepa-fx-risk/
|
||
├── src/ # Go — data pipeline + eval harness + dashboard
|
||
│ ├── data/ # DUKASCopy fetch, hourly processing, validation
|
||
│ └── eval/ # silhouette, linear probe, collapse, backtest
|
||
├── model/ # Python — training only
|
||
│ ├── train.py # TS-JEPA + SIGReg backbone (autoresearch edits this)
|
||
│ ├── prepare.py # LOCKED — data loading, tokenization, export
|
||
│ └── requirements.txt
|
||
├── specs/ # Research specs (one per phase/experiment type)
|
||
├── experiments/ # Per-run outputs: embeddings, metrics.json, git tag
|
||
├── results/summaries/ # Human-readable outcome per experiment
|
||
├── program.md # Autoresearch agenda — researcher edits this
|
||
├── DECISIONS.md # Architecture Decision Records
|
||
└── Taskfile.yml # task data:fetch, task experiment:run, task eval:*
|
||
```
|
||
|
||
## Phase structure
|
||
|
||
- **Phase 0** (current): MAE baseline on EUR/USD hourly 2008–2022.
|
||
Gate: silhouette > 0.20, MAE > PCA, ±10% over 3 reruns.
|
||
- **Phase 1**: TS-JEPA + SIGReg autoresearch sweep, 50 experiments.
|
||
Gate: val_vol_r2 > GARCH baseline AND Kupiec p > 0.05.
|
||
- **Phase 2**: MTS-JEPA multi-resolution hypothesis.
|
||
- **Phase 3**: Internal bank tick/position data (future, out of current scope).
|
||
|
||
## Data
|
||
|
||
DUKASCopy hourly OHLCV, 10 G10 pairs, 2008–2022 train / 2023 val / 2024 test.
|
||
Features: log-return, log rolling-20-period HV, VIX (daily interpolated).
|
||
Weekend gaps handled explicitly. See ADR-002.
|
||
|
||
## Key conventions
|
||
|
||
- `prepare.py` is LOCKED — never modified by agents or autoresearch
|
||
- Evaluation metrics are always computed by the Go harness, never in Python
|
||
- Every experiment gets a git tag: `exp/YYYYMMDD-description`
|
||
- Null results are recorded explicitly in `results/summaries/` — do not iterate silently
|
||
- `program.md` is the only file the researcher edits to steer autoresearch
|
||
- CI runs `task check` (lint + vet + test) only — no GPU, no training
|
||
|
||
## Evaluation metrics
|
||
|
||
Primary (autoresearch optimizes): `val_vol_r2` — linear probe R² on 1-day
|
||
realized volatility from frozen embeddings, computed by Go harness.
|
||
|
||
Secondary (logged, not optimized): Kupiec p-value (VaR 99% backtest on EUR/USD).
|
||
Must co-move with val_vol_r2 — checked from experiment 1.
|
||
|
||
Diagnostics: silhouette score (regime clustering), PC1/HV correlation (collapse check).
|
||
|
||
## Benchmarks to beat (trading desk comparison)
|
||
|
||
- GARCH(1,1) — volatility forecasting baseline
|
||
- Historical Simulation VaR (250-day rolling) — Basel default
|
||
- EWMA RiskMetrics (λ=0.94)
|
||
|
||
## Agent guidance
|
||
|
||
Read `DECISIONS.md` before making architecture suggestions.
|
||
Do not modify `prepare.py` or `src/eval/`.
|
||
Do not suggest changing the Python/Go separation.
|
||
Training runs are always manual via `task experiment:run` — never triggered by CI.
|
||
When implementing, follow Go conventions in `.skills/go-patterns/SKILL.md`.
|