Memory · System Knowledge
🧠

The memory layer is your dialogue with the model

Markets change. What predicted outcomes in Q1 may be noise by Q3. The memory layer lets you correct the model's understanding, add your own knowledge, and flag trades as meaningful or anomalous. Everything you do here directly affects how the model weights future decisions. Approved memos feed into weight updates. Annotations change training weights. Knowledge entries inform scoring context.

Regime & MemosReview and approve
Regime: STABLE
All factor weights at baseline (v1).
Collecting data — model will adapt after 50+ trades.
SYSTEM STATUS
Phase 1 active — observation mode. Markets are being collected and scored every 5-10 minutes. Weekly memos will be auto-generated once paper trading begins in Phase 2.
Phase 1Observing
Knowledge BaseCategorized insights

Free-form knowledge entries about how specific market types behave. Each entry has a confidence score that decays over time without reinforcement.

No knowledge entries yet

Examples: "Political markets show elevated velocity noise 30 days before elections" · "Crypto markets: divergence with BTC implied probability is reliable when BTC vol is low"

Trade AnnotationsLabel trades to guide learning

Every trade can be annotated to tell the model how to treat it during weight updates.

LEARNOutcome was meaningful — upweight in training
EXCLUDEExternal cause — remove from training
WRONG REASONRight outcome, wrong signal — downweight
STRUCTURALReveals market type behavior
ANOMALYUnusual event — don't generalize

Annotations will appear once paper trading generates trades