Portfolio Agent EvalsHarbor task suite · ETF analyze → backtest → rebalance
← All themes
AnalyzeTheme 01

Data Forensics & Canonicalization

Turn hostile vendor exports into a panel you can trust — and prove what you found.

Why this theme exists

Every downstream number is only as good as the price panel. These tasks hand the agent multi-vendor ETF price files with planted defects (format drift, duplicates, unit scaling, undocumented splits, mis-stamped dividends, calendar mismatches) and require a canonical, adjusted, calendar-aligned panel plus an explicit anomaly ledger.

Capability under test

Data hygiene under adversarial conditions: detecting rather than silently smoothing defects, distinguishing genuine market events from data errors, and applying corporate-action math exactly.

Design notes

Anomaly placement is sampled from the trial seed at image build; the generator is removed from the image and re-run by the verifier. Scoring separates panel accuracy from anomaly recall/precision so that an agent which produces correct numbers by luck but cannot explain why still loses credit. Calibration: a 'trap-blind' cleaner (drop duplicates, forward-fill everything) must score below 0.5.

Tier ladder

  • Tier 11
  • Tier 22
  • Tier 32
  • Tier 40
TaskTierPhaseRewardGatesBudgetStatus
Profile raw price files against calendar and metadata
pf-data-provenance-profile

Profile every ticker's raw price file against the trading calendar and metadata and emit a structured data-quality report with exact counts.

T1
easy
Analyzepartial15 minready
Build a canonical adjusted price panel from messy vendor files
pf-data-canonical-panel

Turn messy multi-format price files plus a corporate-actions file into a canonical split- and dividend-adjusted close panel aligned to the trading calendar, and report every anomaly found.

T2
medium
Analyzemulti-metric40 minready
Multi-currency, multi-calendar alignment to USD returns
pf-data-currency-and-calendar

Merge a London-listed ETF quoted in pence with USD ETFs and FX rates, aligning trading calendars per an explicit rule, and produce USD daily returns.

T2
medium
Analyzepartial30 minready
Reconcile custodian dividends against the vendor file and rebuild total-return indices
pf-data-dividend-reconciliation

Reconcile dividends in the account transactions log against the vendor dividend file, find the ticker whose vendor records are stamped on pay-date instead of ex-date, and build a correct total-return index.

T3
hard
Analyzemulti-metric40 minready
Detect an undocumented split without misclassifying a genuine crash
pf-data-hidden-split

Detect a split missing from the corporate-actions file and adjust for it, while leaving a genuine one-day crash untouched.

T3
hard
Analyzemulti-metric40 minready