tengu_v3_intel_pnl_attribution
shallowio.github.Hlobo-dev/tengu-firm · Verify this server
Daily PnL track record for the paper book, Carhart 4-factor-decomposed. Snapshotted nightly. Returns `rows[]` of trading days with per-row gross/net return in basis points, transaction cost, turnover, plus the Carhart factor contributions (MKT-RF, SMB, HML, UMD) and residual alpha — the institutional skill measure that strips market/size/value/momentum beta. Window aggregate: mean daily bps, hit rate, annualised Sharpe, cumulative net + alpha. Default 30 trading days; query `?days=N` (bounded to 365). Use this to ground any track-record claim the chat makes — e.g. 'our paper book made +29 bps yesterday, +111 bps alpha contribution'. 1h cache.
1 trials · measured 8 days ago
tengu_v3_intel_pnl_attribution scores 100.0/100 on Vouch's measured behaviour index, from 1 real invocation trials against io.github.Hlobo-dev/tengu-firm, measured 25 Aug 2026 under methodology v0.2.0. Every measured component scored 100.
Component breakdown
| Component | Weight | Value |
|---|---|---|
| Reliability | 35% | not applicable |
| Schema integrity | 25% | 100.0 |
| Failure behaviour | 15% | not applicable |
| Latency | 15% | not applicable |
| Concurrency | 10% | not applicable |
Tool details
- Transport
- remote
- Credential class
- unreachable
- Category
- Finance & compliance
- Input schema
- not declared
- Output schema
- not declared
- Side-effect classification
- unclassified
Score history
| Day | Score | Tier | Methodology |
|---|---|---|---|
| 2026-08-25 | 100.0 | shallow | v0.2.0 |
Probe evidence
| Probe | Outcomes |
|---|---|
| schema_integrity | pass: 1 |
Raw request/response logs are not archived yet — the outcome counts above are drawn directly from every recorded trial.
Embed this score
Available for every tool, scored or not — not a verification perk. Always links back to this page.
[](https://vouch.tools/tools/47c9ccac-0cad-4192-acc1-9193f950f612)