v4.0

Evidence-First Financial AI

Open-source equity research where every composite signal traces back to a verifiable SEC filing or deterministic supply-chain cascade. Replayable point-in-time. Tamper-evidenced via a public git-anchored Verified Research Ledger. Research and education only.

Agent Research API · MCP · LangChain/LlamaIndex · pip install yuclaw
Disclaimer — YUCLAW research output. Not investment advice. Past performance does not guarantee future results. Signal labels are research classifications, not buy/sell recommendations. YUCLAW is not a registered investment adviser. Past results — in-sample or forward-tracked — do not predict future performance.
How it works

1 · Evidence layer

SEC EDGAR filings (Form 4, 8-K, 10-Q, 10-K, 6-K) are extracted with a local Llama 3.1 70B model. A deterministic SourceLock Guard validates every extraction against the source text before any signal sees it.

2 · Composite scoring

Nine components combine into a confidence-weighted composite. C6 event impact carries the highest weight (0.18) — by design, the evidence layer leads.

3 · Time-machine replay

Any signal can be recomputed as of a past date. Point-in-time filtering (available_as_of <= as_of) is leak-audited; reproducible via the yuclaw replay CLI or REST API.

4 · Verified Research Ledger

Each day's published signals have their content hashes committed to a public git repo (yuclaw-trust). Anyone can call yuclaw verify to confirm a signal hasn't been edited since publication.

Current signals — Forward Tracking Ledger
TickerSignal labelScore
COPSTRONG_BULLISH+0.612
XOMSTRONG_BULLISH+0.612
XLESTRONG_BULLISH+0.601
PEPBULLISH+0.512
AXPBULLISH+0.509
WFCBULLISH+0.495
CBULLISH+0.489
SLBBULLISH+0.478
MSBULLISH+0.468
INTCBULLISH+0.449
DELLBULLISH+0.443
PSXBULLISH+0.435
MABULLISH+0.425
AMATBULLISH+0.425
HPEBULLISH+0.421
IBBBULLISH+0.419
KREBULLISH+0.419
SMHBULLISH+0.419
XBIBULLISH+0.419
XLFBULLISH+0.401
MRVLBULLISH+0.401
LUNRNEUTRAL+0.398
COSTNEUTRAL+0.396
PGNEUTRAL+0.396
XLPNEUTRAL+0.396
WMTNEUTRAL+0.396
ABBVNEUTRAL+0.395
GOOGLNEUTRAL+0.374
BACNEUTRAL+0.370
KONEUTRAL+0.366
DIANEUTRAL+0.350
EEMNEUTRAL+0.350
FXINEUTRAL+0.350
GLDNEUTRAL+0.350
IEFNEUTRAL+0.350
IWMNEUTRAL+0.350
MDYNEUTRAL+0.350
QQQNEUTRAL+0.350
SLVNEUTRAL+0.350
SPYNEUTRAL+0.350
TAILNEUTRAL+0.350
TLTNEUTRAL+0.350
UUPNEUTRAL+0.350
VIXYNEUTRAL+0.350
VXXNEUTRAL+0.350
PYPLNEUTRAL+0.332
NVDANEUTRAL+0.316
XLCNEUTRAL+0.315
JNJNEUTRAL+0.304
TMONEUTRAL+0.304
ABTNEUTRAL+0.286
BMYNEUTRAL+0.286
MRKNEUTRAL+0.286
PFENEUTRAL+0.286
UNHNEUTRAL+0.286
XLVNEUTRAL+0.286
CVXNEUTRAL+0.286
LRCXNEUTRAL+0.262
DHRNEUTRAL+0.253
ARMNEUTRAL+0.236
MUNEUTRAL+0.227
RKLBNEUTRAL+0.223
VNEUTRAL+0.220
AMDNEUTRAL+0.203
XLREWATCH+0.196
LLYWATCH+0.195
CRCLWATCH+0.188
XLIWATCH+0.158
JPMWATCH+0.156
XLKWATCH+0.155
XLYWATCH+0.155
MSFTWATCH+0.149
AMZNWATCH+0.138
GSWATCH+0.112
XLUWATCH+0.085
AAPLWEAKENING-0.065
XLBWATCH+0.055
METAWATCH+0.031
TSLAWATCH+0.021
data as of 2026-05-31 19:29 UTC · landing page rebuilt 2026-06-01 17:03 UTC
Public signal vocabulary

Labels are research classifications, not buy/sell recommendations:

STRONG_BULLISH · BULLISH · NEUTRAL · WATCH · WEAKENING · NEGATIVE_EVENT · BEARISH_WATCH · RISK_ALERT

There is no SELL or SHORT label. The SDK's _validate_label() is invoked on every signal-bearing return.

Install + try it
pip install yuclaw
yuclaw demo                         # 3-minute guided "Why AMD?" journey
yuclaw why NVDA                     # signal + evidence trail
yuclaw verify NVDA --as-of 2026-05-20   # check the public ledger

SDK + REST API + MCP server documented at github.com/YuClawLab/yuclaw-brain. REST API terms at /API_TERMS.md.

Disclaimer — YUCLAW research output. Not investment advice. Past performance does not guarantee future results. Signal labels are research classifications, not buy/sell recommendations. YUCLAW is not a registered investment adviser. Past results — in-sample or forward-tracked — do not predict future performance.