YUCLAW v7.0.1
Validation LabSMH Evidence LensXLK Evidence LensCanada Resources EvidenceForward TrackingSignal ReviewExplorerSectorsEvidence ScoreboardGitHubPyPILedgerMethodologyHome

Evidence-First Financial AI

Every signal traces to a real SEC filing.

Agent Research API · MCP · LangChain/LlamaIndex · pip install yuclaw

About YUCLAW

Disclaimer — Research & education only. Not investment advice. Signal labels are research classifications, not buy/sell recommendations.

Built in Canada — from Lake Ontario to Lake Louise and Kananaskis Lake — with gratitude to the country whose land and light frame this work.

How we work
  • We don’t ask you to trust us. We give you the hash.
  • We don’t predict. We register, compute once, and disclose.
  • We don’t hide the days we were wrong. We chain them.
What you get
  • Analysts The evidence behind every label, and the label’s limits.
  • Builders Machine-readable receipts — passports, endpoints, and a registry you can walk line by line.
  • Institutions A record that can be audited without asking us.
Current signals — Forward Tracking Ledger
Current research classifications — not recommendations
TickerSignal label Score Evidence coverage
XLCNEUTRAL+0.3980
MRKNEUTRAL+0.36477
PFENEUTRAL+0.36477
GOOGLNEUTRAL+0.33970
XLVNEUTRAL+0.3370
IBBNEUTRAL+0.3050
ABBVNEUTRAL+0.27979
WFCNEUTRAL+0.27051
TSLANEUTRAL+0.26874
XLPNEUTRAL+0.2530
BMYNEUTRAL+0.25069
XBINEUTRAL+0.2470
KRENEUTRAL+0.2370
COSTNEUTRAL+0.23547
UUPNEUTRAL+0.2330
PSXNEUTRAL+0.23274
LRCXNEGATIVE_EVENT-0.23090
RKLBNEGATIVE_EVENT-0.22080
CRCLNEUTRAL+0.21584
AMATNEGATIVE_EVENT-0.21490
CNEUTRAL+0.21341
TLTNEUTRAL+0.2100
PEPNEUTRAL+0.21052
SPYNEUTRAL+0.2090
DHRNEUTRAL+0.20669
SMHNEGATIVE_EVENT-0.2020
QQQNEUTRAL+0.2010
IEFWATCH+0.1980
XLFWATCH+0.1980
TAILWATCH+0.1980
DIAWATCH+0.1950
UNHWATCH+0.19360
AXPWATCH+0.19173
BACWATCH+0.18952
MSWATCH+0.18969
FXIWATCH+0.1880
COPWATCH+0.18478
JPMWATCH+0.17784
XLEWATCH+0.1750
EEMWATCH+0.1570
XLYWATCH+0.1570
GSWATCH+0.15685
IWMWATCH+0.1530
XOMWATCH+0.14954
TMOWATCH+0.14979
LLYWATCH+0.14873
KOWATCH+0.14775
PGWATCH+0.14775
MDYWATCH+0.1430
AMZNWEAKENING-0.14287
VXXWATCH+0.13925
SLVWATCH+0.13941
MUWEAKENING-0.13682
JNJWATCH+0.12680
CVXWATCH+0.12673
VIXYWATCH+0.12441
AMDWEAKENING-0.119100
GLDWATCH+0.11741
XLREWATCH+0.1140
MSFTWEAKENING-0.11485
ABTWATCH+0.10379
SLBWATCH+0.09575
NVDAWEAKENING-0.09195
ARMWEAKENING-0.08390
WMTWATCH+0.07779
PYPLWATCH+0.07689
XLBWATCH+0.0600
XLIWEAKENING-0.0380
MRVLWEAKENING-0.03692
XLKWEAKENING-0.0360
AAPLWATCH+0.03384
INTCWATCH+0.02374
HPEWEAKENING-0.01666
MAWATCH+0.01680
METAWEAKENING-0.01285
DELLWATCH+0.00785
LUNRWEAKENING-0.00690
XLUWATCH+0.0050
VWATCH+0.00084

Evidence coverage = how much evidence stands under this classification — coverage, not prediction (Evidence Coverage v1, registered protocol). Score = composite research score. It is not an expected return, a probability, a price target, or a recommendation.

Public signal vocabulary

Labels are research classifications, not buy/sell recommendations:

STRONG_BULLISH · BULLISH · NEUTRAL · WATCH · WEAKENING · NEGATIVE_EVENT · BEARISH_WATCH · RISK_ALERT (each label links to its locked threshold definition)

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

How it works

1 · Evidence layer

SEC EDGAR filings (Form 4, 8-K, 10-Q, 10-K, 6-K, 40-F) 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.

Full disclaimer & methodology

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.

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.
About YUCLAW — mission and vision

YUCLAW

Evidence-First Financial AI
The Science Trust Layer for Financial AI.

Evidence before answers.

Financial AI normally gives you an answer.

YUCLAW gives you the evidence — what was known, when it was known, what it can support, what it cannot, and whether the conclusion survived.

Mission

Make financial AI accountable to evidence.

A public, hash-linked record, built to be recomputed by anyone.

Vision

Become the Science Trust Layer for Financial AI.

The evidence infrastructure that AI systems, researchers, and institutions use to decide what deserves to be believed.

How we work

Principle Practice
We don’t ask you to trust us. We give you the hash.
We don’t predict. We register, compute once, and disclose.
We don’t hide the days we were wrong. We chain them.

What you get

For What you get
Analysts The evidence behind every label, and the label’s limits.
Builders Machine-readable receipts — passports, endpoints, and a registry you can walk line by line.
Institutions A record that can be audited without asking us.

Statistics is one instrument. Evidence is the foundation. Science is the discipline.

AI is the market. Trust is the product. Accountability is the mission.

🍁 Built in Canada

Use YUCLAW in your research
1 · Verify the record

pip install yuclaw then yuclaw replay-lab.
No install: tools/replay_lab.py (stdlib only) against the published bundle.
Exit 0 = every statistic and evidence-ledger root reproduced. How to report a replication →

2 · Inspect one evidence trace

One real Suncor 6-K, end to end:
filing → exhibit → extracted prose → event type → grade → C6 posture.
Open the trace → · example evidence memo (Suncor) →

3 · Cite a research lens

Every evidence packet ships a ready citation snippet
(version, data-through, build date, source commit).
Get the citation →

📖 User Guide (PDF) — from pip install to full verification, six pages. · 📖 Guide de l'utilisateur (FR)

Status — proven · not proven · accruing

Rendered from one shared source (v3/web/useful_blocks.py) on every page that shows it, so the copies cannot drift. Statuses are measured, not aspirational.

Proven (verifiable today)
  • ✓ Replay works — one command reproduces every Lab statistic and evidence-ledger root from published data
  • ✓ Ledger anchored daily — sha-256 daily roots committed to a public git repository before pages update
  • ✓ Evidence traces to filings — every accepted event carries a source URL, accession number, and verified excerpt
  • ✓ Coverage measured — SEC-filer weight per lens is stated as measured, never rounded up
  • ✓ Snapshots are point-in-time — daily as-of writes, zero retroactive edits (outage window disclosed, not repaired)
  • ✓ Evidence-tier names are never scored — enforced by positive gating and a standing negative check
Not proven
  • ✗ Forward alpha — no spread, IC, or alpha significant at 5% with adequate power
  • ✗ C6 risk-gate sign — rareness confirmed OOS 2026-07-06 (22% fire rate, n=9 held-out); sign confirmation pending (elevated arm n=2; accrual live from 2026-07-16)
  • ✗ Peer-model CAR lead — event-study lead over peer models is not established; live-era sample remains small
Accruing
  • · Forward out-of-sample record — one period per trading day, accruing daily
  • · Matured CAR events — each accepted event matures into the event study after its forward window completes
  • · C6 elevated arm — live Form-4 ingestion since 2026-07-16 restores the insider stream to production inputs
  • · External replications — the replication log accrues as independent runs are reported
For AI agents & researchers

YUCLAW is the open evidence layer underneath AI research tools. Start with llms.txt and the machine-readable evidence_index.json (every page, packet, and protocol with stable URLs and data-through dates). Packets carry derived statistics, event CSVs, engine run JSONs, and citation snippets; yuclaw replay-lab re-computes the published statistics from the public bundle. Derived data only — preserve the disclaimers when quoting; nothing here is advice or a recommendation.

Install + try it
pip install yuclaw
yuclaw demo                         # 3-minute guided "Why AMD?" journey
yuclaw why AMD --as-of 2026-05-20   # bundled offline signal
yuclaw verify AMD --date 2026-05-20 # check the ledger record
# all tickers/dates: connect the local backend — see README

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

YUCLAW v7.0.1 · YuClawLab · Full Disclaimer · 🚀 5-minute tour · 🤖 For AI builders · 📐 EvidenceBench · 📖 User Guide (PDF) · 📖 Guide de l'utilisateur (FR) · Methodology · Replication · Today's Evidence Changes · YUCLAW's Lane · Weekly Note · Apache-2.0 Licensed
Data through 2026-09-14 (last completed U.S. trading day); generated at 2026-09-15 04:24 UTC.