Something happened. Does it reach your book?

SigmaLens reads public filings and public news, works out which of your positions each event actually reaches and by what route, and hands you the document it came from. When an event reaches none of them, it says that too.

Every figure on this page is one you can check, including the ones we have withdrawn.

Reads directly from SEC EDGAR GDELT OFAC US Treasury
Event Entity Exposure path Your book Why it matters Primary evidence
A real event, end to end filed 2 September 2026
  1. Event GoPro, Inc. filed an 8-K under item 1.01, entry into a material definitive agreement
  2. Entity GoPro, Inc. (GPRO), matched from the filer, not from a headline
  3. Exposure path GPRO’s own SEC filings → direct equity holding → GPRO
  4. Your book the position you hold in GPRO, and nothing else in the book
  5. Why it matters a merger agreement with Action Acquisitions LLC and Starman Optical, Inc.; $1.14 in cash plus 0.1 of a share; conditions stated in the filing. Every one of those is quoted from the sentence it was read from.
  6. Primary evidence the filing itself, on sec.gov, with the merger agreement attached as EX-2.1

A filing establishes that the filing was made and what it says. It does not establish what the market will do, and SigmaLens does not say that it does.

Live market sentiment by sector, scored from current news
Loading a live read…

What we claim, checked in full.

Four claims, each one checkable inside the product rather than taken on trust, and true every time you open a holding. Then a fifth claim we tested, found didn't hold, and withdrew rather than kept.

01
Every reading traces to a primary document. The filing, the item, the sentence a term was read out of, and a link to the original on sec.gov. Nothing on the page is a claim you have to accept because we made it.
02
The route is named, not implied. Not "exposed to China" but which exposure, through which channel, at what weight, and whether it is first or second hand.
03
It says what it cannot see. Positions that did not resolve are named and counted on the page. A book we cannot read is never rendered as a book with nothing happening in it, which is the failure every quiet dashboard hides.
04
The score shows its own arithmetic. Magnitude, direction, stance and exposure weight, each with the reason it reads that way, and the four multiplied back together give the number on screen. "Why is this a 1.7 and not a 0.5" has an answer on the page.

These are properties of the system, not performance figures, and that distinction is the point: each one is either true when you open a holding or it is not, and you can check it in a minute without taking our word for anything.

And one we withdrew

−0.05 against a sort-by-volume list, over 42 days. No advantage.

We used to claim the ordering beat a naive alternative. It does not. Forty-two days never used to build the engine, in three blocks, judged by 45 blinded AI runs (not human professionals), never told which system produced what they saw. Re-measured on the configuration we actually ship, the ranking comes out at −0.05, Fisher p = 0.26, winning 20 of 42 days. On the 2023 to 2024 block the plain volume sort won outright.

Why the old number was wrong

We published +0.12 to +0.21 and believed it. Auditing an unrelated change, we found the evaluation harness had been building its exposure graph without the entity map the product uses. The evidence had never described the shipped engine. We rebuilt all three blocks and re-ran every evaluator; the advantage disappeared. The engine now records a hash of its own configuration alongside each result so this cannot recur silently. The full working, all three blocks → Every claim and its status →

The four claims above are separate from the ordering claim, are measured separately, and none of them depends on it. Ranking was removed from the product; the withdrawal stands and the figures for it are published above and on the claim register.

One headline. Three holdings. Opposite answers.

Everyone knows an oil supply shock helps oil producers. The useful part is the rest of the chain, and it is the part a person reading the news does not have time to trace.

The event, worked through as an example Crude supply disruption 40 articles, corroborated
XOM Oil & Gas Integrated · producer bullish
UAL Airlines · fuel cost bearish
KMB Household products · feedstock cost ~35% · crude → cracker → resin bearish, faintly

The third row is the one worth paying for. Kimberly-Clark has never bought a barrel of crude, but the resin in its products is made from one. SigmaLens carries that through with a weight and a stated reason, and scores it more faintly than the airline that burns the fuel directly, because it is a smaller share of cost and arrives with a lag. This chain is a worked example of the output format. The relationships are the curated ones the product uses; the cost share and the article count are illustrative. Live output, on a book you enter yourself, is one click away.

Your exposures, checked against what the prices actually did.

Most tools infer your exposures from a sector code and leave it there. We fit each holding against crude, gas, wheat, the 10-year, the dollar and gold over five years, with the market's own move removed, and report four answers: confirmed, contradicted, cannot detect, or a link the prices show that nobody modelled. On our own sample that last group included a refiner with no crude exposure on its record.

Sample portfolio live
Loading…
01

Measured exposure, not asserted

Each holding fitted against crude, gas, wheat, the 10-year, the dollar and gold over five years, with the market's own move taken out. A link is reported only when it clears both bars: distinguishable from noise, and large enough to explain something.

BP +0.42% per 1% crude R² 0.37, n=250 illustrative shape, not a published fit
02

Exposures you can't see

Your US-listed Apple is really a Taiwan bet, because TSMC makes its chips. SigmaLens surfaces the supply-chain exposure that country and sector labels miss.

AAPL · Taiwan ~75% via TSMC curated relationship, illustrative weight
03

What-if in one tap

Pick a scenario, a Strait of Hormuz closure or a Taiwan crisis, and see your book's reaction holding by holding before it happens.

Hormuz closure → your book +2.1 illustrative, on a sample book
04

A record you can check, including when it is bad

Every signal is written to a ledger and resolved against what the market actually did, and the resolved record is published whether or not it flatters us. It is a record, not a promise that the reading improves: we have withdrawn two published figures after auditing them ourselves, and both retractions are on the evidence page with the numbers that replaced them.

From your holdings to a clear read in under a minute.

Step 1

Add your holdings

Type them, paste them, or load a sample. Stocks, ETFs and funds all work.

Step 2

See the read

Per-holding sentiment, your net exposure across themes, and the events driving each one, each linked to its source article.

Step 3

Stay ahead

Get alerted when a holding turns strongly bullish or bearish. In-app, by email, or to Slack.

What you get, and where the limits are.

SigmaLens is in design-partner phase. Everything below is open to the people using it, and no commercial terms are set. The tiers describe how much book each account can carry, not what anything costs.

Standard
Everything you need to read your book.
  • Per-holding news readings, signed, with the arithmetic behind each one
  • Net-exposure compass and scenarios
  • Supply-chain exposures and sector board
  • Market regime and macro propagation
  • Up to 15 holdings
  • Daily digest alerts, in-app and email
Get started
Design partners
Full book
For a book too large to read by hand.
  • Everything above, plus:
  • Up to 500 holdings
  • Instant threshold alerts
  • Per-holding history and analogues
  • Institutional (13F) holders and API access
Request access

See how today's news reads for your portfolio.

It takes a minute.