Skip to main content
A signal is a structured takeaway drawn from the most strategically relevant parts of a source. A signal may represent a full article, a segment of a podcast, a section of an SEC filing, or any other discrete unit of content worth tracking. Gildea processes signals daily through an automated pipeline, prioritizing what materially changes the strategic picture.

What gets ingested

Gildea ingests from a curated set of 500+ sources across these formats:
FormatExamples
EssaysBlog posts, newsletters, long-form analysis
News articlesIndustry reporting, first-party announcements
PodcastsTranscribed and decomposed
SEC filings10-Ks, 10-Qs, 8-Ks, proxy statements
Research papersAcademic and industry research
Social mediaExpert discourse and announcements
Earnings transcriptsQuarterly earnings calls
Press releasesProduct launches, partnerships, policy announcements

Two types of signals

Every signal is classified into one of two content types:

Event signals

Key development signals sourced from global reporting and first-party announcements.
DecompositionDescription
SummaryWhat happened, broken into individual sentences
ClaimsSpecific factual assertions extracted from the source

Expert analysis signals

Expert analysis signals from leading researchers, operators, investors, and analysts who explain what developments mean.
DecompositionDescription
ThesisThe author’s core argument, broken into individual sentences
ArgumentsSupporting arguments, each with its own sentences and claims
ClaimsSpecific factual assertions within the argument

Decomposition structure

Expert analysis signals

Event signals

Text units

All decomposed pieces are text units. This is the fundamental atom of Gildea’s data model.
Unit typeFound inScoring mode
thesis_sentenceExpert analysis signalsregression
argument_sentenceExpert analysis signalsregression
summary_sentenceEvent signalsregression
analysis_claimExpert analysis signalsnli
event_claimEvent signalsnli
Every text unit has:
  • A verification verdict (only pass is served)
  • A scoring mode (nli for claims, regression for sentences)
  • A primary score (method-specific, do not compare across modes)
Claims and sentences use different scoring methods. Do not compare primary scores between nli and regression modes.

Signal card vs. signal detail

The list endpoint returns lightweight signal cards with metadata and a decomposition_text preview (thesis or summary text). The detail endpoint returns the full decomposition tree with all verified text units. Use include=evidence for source evidence snippets. See Progressive Disclosure for the full pattern.