Glossary

Terms worth more than one sentence.

Short definitions live in the term list. These explainers cover the three concepts that decide whether a web-enabled feature can be checked, trusted, and maintained.

Glossary explainer · 2 min read

What Is Source Provenance in AI Systems?

The record connecting an output back to the page, moment, and sentence it came from.

Source provenance is the retained record of where a piece of information came from and when it was obtained. In an AI system it usually means three things travelling together: a canonical URL, a retrieval timestamp, and the excerpt supporting the claim. It tells you the origin of a statement; it does not tell you the statement is true.

provenancecitationsglossary

Glossary explainer · 2 min read

What Is Semantic Change Detection?

Deciding whether a page changed in a way that matters, rather than whether its bytes changed.

Semantic change detection compares the meaning of a page between two points in time instead of its raw markup. A byte diff fires on a rotated testimonial or a new build hash; a semantic comparison asks whether a tracked fact — a price, a limit, a supported region, a policy clause — is different now. It is the difference between a monitoring system people read and one they mute.

monitoringchange detectionglossary

Glossary explainer · 2 min read

What Is Structured Extraction?

Turning a page into typed records against a schema you defined first.

Structured extraction is the process of converting unstructured page content into records that match a schema: named fields, declared types, explicit optionality. The output is something software can validate, store, compare, and sort — as opposed to a summary, which only a person can evaluate. The schema comes first; that ordering is what separates extraction from interpretation.

extractionschemaglossary

Term list

20 short definitions covering crawling, chunking, canonical URLs, and the rest of the vocabulary used across this site.

Open the full glossary →