Draft preview. Not published. Signup and sponsor areas are placeholders.

Method

How items are collected and labeled, and what the labels mean.

How it works

  1. Scripts collect items from public feeds: education news outlets, peer-reviewed journals, and preprint servers such as arXiv.
  2. Items that do not mention AI and education are filtered out.
  3. Each item gets an evidence flag, learning principle tags and an audience tag (K-12, higher ed, adult ed / CTE / workforce, or general) using fixed keyword rules. No person picks individual labels.
  4. Summaries are the source's own opening sentences, trimmed. For journal feeds that publish no abstract, the summary is the publisher listing (journal, authors, issue) and is marked as such. Every item links to the original.

Item types

Study: from a peer-reviewed journal feed. Study (preprint): from arXiv. Commentary: a researcher or writer discussing research. Launch / announcement: a product launch or announcement. Report / framework: a framework, guidance, standards or report release. News: everything else.

Evidence flags

These labels describe source type and cited research; they do not rate study quality or learning impact.

Research-backed

From a peer-reviewed journal feed.

Promising

A preprint, or an item whose text mentions a study, trial, review, experiment, survey, new research or report findings.

No evidence cited

A product launch or announcement whose collected text cites no study.

Context

News, policy or opinion with no study and no product claim.

A flag describes the kind of evidence a source cites. It is not a judgment of quality, and it is not a rating or endorsement. Items with no keyword match get no principle tag rather than a guess.

Learning principle tags

Retrieval practice, Spacing and interleaving, Feedback, Cognitive load, Worked examples and explicit instruction, Metacognition and self-regulation, Motivation and engagement, Reading and writing, Inclusion and accessibility, Tutoring and personalization. Separate topic tags cover assessment and grading, academic integrity, and policy and governance.

Disclaimer

Evidence Signal is an automated tracker. Items are collected from public sources and labeled by fixed, published rules, not reviewed one by one by a person. Labels describe what kind of evidence a source cites. They are not ratings, endorsements, or advice. Summaries are excerpts from the original source, which is always linked. Read it before you act on anything here. Spot an error? Use the corrections link and we'll fix it and log the change.

Sponsor policy

Evidence Signal accepts sponsors whose products or services serve educators, but sponsorship never buys coverage, placement in the tracker, or a better evidence flag. Every sponsored item is labeled "Sponsored" and kept separate from the automated tracker. Sponsors cannot review or edit content before it is published. We do not accept sponsors that sell student data, make claims of learning results they won't back with a source, or market directly to children. Labels on a sponsor's own products are set by the same fixed rules as everyone else's, and we may decline or end any sponsorship that conflicts with these terms.

Corrections

Spot a wrong label, broken link or error? Email a correction. Fixes are listed in the corrections log.