Loading page...Загружаем страницу...正在加载页面...
AtlasRepo

Receipts: paste text, get every claim marked by whether a source backs it up

Описание и применение

Receipts автоматически проверяет утверждения в тексте, выдавая статус SUPPORTED, CONTRADICTED или UNSUPPORTED, и явно указывает, когда не знает, что позволяет авторам избежать ошибок, которые легко пропустить.

Задача

Fast‑published text contains plausible errors that readers overlook, such as wrong dates or figures, and existing claim checkers often report “unsupported” as false, giving a false sense of confidence.

Результат

Receipts automatically verifies claims in text, distinguishing supported, contradicted, and unsupported cases, and explicitly indicates uncertainty, thereby reducing the risk of plausible errors slipping through.

Рабочий процесс

  • Paste text into the browser demo or run the CLI
  • The model extracts atomic, stand‑alone claims and proposes a Wikipedia search query
  • The query retrieves top Wikipedia pages via the open API
  • The tool filters retrieved sentences by vocabulary overlap with the claim
  • The model judges the claim against the filtered passages, returning a verdict and the passage used
  • The result is displayed with a clear label (SUPPORTED/CONTRADICTED/UNSUPPORTED) and source URL

Доказательства

Receipts reads a block of text, pulls out the claims that a source could settle, looks each one up, and marks it one of three ways: SUPPORTED, CONTRADICTED, UNSUPPORTED

Источник

The product is the third one. Most tools quietly treat "I could not find it" as "false," which means the tool is confident about things it never checked.

Источник

The model compares the claim against those passages and returns a verdict plus the passage it used. It is told, explicitly, to use only the passages and never its own knowledge.

Источник

The failure mode of a checker like this is a model "correcting" text from vibes. Every design choice is aimed at that: claims must stand alone, the judge sees only retrieved passages, the retrieved passages are filtered by vocabulary overlap with the claim, and a claim's numbers must match to the precision the claim states.

Источник

  • Дата записи: 2026-10-15T12:41:18.670Z