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

I Built an AI That Checks Whether Digital Products Deliver What They Promise

说明与用途

PromiseDiff 自动验证数字产品是否满足列表承诺,对每个声明进行分类并在发布前提供 Markdown 报告。它将 LLM 语义检查与 PDF 元数据提取相结合。

问题

Digital‑product listings often promise specific content (e.g., page counts, file formats, worksheets) that the delivered ZIP or PDF does not match, leading to refunds and negative reviews.

结果

In a demo with a 48‑page A4 Budget Planner PDF, PromiseDiff confirmed the page count, flagged the missing US Letter edition, and exported a Markdown report. A benchmark of ten synthetic PDFs achieved 90% exact‑label accuracy, 100% contradiction precision, and 75% supported recall.

工作流

  • Paste listing text into the UI
  • Upload the PDF or ZIP of the product
  • PromiseDiff parses claims with Gemma
  • Python validates measurable claims (page count, file existence, page size)
  • Gemma evaluates semantic claims against extracted text
  • Evidence validation checks filename, page, and exact quote
  • Results are displayed with evidence and exported as Markdown

证据

PromiseDiff shows what the files can back up, what they contradict, and what they simply cannot prove.

来源

missing evidence != contradiction

来源

exact-label accuracy = correct labels / total cases = 9 / 10 = 90%

来源

  • 记录日期: 2026-10-13T21:55:54.161Z