Principle
Separate discovery tools from evidence sources
The thing that found the evidence is not necessarily the evidence.
When it fits
- An AI answer, search snippet or recommendation surfaces a useful claim.
When to avoid it
- Some expert syntheses are legitimate evidence sources themselves; 'primary' is not automatically superior for every question.
Why it matters
Use AI, search ranking, newsletters and aggregators to discover candidates. Then open and inspect the source appropriate to the claim—primary study, standard, official guidance or strong synthesis. Preserve the discovery route for provenance if useful, but cite the evidence source for the factual proposition.
An example
An AI tool suggests a new 2026 experiment; the corpus claim links to the paper, not to the AI conversation.
Check your result
Every material claim can point beyond the discovery interface to an inspectable evidence source.
Keep this limit in mind
- Some expert syntheses are legitimate evidence sources themselves; 'primary' is not automatically superior for every question.
Connected ideas
Useful withTrace the claim to an accountable origin before counting citations
Evidence and sources
Generative-AI literature synthesis can contain hallucinated or misattributed evidence, so generated summaries should not substitute for inspecting the underlying source.
AI tools vary and can still be useful for discovery, query expansion and triage with verification.
Can generative AI reliably synthesise literature? exploring hallucination issues in ChatGPT · Hallucination and attribution findings