From the hash-bound evidence releases
Recorded claims
Each claim states what the inspected source says, at the recorded location—bounded by its scope and graded by its confidence. Nothing here is a synthesis across works.
Experiments with physicians report that presenting AI advice after an initial diagnosis produced better diagnostic accuracy and calibration than concurrent advice, with the difference attributed to more thorough information processing and engagement with the AI's reasoning.
Scope: publisher-deposited abstract metadata; physician work process and timing of AI advice; participant denominator and study period are not stated
The abstract reports that the timing of AI advice changes physicians’ diagnostic information processing, engagement with AI reasoning, and ability to distinguish correct from incorrect advice.
Scope: abstract-level
Structured relationships
In-corpus citations
Only source-supplied cites relationships whose two endpoints are admitted are shown. Invocation evidence remains a separate relationship.
Cites (2)
Cited by (1)
Boundaries
Limitations & independence
Recorded at coding time, carried with the work forever. A claim without its limits is not evidence.
Recorded limitations
- Abstract-level Crossref metadata only; the blocked publisher surface was not retried.
- The captured abstract does not state participant denominators or study periods.
- Crossref supplies only a year and month for publication, so published_date is null rather than an invented day.
- Full text was not inspected.
- Crossref metadata only; full text was not inspected.
- The publisher surface was not queried after the lane’s quarantined dynamic-challenge response; no independent publisher-page verification was attempted.
Source independence
publisher-only