Direction, evidence grade, and study type are AI-generated labels (gpt-5-mini), not human-verified. Syntheses are LLM-written. "Tensions" are machine-detected candidates, not confirmed contradictions. A research-acceleration tool, not peer review.
How this is built →
1Distinct papers
3Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2025. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2302202750
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Ziyi Wang (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Governance: 1 paper
- Human Ai Collab: 1 paper
Claim outcomes
- Decision Quality: 1 paper
- Consumer Welfare: 1 paper
Papers in the Semantic Scholar view
Latest stored Semantic Scholar author observations only. Citation counts below are from the same provider and are not combined with other services.
Scroll the table horizontally to see every column.
| Paper | Author evidence | Date | Provider citations |
|---|---|---|---|
| Explanations help when AI is right but amplify errors when it is wrong: explained recommendations increase accuracy by 6.3pp when correct but reduce it by 4.9pp when incorrect, driving over-reliance; selectively providing explanations could raise healthcare value to $2.59bn annually versus $1.82bn under universal transparency.arxiv | Ziyi Wang provider id |
2025-12-09 | 1 |
Citation observation summary
Semantic Scholar supplied counts for 1 of 1 papers in this view; 0 are missing. The observed paper counts sum to 1 cumulative citations. This is a coverage summary, not an author score or h-index.