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
14Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2303655489
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Wei Yang Bryan Lim (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Governance: 1 paper
- Innovation: 1 paper
Claim outcomes
- Other: 1 paper
- Error Rate: 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 |
|---|---|---|---|
| A new benchmark finds that AI-generated images make convincing refund fraud — current multimodal LLMs and specialized detectors routinely miss synthetic 'damaged' evidence and are inconsistent across generators, leaving e-commerce and service platforms exposed.arxiv | Wei Yang Bryan Lim provider id |
2026-05-09 | 0 |
Citation observation summary
Semantic Scholar supplied counts for 1 of 1 papers in this view; 0 are missing. The observed paper counts sum to 0 cumulative citations. This is a coverage summary, not an author score or h-index.