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
1Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2157052
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Mo Hai (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 1 paper
- Org Design: 1 paper
Claim outcomes
- Decision Quality: 1 paper
- Task Allocation: 1 paper
- Ai Safety And Ethics: 1 paper
- Error Rate: 1 paper
- Team Performance: 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 |
|---|---|---|---|
| Correlated errors across language models limit the benefits of majority voting and alter the optimal approval threshold; modeling state-dependent dependence on held-out items cuts screening loss by about 15.7% relative to majority voting and gives modest additional gains over independence-based thresholding.arxiv | Mo Hai provider id |
2026-07-27 | 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.