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 →
2Distinct papers
12Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2273551430
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Maosong Sun (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 2 papers
- Inequality: 1 paper
- Innovation: 1 paper
Claim outcomes
- Output Quality: 2 papers
- Task Allocation: 1 paper
- Inequality: 1 paper
- Organizational Efficiency: 1 paper
- Other: 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 |
|---|---|---|---|
| LLM agents can run and debug training pipelines effectively but rarely change their initial training strategy, so extra experience, human guidance or more compute mainly yields local fixes rather than strategic improvements.arxiv | Maosong Sun provider id |
2026-08-19 | 0 |
| Large language models favour wealthier, tech-advanced countries when simulating public values, producing systematic cross-country representational inequality; common fixes such as native-language prompting, post-training and alignment often raise average accuracy but fail to produce consistent gains in equality.arxiv | Maosong Sun provider id |
2026-08-08 | 0 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 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.