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
0Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2025. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2257431380
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Zhongjie Jiang (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 1 paper
- Innovation: 1 paper
Claim outcomes
- Ai Safety And Ethics: 1 paper
- Output Quality: 1 paper
- Firm Revenue: 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 |
|---|---|---|---|
| Generative models that simulate human cognitive states preserve the irregularities standard synthetic data erases and produce more human-like text; in the authors' experiments this approach halved distributional divergence and, in a Chinese A‑share backtest, cut maximum drawdown by 47% during the 2015 crash while producing 8.6% defensive alpha.arxiv | Zhongjie Jiang provider id |
2025-12-01 | 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.