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
2Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2303617802
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Jiyuan Tan (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 2 papers
- Innovation: 1 paper
- Productivity: 1 paper
Claim outcomes
- Research Productivity: 2 papers
- Decision Quality: 2 papers
- Other: 1 paper
- Adoption 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 system can autonomously generate and machine-verify causal-inference theorems, but formal correctness alone is insufficient — an audit step is required to ensure the formal statements reflect the intended scientific claims.arxiv | Jiyuan Tan provider id |
2026-07-24 | 0 |
| Large language models can pick the right causal strategy most of the time but fail on the fine print: they identify the high-level design in 79% of cases but correctly specify all design details only one-third of the time, making nuanced research design the bottleneck for automated causal inference.arxiv | Jiyuan Tan provider id |
2026-02-24 | 1 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 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.