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
5Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2391561860
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Xiang Li (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Adoption: 1 paper
- Human Ai Collab: 1 paper
- Productivity: 1 paper
- Skills Training: 1 paper
Claim outcomes
- Other: 1 paper
- Output Quality: 1 paper
- Adoption Rate: 1 paper
- Developer Productivity: 1 paper
- Research Productivity: 1 paper
- Worker Satisfaction: 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 large study of 6,000 live coding-agent sessions finds agents either write almost all or none of committed code — 41% 'vibe coding' versus 23% human-only — yet only 44% of agent-produced code survives into commits and agent contributions carry more security flaws, with users pushing back in 44% of interactions.arxiv | Xiang Li provider id |
2026-04-22 | 15 |
Citation observation summary
Semantic Scholar supplied counts for 1 of 1 papers in this view; 0 are missing. The observed paper counts sum to 15 cumulative citations. This is a coverage summary, not an author score or h-index.