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
4Unique collaborators
0/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2299103433
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Jingyu Zhang (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 1 paper
- Productivity: 1 paper
Claim outcomes
- Decision Quality: 1 paper
- Error Rate: 1 paper
- Organizational Efficiency: 1 paper
- Other: 1 paper
- Task Allocation: 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 cost-aware router halves expensive LLM reasoning spend while preserving accuracy: deployed on a production image-annotation workflow, DRR matches the top confidence-based system’s accuracy (≈82.8%) while cutting incremental reasoning-token use by about two-thirds and routing roughly 21–22% of items to human review.arxiv | Jingyu Zhang provider id |
2026-08-31 | Missing, not zero |
Citation observation summary
Semantic Scholar supplied counts for 0 of 1 papers in this view; 1 are missing.