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
3Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2025. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2395678563
ORCID evidence
No valid ORCID is stored.
Observed aliases (2)
- S. Chew (semantic scholar, provider refresh)
- Shila Chew (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Adoption: 1 paper
- Org Design: 1 paper
- Productivity: 1 paper
Claim outcomes
- Organizational Efficiency: 1 paper
- Output Quality: 1 paper
- Adoption Rate: 1 paper
- Research Productivity: 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 |
|---|---|---|---|
| Smaller LLMs can outcompete flagship models for software-test review: GPT-4o Mini achieved the best accuracy (6.07 MAAE), high first-attempt reliability (96.6% ECR@1) and a low operating cost ($1.01 per 1K), yielding roughly a 78x cost reduction versus a high-reasoning GPT-5 configuration; overall costs ranged from $0.45 to $78.96 per 1K depending on model and reasoning strategy.arxiv | Shila Chew 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.