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
4Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2337795179
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Graham Neubig (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 2 papers
- Productivity: 2 papers
- Adoption: 1 paper
Claim outcomes
- Research Productivity: 1 paper
- Developer Productivity: 1 paper
- Output Quality: 1 paper
- Task Allocation: 1 paper
- Organizational Efficiency: 1 paper
- Other: 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 clarification module trained on Shapley-derived relevance and simulated answerability matches GPT-5’s issue-resolution success while cutting clarification questions by 41%, suggesting more efficient human–AI collaboration in software engineering; however, results rely on simulated users and a narrow task set, tempering claims about real-world gains.arxiv | Graham Neubig provider id |
2026-04-16 | 2 |
| A new pipeline turns real software into 10,000+ long-horizon agent environments tied to U.S. occupations, creating CUA-World for evaluating computer-use assistants; distilled 2B vision-language models and reviewer-audit loops yield measurable but modest performance gains on these economically relevant tasks.arxiv | Graham Neubig provider id |
2026-04-07 | 11 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 papers in this view; 0 are missing. The observed paper counts sum to 13 cumulative citations. This is a coverage summary, not an author score or h-index.