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:
2286321592
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Sarit Kraus (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 2 papers
- Adoption: 1 paper
- Productivity: 1 paper
Claim outcomes
- Decision Quality: 2 papers
- Organizational Efficiency: 2 papers
- Error Rate: 2 papers
- Other: 2 papers
- Adoption Rate: 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 |
|---|---|---|---|
| An automated LLM pre-mediator performs comparably to professional mediators on short-term preparation measures while inferring party preferences more accurately — cutting preference-inference error by 36%; prompt tuning also reduces excessive affirmation to match human mediator baselines.arxiv | Sarit Kraus provider id |
2026-06-09 | 0 |
| Polished explanations from LLMs increase confidence but can mislead: in visual reasoning they suppress users' ability to catch model errors, whereas in logical reasoning they improve performance; exposing uncertainty and deferring unclear cases to humans yields better error recovery in many settings.arxiv | Sarit Kraus provider id |
2026-01-31 | 0 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 papers in this view; 0 are missing. The observed paper counts sum to 0 cumulative citations. This is a coverage summary, not an author score or h-index.