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
2Unique collaborators
0/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2186407570
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Jookyung Song (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 1 paper
- Productivity: 1 paper
- Skills Training: 1 paper
Claim outcomes
- Organizational Efficiency: 1 paper
- Ai Safety And Ethics: 1 paper
- Task Completion Time: 1 paper
- Decision Quality: 1 paper
- Error Rate: 1 paper
- Skill Acquisition: 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 document-oriented agent runtime (String) lets language-model agents use apps as Markdown, matching curated-skill success on an 87-task benchmark while cutting tokens by about one-third; staged, partial disclosure improves action-selection accuracy and reduces wrong actions from ~28% to ~2%. arxiv | Jookyung Song provider id |
2026-08-28 | Missing, not zero |
Citation observation summary
Semantic Scholar supplied counts for 0 of 1 papers in this view; 1 are missing.