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
17Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2269731718
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Chanyeol Choi (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Governance: 2 papers
- Human Ai Collab: 1 paper
- Org Design: 1 paper
Claim outcomes
- Decision Quality: 2 papers
- Ai Safety And Ethics: 1 paper
- Consumer Welfare: 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 |
|---|---|---|---|
| Simple, black-box manipulations of inputs and prompts can reliably hijack multi-agent LLM trading systems' decisions; compromising the terminal risk-management role nearly guarantees control of final actions across tested architectures.arxiv | Chanyeol Choi provider id |
2026-08-25 | 0 |
| A single 'neuron dial' can tune an LLM’s buy–sell bias: researchers show that adding a scalar shift to one MLP coordinate produces monotonic, calibratable shifts in investment stance across five open models—changing decisions, reasoning emphasis and even portfolio composition—without significant degradation on standard benchmarks.arxiv | Chanyeol Choi provider id |
2026-08-24 | 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.