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
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2429421179
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Tommaso Cerruti (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Governance: 1 paper
- Human Ai Collab: 1 paper
- Org Design: 1 paper
Claim outcomes
- Ai Safety And Ethics: 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 |
|---|---|---|---|
| LLM agent memories can invent authority and induce unauthorized actions: a benchmark shows typed incremental memories create false permissions in up to ~50% of cases and executors act on them in ~99% of trials, while oracle memory repair prevents all such violations.arxiv | Tommaso Cerruti provider id |
2026-09-01 | 0 |
Citation observation summary
Semantic Scholar supplied counts for 1 of 1 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.