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
6Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2438737477
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Samuel Verboomen (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 1 paper
- Productivity: 1 paper
Claim outcomes
- Other: 1 paper
- Task Completion Time: 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 self-improving loop that lets a language-model agent rewrite its scaffold and fine-tune weights substantially outperforms prior siloed approaches across three technical domains, cutting GPU kernel runtimes by ~92% and delivering major gains in legal classification and RNA denoising; combining harness changes (to make the agent more agentic) with weight updates (to build domain intuition) yields much larger improvements than changing either alone.arxiv | Samuel Verboomen provider id |
2026-05-26 | 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.