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
4Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
48570960
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Lining Zhang (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Adoption: 1 paper
- Skills Training: 1 paper
Claim outcomes
- Output Quality: 1 paper
- Adoption Rate: 1 paper
- Other: 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 cheap Shadow-RAG tutor unlocks latent capability in modern 32B models: on a graduate Applied Mathematics final, structured reasoning guidance lifts accuracy from 74% with naive retrieval to 90%, achieved with just 3 person‑days and a single consumer GPU, while older model generations improve far less.arxiv | Lining Zhang provider id |
2026-03-21 | 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.