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
3Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2385502697
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Xuan Tang (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Innovation: 1 paper
- Productivity: 1 paper
Claim outcomes
- 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 |
|---|---|---|---|
| Low-precision training always reduces effective data size, but only signal-independent (additive) quantization shrinks effective model capacity; signal-dependent (multiplicative) quantization preserves model scale while adding error, informing cost–quality trade-offs when choosing precision, model size and dataset size.arxiv | Xuan Tang provider id |
2026-02-22 | 2 |
Citation observation summary
Semantic Scholar supplied counts for 1 of 1 papers in this view; 0 are missing. The observed paper counts sum to 2 cumulative citations. This is a coverage summary, not an author score or h-index.