Advantage Scale Calibration Imbalance in Group-Relative Optimization under Low-Variance Rewards: Diagnosis and Bounded Recovery
arXiv 2609.19164v1•c0dc6727307354a2668ccbbb46be614201c340fa89e121b8f4c747a6d48540f7
Paper metadata
- arXiv ID
- 2609.19164
- Version
- v1
- Category
- cs.CL, cs.LG
- Authors
- Fei Ding
- Publication date
- 2026-09-18T04:00:00Z
- Source identifier
- 2609.19164v1
- Public record ID
- record:sha256:c0dc6727307354a2668ccbbb46be614201c340fa89e121b8f4c747a6d48540f7
The PDF link points to arxiv.org. Baitaphish does not expose a private stored PDF.
This is source-provided metadata, not an enriched summary or an impact assessment. Follow the canonical source link for the published material.
Evidence and limitations
- Source ID
- arxiv_research
- Record identifier
- c0dc6727307354a2668ccbbb46be614201c340fa89e121b8f4c747a6d48540f7
- Record type
- Source metadata
This record may overlap with other records. Source metadata can be incomplete or change. Validate consequential decisions against the linked source and your own environment.