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
8Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2389916963
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Subhransu Das (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Adoption: 1 paper
- Productivity: 1 paper
Claim outcomes
- Output Quality: 1 paper
- Task Completion Time: 1 paper
- Decision Quality: 1 paper
- Organizational Efficiency: 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 |
|---|---|---|---|
| There is no one-size-fits-all compression for edge AI: quantization typically yields predictable size and latency wins, but structured pruning can both erode task performance and — by breaking format alignments — inflate deployed artifacts and increase latency. Edge deployments must pick compression techniques by task, model family and hardware, or risk surprising slowdowns and hidden accuracy failures.arxiv | Subhransu Das provider id |
2026-08-16 | 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.