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
5Unique collaborators
1/1Semantic Scholar citation coverage
Publication span: 2025. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2083451204
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Fateme Hashemi Chaleshtori (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Adoption: 1 paper
- Human Ai Collab: 1 paper
- Productivity: 1 paper
- Skills Training: 1 paper
Claim outcomes
- Decision Quality: 1 paper
- Error Rate: 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 |
|---|---|---|---|
| Predictable LLM blindspots can be taught — but only if you can find them. The study shows identifiable failure-pattern groups that help users anticipate model mistakes, yet embedding- and prompt-based discovery methods detect them unevenly, and a new anticipation metric reveals teaching benefits missed by traditional team-accuracy measures.arxiv | Fateme Hashemi Chaleshtori provider id |
2025-12-24 | 1 |
Citation observation summary
Semantic Scholar supplied counts for 1 of 1 papers in this view; 0 are missing. The observed paper counts sum to 1 cumulative citations. This is a coverage summary, not an author score or h-index.