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:
2458158913
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- María Óskarsdóttir (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Governance: 1 paper
- Human Ai Collab: 1 paper
Claim outcomes
- Ai Safety And Ethics: 1 paper
- Decision Quality: 1 paper
- Governance And Regulation: 1 paper
- Regulatory Compliance: 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 |
|---|---|---|---|
| How you present model evidence matters more than which LLM you use: in mortgage credit scoring, the evidence modality (tabular, network or both) explains far more variation in explanation fidelity than the choice of LLM; language models reliably name influential factors but frequently err on the direction of influence, and credit professionals judge outputs more harshly than lay readers.arxiv | María Óskarsdóttir provider id |
2026-08-18 | 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.