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
0/1Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2313914951
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Pablo Ortega-Kral (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Adoption: 1 paper
- Human Ai Collab: 1 paper
Claim outcomes
- Output Quality: 1 paper
- Error Rate: 1 paper
- 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 |
|---|---|---|---|
| A few words fix many robot misses: CorrectVLA maps one task-level language correction into small per-timestep action biases that recover miscalibrated VLA executions in simulation and restore 95% success on a shifted real-robot pick-and-place task — all without retraining.arxiv | Pablo Ortega-Kral provider id |
2026-08-30 | Missing, not zero |
Citation observation summary
Semantic Scholar supplied counts for 0 of 1 papers in this view; 1 are missing.