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 →
2Distinct papers
27Unique collaborators
2/2Semantic Scholar citation coverage
Publication span: 2026. Corpus fetch span: 2026.
Identity provenance
Provider IDs
- Semantic Scholar:
2375078291
ORCID evidence
No valid ORCID is stored.
Observed aliases (1)
- Jizhou Huang (semantic scholar, provider refresh)
Topics and outcomes in this view
Assessment themes
- Human Ai Collab: 2 papers
- Adoption: 1 paper
- Innovation: 1 paper
Claim outcomes
- Output Quality: 2 papers
- Task Allocation: 2 papers
- Other: 2 papers
- Adoption Rate: 1 paper
- Consumer Welfare: 1 paper
- Task Completion Time: 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 |
|---|---|---|---|
| Meta’s 'Shape Your Feed' uses LLM agents to let users steer their feeds in real time, substantially improving offline alignment (98.9% accuracy) and driving positive lifts in feed relevance and user sentiment in large-scale production A/B tests; however, the paper provides limited experimental detail on effect sizes, duration and robustness. arxiv | Jizhou Huang provider id |
2026-08-06 | 0 |
| A hybrid conversational engine at Baidu decouples instant replies from asynchronous tool-driven work, preserving conversational flow while integrating delayed results; in production this architecture reduced latency and—by observational metrics—tripled Day-7 retention and raised complex task completion to 65%.arxiv | Jizhou Huang provider id |
2026-02-25 | 2 |
Citation observation summary
Semantic Scholar supplied counts for 2 of 2 papers in this view; 0 are missing. The observed paper counts sum to 2 cumulative citations. This is a coverage summary, not an author score or h-index.