GroundCite

Live stats

Transparency on real usage. Derived metrics only - no question or answer text is stored or shown publicly. Updated live.

Questions
34
Grounded
68%
answered from sources
Cache hits
24%
served without a model call
Total cost
$0.083
OpenRouter, all-time
Avg latency
4.8s
uncached queries
Avg sources
3.2
per grounded answer

Questions per day

2026-06-09: 82026-06-10: 252026-06-12: 12026-06-092026-06-12

Most-cited papers

The arXiv papers GroundCite has grounded its answers in most often.

  1. 1
    Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token Selection
    arXiv:2602.03216 · cited in 3 answers
  2. 2
    Self-Improvement of Large Language Models: A Technical Overview and Future Outlook
    arXiv:2603.25681 · cited in 3 answers
  3. 3
    Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training Steps
    arXiv:2605.16928 · cited in 3 answers
  4. 4
    Latent-Condensed Transformer for Efficient Long Context Modeling
    arXiv:2604.12452 · cited in 3 answers
  5. 5
    Off-Distribution Voices: Fanfiction Subgenres as Universal Vernacular Jailbreaks for Aligned LLMs
    arXiv:2606.04483 · cited in 3 answers
  6. 6
    SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM Inference
    arXiv:2606.04511 · cited in 3 answers
  7. 7
    DeInfer: Efficient Parallel Inferencing for Decomposed Large Language Models
    arXiv:2604.17709 · cited in 2 answers
  8. 8
    Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model Serving
    arXiv:2606.02964 · cited in 2 answers
  9. 9
    Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative Analysis
    arXiv:2603.05698 · cited in 2 answers
  10. 10
    Faster LLM Inference via Sequential Monte Carlo
    arXiv:2604.15672 · cited in 2 answers