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
Most-cited papers
The arXiv papers GroundCite has grounded its answers in most often.
- 1Token Sparse Attention: Efficient Long-Context Inference with Interleaved Token SelectionarXiv:2602.03216 · cited in 3 answers
- 2Self-Improvement of Large Language Models: A Technical Overview and Future OutlookarXiv:2603.25681 · cited in 3 answers
- 3Full Attention Strikes Back: Transferring Full Attention into Sparse within Hundred Training StepsarXiv:2605.16928 · cited in 3 answers
- 4Latent-Condensed Transformer for Efficient Long Context ModelingarXiv:2604.12452 · cited in 3 answers
- 5Off-Distribution Voices: Fanfiction Subgenres as Universal Vernacular Jailbreaks for Aligned LLMsarXiv:2606.04483 · cited in 3 answers
- 6SparDA: Sparse Decoupled Attention for Efficient Long-Context LLM InferencearXiv:2606.04511 · cited in 3 answers
- 7DeInfer: Efficient Parallel Inferencing for Decomposed Large Language ModelsarXiv:2604.17709 · cited in 2 answers
- 8Multi-Segment Attention: Enabling Efficient KV-Cache Management for Faster Large Language Model ServingarXiv:2606.02964 · cited in 2 answers
- 9Towards Robust Retrieval-Augmented Generation Based on Knowledge Graph: A Comparative AnalysisarXiv:2603.05698 · cited in 2 answers
- 10Faster LLM Inference via Sequential Monte CarloarXiv:2604.15672 · cited in 2 answers