"Publication bias and the canonization of false facts" published in eLife (2016)
Graph-Tabular Fusion for Bitcoin Fraud Detection - Demonstrating when Node2Vec embeddings don't improve XGBoost. Scientifically rigorous negative result validating that tabular features encode graph structure.
Reproducible evaluation harness for hidden coordination variables in multi-agent LLM systems.
🔗 Explore Graph-Tabular Fusion to enhance Bitcoin fraud detection, revealing that rich tabular features render graph embeddings redundant.
Content-aware adaptive sampling for Stable Diffusion - dynamically optimizing inference steps based on prompt complexity for 30-50% speedup with <5% quality loss.
Neuro-symbolic AI that beats end-to-end baselines on structured manipulation (Towers of Hanoi, 8-puzzle). 100% success validated with Wilson 95% CIs. MIT license.
Why your multi-agent LLM deception experiment might be measuring prompt comprehension. An honest post-mortem.
A cost-sensitive Human-in-the-Loop framework for AML transaction monitoring — empirically demonstrating when human review increases operational cost under asymmetric error regimes.
Add a description, image, and links to the negative-results topic page so that developers can more easily learn about it.
To associate your repository with the negative-results topic, visit your repo's landing page and select "manage topics."