100 active frozen predictions, ranked by signal-fusion score. Outcome windows are still open, so these rows are awaiting outcome evidence rather than true/false resolution.
| # | Paper · arxiv id | Domain | Signal Fusion | Predicted | Frozen | Lineage | Outcome |
|---|---|---|---|---|---|---|---|
| 100 | 98$\times$ Faster LLM Routing Without a Dedicated GPU: Flash Attention, Prompt Compression, and Near-Streaming for the vLLM Semantic Router 2603.12646v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 83 | MDER-DR: Multi-Hop Question Answering with Entity-Centric Summaries 2603.11223v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 79 | Shepherd: A Runtime Substrate Empowering Meta-Agents with a Formalized Execution Trace 2605.10913v1 | cs.CL | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 78 | Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation 2604.05150v1 | cs.CL | 95.0 | 2026-04-20 | 2026-04-20 | unverifiable | P |
| 77 | Compiled AI: Deterministic Code Generation for LLM-Based Workflow Automation 2604.05150v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 65 | Action-Aware Generative Sequence Modeling for Short Video Recommendation 2604.25834v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 59 | Training-Free Test-Time Contrastive Learning for Large Language Models 2604.13552v1 | cs.CL | 95.0 | 2026-04-20 | 2026-04-20 | unverifiable | P |
| 58 | Training-Free Test-Time Contrastive Learning for Large Language Models 2604.13552v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 51 | A Swap-Adversarial Framework for Improving Domain Generalization in Electroencephalography-Based Parkinson's Disease Prediction 2602.10528v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 50 | SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills 2604.06550v1 | cs.CL | 95.0 | 2026-04-20 | 2026-04-20 | unverifiable | P |
| 49 | SkillSieve: A Hierarchical Triage Framework for Detecting Malicious AI Agent Skills 2604.06550v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 38 | Graph Neural Operator Towards Edge Deployability and Portability for Sparse-to-Dense, Real-Time Virtual Sensing on Irregular Grids 2604.01802v1 | cs.CL | 95.0 | 2026-04-20 | 2026-04-20 | unverifiable | P |
| 37 | Graph Neural Operator Towards Edge Deployability and Portability for Sparse-to-Dense, Real-Time Virtual Sensing on Irregular Grids 2604.01802v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 31 | FAME: Force-Adaptive RL for Expanding the Manipulation Envelope of a Full-Scale Humanoid 2603.08961v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 30 | Contextualizing Sink Knowledge for Java Vulnerability Discovery 2604.01645v1 | cs.CL | 95.0 | 2026-05-31 | 2026-05-31 | unverifiable | P |
| 25 | Toward Complex-Valued Neural Networks for Waveform Generation 2603.11589v1 | cs.CL | 95.0 | 2026-04-20 | 2026-04-20 | unverifiable | P |
| 23 | Toward Complex-Valued Neural Networks for Waveform Generation 2603.11589v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |
| 3 | Woosh: A Sound Effects Foundation Model 2604.01929v1 | cs.CL | 95.0 | 2026-05-24 | 2026-05-24 | unverifiable | P |