repoGitHubTrust 82 · PrimaryPublished 9d agoLive · 20h ago

dp-web4/SAGE

A cognition kernel that wraps a frozen LLM in a persistent identity + trust + governance loop — testing whether capability comes from structure, not weights. Research-stage; honest about what's real vs mocked.

Lineage graph

Paper → model → repo connections mined from source citations (Tier-1 exact match).

Why these links exist

Every edge carries a method, confidence, and the source snippet that justified it — so bad links are debuggable.

PossiblePossibly related (embedding) · 49%Disaggregated prefill and decode for LLM inference on SageMaker HyperPod →
PossiblePossibly related (embedding) · 45%Evidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs →

Covers

newsDisaggregated prefill and decode for LLM inference on SageMaker HyperPod

Implements

paperEvidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs

Related across the graph

paperEvidence-Grounded Verified Agentic Reasoning: A Path Toward Eliminating LLM Hallucination in Empirical Inference via Tool-Attested Kernel Proofs newsDisaggregated prefill and decode for LLM inference on SageMaker HyperPod

Topics

agentic agents ai ai-governance autonomous cognitive-architecture edge-ai embodied-ai jetson llm