161 MB
11 files
Updated 1 day ago
README.md

Unicosys Hypergraph Knowledge Model

A trainable knowledge graph embedding model encoding the unified evidence hypergraph for Case 2025-137857.

Model Description

This model encodes a unified hypergraph linking financial transactions, email communications, legal evidence, and entity relationships into a single trainable knowledge representation.

Architecture

Component Details
Node Embedding 128-dim structural + 256-dim text
Hidden Dimension 256
Text Encoder 2-layer Transformer, 4 heads
Graph Attention 2-layer GAT, 4 heads
Link Predictor 2-layer MLP with margin ranking loss
Total Parameters 36,023,937

Knowledge Graph Statistics

Metric Count
Total Nodes 300,843
Total Edges 14,439
Cross-Links 3,628
Entities 16
Emails 199,217
Financial Documents 12,103
Timeline Events 59,955
LEX Schemes 13
Legal Filings 5

Subsystems

Subsystem Nodes
Core (Entities) 16
Fincosys (Financial) 101,429
Comcosys (Communications) 199,217
RevStream1 (Evidence) 150
Ad-Res-J7 (Legal) 31

Training

The model can be fine-tuned on link prediction tasks:

from model.unicosys_model import UnicosysHypergraphModel, UnicosysConfig

model = UnicosysHypergraphModel.from_pretrained("hyperholmes/unicosys-hypergraph")
# ... prepare training data ...
# model.forward(node_ids, node_type_ids, subsystem_ids, edge_index, edge_type_ids,
#               pos_edge_index=pos, neg_edge_index=neg, labels=labels)

Files

  • model.safetensors — Model weights
  • config.json — Model configuration
  • graph_data.safetensors — Encoded graph tensors (nodes, edges)
  • tokenizer.json — Character-level tokenizer for node labels
  • node_id_mapping.json — Node ID string to integer index mapping
  • model_summary.json — Compact statistics summary

Source

Generated by the Unicosys intelligence pipeline.

Total size
161 MB
Files
11
Last updated
May 24
Pre-warmed CDN
US EU US EU

Contributors