You can deploy this model and start earning money today!

RthItalia/
shadow-x-v14-ccs

Name: shadow-x-v14-ccs
Availability: InStock

Views

No views yet

Shadow-X v14 CCS

Deterministic Cognitive Control System (CCS-v2) for Shadow-X.

This repository contains the v14 executive controller layer that upgrades Shadow-X from:

topological associative memory + basic deterministic flow, to:
full deterministic cognitive control with hierarchical goals, attention routing, conflict inhibition, self-monitoring, task prospection, and third-order deterministic rule updates.

No probabilities, no gradients, no softmax.

DOI

10.6084/m9.figshare.31384594
Link: https://doi.org/10.6084/m9.figshare.31384594

Public Showcase Pack

This repository includes a public showcase layer designed to prove creation, architecture, deterministic behavior, and enterprise relevance without exposing full proprietary know-how.

Showcase overview: SHOWCASE_PUBLIC.md
Benchmark evidence: BENCHMARK_REPORT.md
Commercial access path: COMMERCIAL_ACCESS.md
Citation metadata: CITATION.cff
Outreach templates: OUTREACH_TEMPLATES.md
Publish steps: PUBLISH_CHECKLIST.md

Core Architecture

mermaid

graph TD
    A[Input Pulse] --> B[Phantom Kernel]
    B --> C[Episodic Memory Slabs and Z-Hypergrid]

    D[Deterministic Cognitive Controller CCS-v2] -->|Goal Maintenance| B
    D -->|Attention Allocation| C
    D -->|Conflict Inhibition| B
    D -->|Error Monitor and Correction| B
    D -->|Task Switching and Prospection| C
    D -->|Meta Rule Update| E[Third-Order Rule Modifier]

    F[goal_vector.dat Hierarchical Goal Stack] --> D
    D --> G[trace_log.jsonl Full Audit Trail]

Deterministic Control Loop

mermaid

flowchart LR
    G1[Load Active Goal] --> A1[Allocate Active Zones]
    A1 --> C1[Query Candidate Bindings]
    C1 --> I1[Resolve Conflicts]
    I1 --> P1[Prospection 2-3 Futures]
    P1 --> E1[Error Monitor vs Goal]
    E1 -->|Deviation High| R1[Deterministic Rebind]
    E1 -->|Deviation Low| O1[Materialize Output]
    R1 --> O1
    O1 --> T1[Append Trace Log]
    T1 --> M1[Third-Order Rule Update]

Modules

Goal Vector + Hierarchical Goal Stack
Persistent goals in goal_vector.dat, parent-child relations, deterministic selection.
Deterministic Attention Allocator
Goal-projected geometric routing to activate relevant slabs/zones only.
Conflict Resolver (Inhibition)
Suppression of contradictory candidates via fixed opposition threshold.
Error Monitor + Self-Correction
Output/goal deviation check with deterministic rebind and constraint strengthening.
Task Switcher + Prospection
Deterministic branch simulation (2-3 futures) and best-branch selection.
Third-Order Rule Modifier
Deterministic threshold adaptation from recurrent error windows.

Repository Content

shadow_x_v14_ccs/cognitive_controller.py: CCS-v2 implementation.
shadow_x_v14_ccs/phantom_bridge.py: bridge from CCS-v2 to phantom_kernel.py.
shadow_x_v14_ccs/demo_cli.py: one-shot + goal query + trace + self-correction demo.
shadow_x_v14_ccs/ARCHITECTURE.md: architecture notes.
shadow_x_v14_ccs/README.md: package-focused documentation.
tests/test_shadow_x_v14_ccs.py: controller unit/integration tests.
tests/test_shadow_x_v14_phantom_bridge.py: bridge tests + real-dataset smoke.
tests/test_shadow_x_v14_demo_cli.py: public demo flow tests.
tests/test_enterprise_aml_use_case.py: AML enterprise case tests.
tests/test_enterprise_real_use_cases.py: insurance + trade enterprise case tests.
tests/test_enterprise_next_use_cases.py: KYC + procurement + pharma enterprise case tests.

Quickstart

python

from shadow_x_v14_ccs import create_v14_controller_with_phantom_kernel

controller = create_v14_controller_with_phantom_kernel(
    model_path="v11_Morpho_Optimized",
    state_dir="shadow_x_v14_ccs/state",
    max_zone_candidates=128,
    max_candidates_per_zone=16,
)

Public Demo

Hugging Face Space: https://huggingface.co/spaces/RthItalia/shadow-x-v14-mini-demo
GitHub Gist: https://gist.github.com/rthgit/6ec122cce85c6aebba46a53df0877027

Benchmark Snapshot

Validated benchmark summary for all implemented enterprise use-cases:

BENCHMARK_REPORT.md

Enterprise Use Cases (Implemented)

AML + Contractual Compliance

script: use_cases/enterprise_aml_contractual_compliance.py
output: deterministic verdict + trace chain (slab_id, vertex_id, resonance)
proof: dual-controller replay with identical selections and error signals
scale-out probe: v15 cluster metrics (throughput, p95, p99)

Insurance Claims Fraud Triage

script: use_cases/insurance_claims_fraud_triage.py
output: deterministic fraud verdict + trace chain (slab_id, vertex_id, resonance)
proof: dual-controller replay with identical selections and error signals
scale-out probe: v15 cluster metrics (throughput, p95, p99)

Trade Surveillance (Market Abuse)

script: use_cases/trade_surveillance_market_abuse.py
output: deterministic surveillance verdict + trace chain (slab_id, vertex_id, resonance)
proof: dual-controller replay with identical selections and error signals
scale-out probe: v15 cluster metrics (throughput, p95, p99)

KYC Periodic Review + Beneficial Ownership

script: use_cases/kyc_periodic_review_beneficial_ownership.py
output: deterministic KYC verdict + trace chain (slab_id, vertex_id, resonance)
proof: dual-controller replay with identical selections and error signals
scale-out probe: v15 cluster metrics (throughput, p95, p99)

Procurement Contract Risk Gate

script: use_cases/procurement_contract_risk_gate.py
output: deterministic legal/security clause verdict + trace chain (slab_id, vertex_id, resonance)
proof: dual-controller replay with identical selections and error signals
scale-out probe: v15 cluster metrics (throughput, p95, p99)

Pharma GxP / SOP Compliance

script: use_cases/pharma_gxp_sop_compliance.py
output: deterministic batch compliance verdict + trace chain (slab_id, vertex_id, resonance)
proof: dual-controller replay with identical selections and error signals
scale-out probe: v15 cluster metrics (throughput, p95, p99)

Backlog of next prioritized use cases:

use_cases/USE_CASES_BACKLOG.md

Notes on Large Out-of-Core Assets

The local Shadow-X memory assets include very large slab files. In this v14 CCS repository, the focus is on the deterministic control layer and bridge logic. Large slab binaries can be versioned separately when needed.

Memory-assets dataset (large slabs):

https://huggingface.co/datasets/RthItalia/shadow-x-memory-assets

License

This repository is distributed under Shadow-X Non-Commercial License v1.0.

Free for personal, educational, research, and study use.
Commercial usage is not allowed without written permission.
For commercial licensing: info@rthitalia.com

Full terms: LICENSE.md

Commercial process details: COMMERCIAL_ACCESS.md

RthItalia/shadow-x-v14-ccs