Kill Web Doctrine

12-Namespace DAG -- NSL, CDE, LOAC, Authorization

Select Doctrine Scenario

Doctrine-expanded pipeline: 90 rules across 13 namespaces with 47 inter-namespace edges forming a 10-hop DAG. Includes No-Strike List (NSL), Collateral Damage Estimation (CDE Levels 1-5), Law of Armed Conflict (LOAC), and engagement authorization chain.

Tactical Situation

Tactical Map

● Armor ▲ Air Defense ■ Soft Target ◆ Civilian ★ Platform ☆ Protected Asset
NSL entities: + Medical ☪ Religious ☐ Educational ☖ Civilian

ROE Status

NSL Entities (0)

Targets (0)

Platforms (0)

Doctrine Engagement Pipeline

Mission Profile OBJECTIVE

Select a mission profile to apply objective rules that shape engagement scoring without modifying constraint rules.

ML Model CLASSIFIER

Composite (recommended) -- runs both CNN and LR, composes predictions through AR-governed fusion. Agreement boosts confidence; disagreement triggers more conservative decisions. Same zero-violation guarantee.

Doctrine-Aware Decisions

Run the pipeline to see engagement decisions with doctrine checks.

Doctrine Statistics

Run pipeline to see namespace activation, authorization levels, and doctrine flags.

Triage Priority Ranking

ENGAGE targets ordered by priority_score. Objective AR rules shift priority without changing engage/hold/escalate decisions.

Run pipeline to see priority ranking of ENGAGE targets.

Baseline Comparison

Run pipeline to compare Doctrine DAG vs flat baselines.

12-Namespace DAG Inspector

DAG Topology

Features flow through 12 rule namespaces arranged in 4 layers. Select a target to trace its 8-10 hop BFS path through the full doctrine chain.

Features (40-D)

Target Assessment

Weapons Pairing

ROE Compliance

Tactical Priority

No-Strike List

Collateral Objects

CDE L1

CDE L2

CDE L3

CDE L4

CDE L5

Eng. Authority

LOAC

BFS Trace

Select a target to see the doctrine BFS trace.

DAG vs Flat Comparison

Select a target to compare DAG-composed vs flat scores.

Verification & Decision Trace

ErgoAI Formal Verification (Flora-2 / XSB)

Independent formal verification using ErgoAI logic engine. Rules are checked for consistency, constraint invariance, and non-interference. Per-target decisions are independently re-derived via final_decision/2 and compared with the pipeline's output.

Rule Consistency

Click "Check Consistency" to verify all doctrine rules are non-contradictory.

Constraint Invariance & Non-Interference

Click "Verify Invariance" to prove no objective rule can weaken a constraint rule.

Per-Target Formal Proof

Select a target from the pipeline results and click "Verify Target" for formal verification.

Sample Proof Certificate

Pre-computed BTR-60 open-terrain engagement proof. Works without running the pipeline.

Trace Decision Trace

Pipeline audit trail showing which doctrine checks each decision traversed. Not an independent proof -- see ErgoAI above for formal verification.

Rules

System doctrine rules are loaded from published sources and are write-protected (SHA-256 verified). User rules are added at runtime and take effect on next pipeline run without retraining.

Doctrine Rule Precedence Hierarchy

Higher-precedence rules cannot be overridden by lower levels. User rules (Level 6) can only ADD restrictions.

Level 1: LOAC (immutable -- international law, non-derogable)
Level 2: NSL (overridable: dual-use + commander auth only)
Level 3: ROE (commander adjustable within LOAC bounds)
Level 4: CDE (procedural, thresholds adjustable)
Level 5: Tac (fully adjustable by commander)
Level 6: User (additive only -- cannot weaken above)

SYSTEM Doctrine Rules (90 rules, 13 namespaces, write-protected)

Loading doctrine rules...

OBJECTIVE Mission Objective Rules (select a profile)

Select a mission profile to view its objective rules. Objective rules apply soft boosts/penalties and do not override constraint rules.

USER Add Rule Override

Active User Rules

No user rules applied. System doctrine rules are active.

Impact Preview

Apply a rule change to see which targets change decisions.

Doctrine Evaluation Summary

Ablation: DAG vs Flat

Click "Load Evaluation Results" to view doctrine DAG vs flat ablation results.

Edge Activation Frequency

Flag Agreement (DAG vs Flat)

Per-Scenario Results

Mission Profile Comparison OBJECTIVE

Compare pipeline results across mission profiles. Constraint rules remain invariant; only objective scoring changes.

Click "Load Profile Comparison" to compare mission profiles.

Objective Parameter Calibration OBJECTIVE learnable

Calibrated objective parameters vs hand-set values. Constraint rules are never modified by calibration.

Click "Load Calibration Results" to view parameter calibration.

ML Model Comparison CLASSIFIER

CNN vs LR through identical 94-rule doctrine DAG across 40 scenarios. Demonstrates ML-agnostic composition: safety invariants hold regardless of classifier quality.

Click "Load ML Comparison" to compare CNN vs LR pipeline results.

AR-ML Integration

How AR doctrine rules shape CNN training and inference.

1. AR Cost-Weighted Training

Doctrine rules define which misclassifications matter. T-72→ambulance costs 10x more than T-72→BMP-2.

2. AR Adaptive Thresholds

Doctrine context adjusts confidence requirements. Targets near hospitals need 0.95, not 0.85.

3. AR Hard Example Feedback

AR blocking decisions identify what the CNN should learn better for next training epoch.

Doctrine Cost Matrix

Misclassification costs derived from engagement rules. Higher cost = CNN pays more attention to avoiding this confusion.

Adaptive Confidence Thresholds

Each target's required confidence level, computed from doctrine context.

Hard Examples for Retraining

Targets where AR overrode CNN's confident prediction -- active learning candidates.

Training Comparison: Standard vs AR-Weighted

AR-Governed Training Profiles OBJECTIVE

Training results per mission profile. The cost matrix is derived from AR doctrine rules, not hand-coded. Constraint violations must remain at zero across all profiles.

Click "Load Training Profiles" to view AR-governed training results.