OODA-expanded pipeline: 105 rules across 15 namespaces with closed-loop Observe-Orient-Decide-Act-Assess engagement cycles and BDA feedback. Includes the full doctrine chain plus bda_assessment and loop_control namespaces.
Select a mission profile to apply objective rules that shape engagement scoring without modifying constraint rules.
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.
Run the OODA loop to see engagement decisions with BDA-informed re-evaluation.
Features flow through 15 rule namespaces arranged in 5 layers. Includes bda_assessment and loop_control namespaces for closed-loop OODA.
Select a target to see the OODA BFS trace.
Select a target to compare DAG-composed vs flat scores.
ErgoAI re-derives the engagement decision independently in Flora-2 using
final_decision/2 over the rule firings, and uses
dominant_blocking_namespace/2 with \overrides/2 to identify
which precedence-class blocker dominates when multiple namespaces fire.
Python composes the same firings as a cross-check; any divergence is reported.
Runs contradictory_same_namespace/3, mutually_exclusive_pair/4,
and redundant_pair/3 queries against the rule meta-data.
Queries \overrides/2 against the 4101 facts in precedence.ergo
to confirm objective namespaces cannot override constraint namespaces.
Asserts the target's features into ErgoAI and queries final_decision/2,
final_score/2, final_cap/2, and
dominant_blocking_namespace/2. The result is checked against the OODA pipeline's decision.
A canonical proof certificate produced by flora2_final_decision/2 on a
representative engage target.
Pipeline audit trail showing which doctrine checks each decision traversed. Not an independent proof -- see ErgoAI above for formal verification.
All doctrine rules (90+ from published sources) plus OODA-specific rules in bda_assessment and loop_control namespaces. OODA rules are highlighted with purple accents.
Higher-precedence rules cannot be overridden by lower levels. User rules (Level 6) can only ADD restrictions.
Select a mission profile to view its objective rules. Objective rules apply soft boosts/penalties and do not override constraint rules.
No user rules applied. System doctrine rules are active.
Apply a rule change to see which targets change decisions.
Loading rules...
Click "Load Evaluation Results" to view OODA multi-cycle evaluation across 40 scenarios.
Compare pipeline results across mission profiles. Constraint rules remain invariant; only objective scoring changes.
Click "Load Profile Comparison" to compare mission profiles.
Calibrated objective parameters vs hand-set values. Constraint rules are never modified by calibration.
Click "Load Calibration Results" to view parameter calibration.
CNN vs LR through identical 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.
How AR doctrine rules shape CNN training and inference within the OODA loop.
Doctrine rules define which misclassifications matter. BDA feedback from prior cycles adjusts cost weights.
Doctrine context adjusts confidence requirements. Re-observed targets may get adjusted thresholds.
Engagement outcomes feed back into the next OODA cycle. Relocated targets trigger re-observation and re-classification.
Misclassification costs derived from engagement rules. Higher cost = CNN pays more attention to avoiding this confusion.
Each target's required confidence level, computed from doctrine context.
Targets where AR overrode CNN's confident prediction -- active learning candidates.
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.
Cycle-by-cycle breakdown of the closed-loop OODA engagement process. Each cycle includes observe, orient, decide, act, and assess phases with BDA feedback.
Run the OODA loop first to see cycle-by-cycle timeline.
Estimated Surviving Target Value (ESTV) plotted across OODA cycles. Shows how iterative engagement with BDA feedback reduces residual threat.
Run the OODA loop first to see ESTV curve.
No data yet.
No data yet.
Tactical map with targets colored by BDA status. Use the cycle slider to step through engagement outcomes.
Run the OODA loop to see BDA status.
No data yet.
Per-cycle evaluation of loop control rules (L1-L7) that determine whether to CONTINUE, TERMINATE, or RE-OBSERVE. The rule that determined the final decision is highlighted.
Run the OODA loop first to see loop control rule trace.