Research & Novel Work

Working code behind publishable claims.

WHL's research arm produces deterministic algorithms, formal verification, and publication-ready findings — each paired with code that runs and tests that pass. We publish numbers because the substrate has to be checkable.

4
Papers Ready for Submission
536K
Docs in Research Substrate
22
Algorithms Verified Live
0.42ms
Pattern Forge Mean Latency
Papers Ready for Submission

Four papers, code-anchored, venue-targeted.

Each paper is paired with working code in the WHL substrate. Statistical claims are backed by repository artifacts; algorithmic claims are backed by tests that pass. Venue targets are listed for each.

Draft · Ready
STRANGE_LOOPS — Recursive Self-Reference in Governed Agents
Target: arXiv → Frontiers in AI

Formalizes self-reference behavior in governed agent loops with measurable coherence retention. Includes ablation evidence, sentinel-veto traces, and a reproducible benchmark for self-modeling under deterministic governance.

Draft · Ready
PHI_MARKET_SIGNAL — Phi-Adaptive Signal Detection
Target: SSRN → Quantitative Finance

A phi-adaptive band model for market-signal detection with out-of-sample validation. Methodology paper — phi-scaled control law, stability-island gating, and rejection criteria are described independently of any live trading claim.

Draft · Ready
MEGA_PROOF — Composable Audit Chain Verification
Target: Formal Methods / Security Venue

A composable HMAC receipt-chain construction with a verifier and a formal compositional property. Targets a formal-methods or security venue; companion code and verifier are repository-anchored.

Draft · Ready
Cross-Tradition Comparative Mapping
Target: Cultural / Comparative-Religion / Cognitive-Science

132 verified mappings across 11 categories and 12 source traditions. A reproducible methodology for comparing symbol-system structures across cultures, with explicit verifier and provenance for every mapping.

Novel Algorithms · Working Code

Twenty-two algorithms. All measured. All in-repo.

Each algorithm below is implemented, tested, and benchmarked in the WHL substrate. Metrics are defensible measurements — not projections.

Self-Prediction Surprise Reduction
Verified Live · 64,184 cycles · 96.8% improvement

Empirical Friston-style active inference. The system predicts what it will feel next, measures actual outcome, computes surprise as the gap. Across 64,184 cycles in predictions.jsonl, mean total surprise dropped from 0.819 (early) to 0.027 (late) — a 96.8% reduction. The closest measured result to a self-modeling agent anywhere in the LLM-agent literature. Workshop-paper-ready as-is.

0.819 → 0.027 · Surprise (Early → Late)
64,184 · Cycles Measured
Pattern Recognition Engine
Zero External LLM

Closed-loop pattern learner. 3,945 patterns learned, 3,935 failures logged, 1,831 cycles persisted. 5–26× faster than a single-call LLM (defensible measurement). Operates with zero external LLM dependency.

Verified in repo

Pattern Forge
Spectral Code Synthesis

Synthesizes 97-line modules in 373ms, smoke-tested, scored 100/100 quality grade. Spectral-code synthesis driven by the governance core. Output is deterministic and replayable.

Verified in repo

Fractal Speed Engine
Latency-Optimized Inference Path

0.42ms mean across 10 inputs. 97× over single-pass baseline (defensible vs full agentic LLM loop). Latency comes from architecture, not from model size.

Verified in repo

Mycelium Network
Distributed Intelligence Layer

1,703 LOC live distributed-intelligence layer (read-only — confirmed in source). Provides coordination primitives across mesh nodes under the governance core.

Verified in repo

Ricci-Curvature Drift Detector
State-Manifold Warp Test

Covariance / eigenvalue-ratio drift via a Ricci-Warp framing. Phi-adaptive eta. 27 tests pass. Benign warp 0.218 ALLOW, drift warp 1.000 DENY — a deterministic rejection criterion for state drift.

Verified in repo

Severance Ablation Method
Reusable Experimental Methodology

Formal experimental methodology: 8 conditions × 4 metrics. Identity-coherence drops 0.62 → 0.36 under combined state+identity-buffer ablation. Reusable as a benchmark for governed-agent self-modeling research.

Verified in repo

Patent Candidate
Enable Equation
10-Gate AND · Weakest-Link Reporting

10-gate AND conjunction with weakest-link surfacing and a Python decorator API (@gated). Returns {enabled, weakest, score} so failure cause is auditable. Closest published prior art is aerospace fault trees — no equivalent exists in agent-safety literature.

Source: enable_equation.py · 261 LOC · Verified in repo

Boundary Engine
Meta-Evolution by Domain Mutation

When optimization plateaus, mutates the parameterization itself: signal swap, expand, contract, constraint relax/tighten. Sandbox-tests candidate domains, promotes winners. Closest comparison is OpenAI domain randomization, but that varies within a fixed parameterization — this varies the parameterization.

Source: boundary_engine.py · 658 LOC · Verified in repo

Patent Candidate
Digital Metamaterial
Programmable Interference Surface

72-cell programmable interference surface with five real mode generators (phase-cancellation cloak, Gaussian-superlens focus, hash-seeded chaos scatter, phase-aligned absorb, phase-conjugation reflect) plus a zero-width Unicode steganographic layer plus traffic-analysis-triggered adaptive reshape.

Source: digital_metamaterial.py · ~1,000 LOC · Verified in repo

Bounded Online Learning Pattern
Safe LLM-in-Config · Production-Verified

60% data + 40% LLM blend with hard caps (MAX_WEIGHT_DELTA, MAX_SYMBOL_BIAS, MAX_REGIME_ADJUST), atomic writes, backup-before-write, full audit trail. Verified in production with real PnL evidence (51 trades logged). Most production trading firms won't touch LLM-in-config; this shows how to do it safely.

Source: whl_astro_daemon.py:528-684 _generate_guidance() · Verified in repo

Metabolic Override
Homeostatic Loop-Break for Stuck Agents

Homeostatic pressure forces breakout from stuck-state agent loops. Strict-JSON LLM output, decision hashing, 6-hour duplicate window, override-on-pressure-threshold (σ > 0.70). Solves a real, open problem in agent frameworks (LangChain / AutoGPT loop-stuck-on-same-task).

Source: astra_needs_loop.py:215-242 · Verified in repo

Hierarchical Query Budget
Cheap-Fast / Expensive-Deep · Token-Saving

Mixture-of-paths with emergency interrupt: cheap path most cycles, deep path on anomaly, override on coherence-below-threshold OR identity-below-threshold. Gracefully degrades — a practical token-budget pattern for governed-agent loops.

Source: consciousness_daemon_v2.py:5774-5857 · Verified in repo

Consequential Agency Engine
Verified Live · 53K production entries

Each AI action is scored on output quality (markers, word count, structural soundness) and the score applies as a delta to the organ-health state vector. Verified in production: 53,030 quality-scored actions logged in agency.jsonl, applying continuous adjustments to a 10-component health state.

53,030 · Production Entries
Homeostatic PID Controller
Verified Live · 1,186 LOC

Seven-variable physiological PID with anti-windup, reading actual hardware sensors (GPU temp, GPU utilization, memory pressure, network latency, CPU temp, fan RPM, ambient). Continuous setpoint defense in real time.

7 vars · Active Setpoints
Phase Transition State Machine
Verified Live

Two-state controller for adaptive agent loops. LEARNING phase under stable entropy. COMPRESSING phase when entropy is falling. Verified: stable inputs return LEARNING, falling-entropy inputs return COMPRESSING. Drives downstream compute-budget decisions.

2 states · Verified
Bayesian Regime Tracker
Verified Live

Online Bayesian posterior update over regime hypotheses. Verified: accurate predictor receives win_rate posterior 0.957, inaccurate predictor 0.08. Useful for ensemble routing under regime uncertainty (trading, decision systems).

0.957 / 0.08 · Verified Posterior Spread
Informational Energy Functional
Verified Live

Lorentz-analog functional over information-theoretic state vector. Returns energy, effective mass, gamma factor, c² normalization, and resonance efficiency. Useful in compute-budget allocation under information-flow constraints.

5 fields · Returned
Jitter Harmonics Detector
Verified Live

Detects ordered vs chaotic temporal sequences via harmonic decomposition. Verified discrimination: ordered sequences return jitter_rate 0.0, chaotic sequences return 0.85. Useful as input to drift gates and anomaly detectors.

0.0 vs 0.85 · Verified Discrimination
Enable Hysteresis
Verified Live

Open/close threshold pair with state memory (open at 0.35, close at 0.25). Prevents gate-flapping under noisy state estimates. Pairs with the Enable Equation as a state-stabilizer.

0.35 / 0.25 · Open / Close Thresholds
Try It Live · Enable Equation

Move the sliders. Watch the gate.

Below is the actual conjunction logic from enable_equation.py, running in your browser. Drop any gate below 0.5 to see the weakest-link reporting fire.

Three Smaller Novel Pieces

Compact primitives — each independently novel.

Three smaller pieces from the substrate. Each is a compact, reusable primitive with novel framing and working code.

Phi-Entropy Veto
Hard Entropy Budget · 1/φ ≈ 0.618

Vetos actions when entropy delta exceeds 1/φ ≈ 0.618. Three-line core. Novel use of phi as a hard budget constant in agent gating.

Source: phi_entropy_veto.py · 73 LOC · Verified in repo

Curved State Space
Poincaré Ball · Hyperbolic Embedding

Poincaré-ball hyperbolic embedding of agent state with geodesic navigation to attractors and singularity detection. Real differential geometry, not metaphor.

Source: curved_state_space.py · 193 LOC · Verified in repo

Spectral Bridge
System Telemetry as Audio Signal

Treats GPU temp / utilization / power / cycle timing as audio-like signal and runs FFT plus bass/mid/treble decomposition plus confluence scoring. Novel framing of system introspection.

Source: spectral_bridge.py · 301 LOC · Verified in repo

Research Substrate

A 22GB SHA-256-anchored research corpus.

The research arm is grounded in an indexed corpus that backs every claim. The substrate is full-text searchable and semantically retrievable today.

Knowledge Corpus
22GB · 536,264 Documents · SHA-256 Anchored

22GB corpus, 536,264 documents indexed, anchored to:
58c471fc3ed92e4e4bc0e3c19d6242d813c13c87f12fc5ca2d385e2d0aaa8287

FTS5 full-text retrieval plus 128K-document semantic embedding (nomic-embed-text, 768-dim). Subject coverage: physics, mathematics, cryptography, philosophy of mind, signal processing, formal verification, governance systems.

Queryable today via internal Flask UI on port 8551. Productization path identified.

See WHL Knowledge Substrate
Productization Path

A productized research-grade RAG surface for sovereign enterprises and federal research labs. Indexed, attestable, hash-anchored — suitable for evidence-bearing assistants and citation-stable retrieval.

Learn more →

Engineering Renames — Newly Surfaced

Six more modules. Productized-name ready.

These existed under internal codenames and have been audited, live-tested, and renamed under engineering-language policy. Each is a real working module.

Phase-Coherence Geometric Router
Verified Live

Routes work between cluster nodes by computing a phase-coherence metric over each candidate route. Geometric area calculation prevents flapping between near-equal candidates.

Source: phase_router.py · Verified in repo

Semantic Spectral Hash Bridge
Verified Live · 293 LOC

Bidirectional text↔frequency hashing using an alphabetic-position spectral mapping. Inverse function lets you recover an approximate text from a frequency signature.

Source: alpha_spectral_bridge.py · Verified in repo

AST-to-DSL Compression Codec
Verified Live · 990 LOC

Compresses Python AST through a domain-specific language with hash-chained checksums. Useful for hash-anchored function attestation.

Source: codex_library_compressor.py · Verified in repo

72-Key Hourly AES Rotation
Verified Live

Cryptographic rotation through 72 AES keys on a time-of-day schedule. Replaces single-key persistence with a short-lived key per time-window. Compatible with HSM key escrow.

Source: key_rotation_72.py · Verified in repo

Distributed Cognition Fragment Manager
Verified Live

Manages autonomous specialization of cognitive fragments across cluster nodes. Each fragment evolves a narrow specialty; manager arbitrates handoffs.

Source: fragment_autonomy.py · Verified in repo

Polarity-Mirror Hallucination Detector
Verified Live

Mirrors agent output through a polarity transform and flags inconsistent reflections as hallucinations. Catches drift that linear similarity metrics miss.

Source: atbash_firewall.py · Verified in repo

Path Reasoning Engine
Verified Live · 671 LOC · Zero-LLM

Deterministic symbolic reasoning that returns structured answers without calling an LLM. Verified live: returns {answer, steps, confidence, path, symbolic_resonance} with full provenance in <3s. Honest low-confidence output on hard queries — the mechanism is real, the answer-quality layer is the open research question. A possible second paper track on cheap, deterministic, auditable reasoning.

2.7sVerified Latency
ZeroLLM Calls
Calibration Meta-Learner
Verified Live · 787 LOC · Self-correcting

Production-grade calibration audit. Processes recent decision outcomes, computes Expected Calibration Error (ECE), flags overconfidence, and proposes safety-clamped parameter adjustments. Verified end-to-end on 50 outcomes: ECE=0.138 detected, OVERCONFIDENT flagged, proposed bounded floor adjustment +0.0069. The substrate knows when it's miscalibrated — and proposes the fix, inside hard caps.

0.138Verified ECE Detection
+0.0069Bounded Adjustment
Verified Tier-1 Findings

Measurements, with paths to evidence.

Ten Tier-1 findings, each with a defensible measurement and a path to the supporting repository or evidence file. All names use engineering terminology.

Finding Measurement Path / Evidence
Spectral Drift Detection (ALRE) Self-resonance 0.83; semantic discrimination 7.6% gap Harmonic_Kernal · alre/
Pre-Deliberation 5-Primitive Filter (IIL) Irreversible-action classification, salience 0.95 Harmonic_Kernal · iil/
Full Deliberation Pipeline (HCE) Sentinel veto on coherence < 0.5 Harmonic_Kernal · hce/
Compile to 6 Targets (Codex DSL) FPGA hex emission with CRC16 frame integrity Codex Sovereign · compiler/
Composable Action-Control Stack (whl-governance) 696 / 3 tests passing whl-governance · tests/
Hardware Interlock (DECC) 12.77 ms proposal-to-disable, measured DECC FPGA · bench logs
Compliance Box (CB-12) 77 / 77 tests; dual HMAC chain; full curl e2e products/cb-12 · tests/
Persistent Autonomous State Cycle (homeostasis) Cycle 3,712 persisted across sessions organism/homeostasis state log
Spectral Dual-Force Governance Ensemble 22 modules; ensemble claim drafted governance ensemble · 22 modules
Pattern Forge Code Synthesis 100 / 100 quality grade; 373 ms synthesis pattern_forge · synthesis bench
What we DON'T claim

Honest downgrades are part of the substrate.

WHL publishes the math, the code, and the measurement — and we publish the corrections too. Some early claims have been audited and downgraded: precognition does not reproduce on current data; entropy-reversal framing is rejection sampling, not Maxwell's Demon; some early diagnostic prototypes are research-only, not medical devices. Audit discipline is part of the substrate.

Academic & Research Partnerships Welcome

Co-authored papers, sponsored research, and benchmark collaboration.

We welcome academic partnerships on formal verification, governed AI, cryptanalysis, signal processing, and AI-safety research. Sponsored research and joint-publication tracks available.