// manuscripts & preprints
Submitted — Jun 2026
The Art of Art: A Strategic Treatise on Human Creativity and Generative AI
Justin A. Fritz — The Canonical Art LLC — 2026
Proposed to Leonardo (MIT Press), CFP “From Cybernetics to Co-Creation”
Develops a dynamical systems framework for distinguishing AI-assisted from AI-generated creative and intellectual work. Grounded in four hand-drawn conceptual diagrams produced 2022–2023, prior to the public availability of large-scale generative AI, and in the author’s experience as a hardware engineer whose AI-assisted papers have been challenged on provenance grounds.

Four propositions: (I) human creative cognition is a knowledge state machine Kt+1 = f(Kt, θt, εt) whose trajectory constitutes authorship; (II) economic value of intellectual work derives from the rate of change of the knowledge field it induces, not static output quality; (III) generative AI is a derived state-space transformer without an independent knowledge trajectory; (IV) current AI provenance evaluation measures distributional proximity to training data — the wrong metric for the right question. The synthesis reconnects to Wiener’s cybernetics trilogy (1948–1964).
Preprint — 2026
The Read-Modify-Write Wall: A Unified Cost Model for Die-to-Die Memory in AI/HPC Algorithm Design
Justin A. Fritz — The Canonical Art LLC — 2026
arXiv cs.AR (endorsement pending)
Presents a four-dimension cost model for HBM die-to-die interfaces: bandwidth efficiency, access latency, energy per operation, and area-normalized throughput. All parameters grounded in JEDEC JESD235C (HBM2e) and JESD270-4A (HBM4) timing specifications.

Central finding: graph traversal and LLM inference achieve only 34–53% bandwidth efficiency on HBM4 at 8 Gb/s. The bottleneck is tRRD — the row-to-row activation delay — not the data bus rate. HBM4’s higher data rate paradoxically reduces random-access efficiency relative to HBM2e. Standards contribution: halving tRRD,S from 4 to 2 cycles in the HBM5 JEDEC JC-42 specification delivers +37% effective bandwidth to graph workloads and +21% to LLM inference.
Preprint — 2026
BFS-HBM: Open-Source RTL for Deterministic k-Hop Graph Traversal on High-Bandwidth Memory
Justin A. Fritz — The Canonical Art LLC — 2026
arXiv cs.AR (endorsement pending)
Synthesizable SystemVerilog microarchitecture for BFS traversal of CSR-encoded sparse graphs stored in HBM. 12-state AXI4 traversal FSM, 2-cycle BRAM read-modify-write visited bitmap, FIFO-based frontier queue. Single-beat row-pointer fetch eliminates a second HBM round trip per vertex.

Cycle-accurate simulation at 250 MHz with 20-cycle modeled HBM latency confirms correct BFS ordering for all vertices in 514 cycles. Throughput model converges to η ≈ 40% at realistic graph degrees, consistent with the companion HBM timing analysis. FPGA bring-up path documented for Xilinx Alveo U280; ASIC target TSMC N7 / GlobalFoundries 12LP. MIT license.
// talks & outreach
Jun 2025
Nerd Nite Fort Collins S25E6 · Wolverine Farm
Used an AI model of Norbert Wiener to diagram modern AI technology and make predictions about its future. Live instance of the two-operator model formalized in The Art of Art: author’s K-trajectory (cybernetics, AI systems, social consequences) directing an AI to instantiate Wiener’s perspective.