cs.LGNov 14, 2026

PBit1: One Programmable P-Bit per Parameter - A Finite-Control Representation of Pretrained Networks

Authors: Omar Ramadan

Organizations: Johns Hopkins Whiting School of Engineering

Abstract

We introduce PBit1, a finite-control representation of pretrained neural networks that assigns one programmable p-bit to each learned parameter. A 12-bit command sets its probability, a shared affine range maps that probability to the weight domain, and temporal observations reconstruct the weight for inference. Operator-aware range grouping and sensitivity-based sampling allocation adapt the representation to the network. Across five independent weight draws at 32,768 observations per scalar, selected configurations preserve task quality in GPT-2, DistilBERT, and LFM3-1.7B with every learned scalar converted and no fine-tuning. GPT-2 and LFM3 perplexity increase by approximately 0.66% and 0.26%, respectively, while DistilBERT accuracy changes from 87.51% to 87.49%. A sensitivity-based policy reduces GPT-2 reconstruction observations by 41.7% while retaining the quality criterion. Complete-model evaluations reuse reconstructed weights in BF16 inference, and THRML operator experiments examine native sampling and spatial-temporal tradeoffs. Together, these results establish PBit1 as a concrete construction for studying finite-control weight representation and temporal reconstruction in pretrained networks.

Figures & tables

Explore similar work

CardsList
  1. ThinkBit: Search Codewords, Recalibrate Scales, Select by Reasoning

    Oct 26, 2026Rhea Sanjay Sukthanker, Pashmina CameronLLM QuantizationLow-Bit Quantization

  2. Weight Pair Encoding: Inducing a Smaller Grammar in Neural Network Weights

    Sep 25, 2026Irene Tallini, Daniele Solombrino, Alberto Cazzaniga +1Neural Network CompressionNeural Network Quantization

  3. All for 1-Bit: Towards Genuine 1-Bit Post-Training Quantization for LLMs

    Sep 5, 2026Zhixiong Zhao, Zukang Xu, Guangyu Sun +2LLM QuantizationPost-Training Quantization