PulseAugur / Brief
EN
LIVE 06:30:00

Brief

last 24h
[2/2] 222 sources

Multi-source AI news clustered, deduplicated, and scored 0–100 across authority, cluster strength, headline signal, and time decay.

  1. TOOL · arXiv stat.ML English(EN) ·

    Worker Utility as Hysteresis: A Preisach Model of Transaction Acceptance in Gig Labour Markets

    Researchers have developed a novel Preisach hysteresis model to better understand worker acceptance in gig labor markets. This model, implemented using a dual-output neural network and an XGBoost classifier, analyzes transaction data to predict worker utility. The system achieved a Jaccard index of 0.827 and an ROC AUC of 0.799 on a dataset of 36,891 gig transactions. The model's findings indicate that price decreases have a more significant negative impact on completion rates than equivalent increases have positive impacts, leading to recommendations that could reduce wage bills by over 21% while increasing fill rates. AI

    IMPACT Provides a new framework for optimizing gig economy platforms by modeling worker acceptance and wage dynamics.

  2. RESEARCH · arXiv cs.NE (Neural & Evolutionary) English(EN) · · [3 sources]

    Preisach Attention: A Hysteretic Model of Sequential Memory

    Researchers have introduced the Preisach Attention Layer (PAL), a new sequence modeling architecture inspired by the Preisach hysteresis operator from mathematical physics. PAL replaces standard softmax attention with a binary relay operator, maintaining a stack of local extrema as its state. This novel approach offers Turing completeness in a single layer and computes historical range statistics efficiently, making it suitable for tasks requiring long episodic memory with weak positional dependence. AI

    IMPACT Introduces a novel architecture for sequence modeling that could improve efficiency for tasks with long-term memory requirements.