Paper

Zero-Copy Semantic Contagion: An In-Memory Streaming Architecture for Evolving Attention Graphs

Unreadunread

AI summary

arXiv:2606. 05733v1 Announce Type: cross Abstract: Per-ticker forecasting models dominate financial time-series work yet remain blind to cross-company propagation: a foundry disruption in Taiwan does not register in a single-asset model until Apple's own price has already moved.

Reading status

Priority

About this paper

Authors: Kabir Murjani
Released: 2026-06-05 (1mo ago)
Topic: Related to current project
Relation to my work: Read next because Zero-Copy Semantic Contagion: An In-Memory Streaming Architecture for Evolving Attention Graphs overlaps with clean result "LoRA persona trained on <A> alone emits <B> at 23.5% when a co-trained partner learns <A>...<B>, vs 0% control on Qwen2.5-7B-Instruct (MODERATE confidence)", clean result "Leakage rate is a usable signal for recovering trigger-shaped phrases on Gaperon-1125-1B without knowing the hidden trigger itself (MODERATE confidence)", clean result "Language-mismatch LoRA SFT on Qwen2.5-7B leaks the trained completion language into bystander directives the model was never trained on, absent under same-language SFT (LOW confidence)". Matching terms: text, rect, eval, line, rate, project, does, propagate. Source: arxiv stat.ML (Machine Learning).
arXiv: 2606.05733

Ask Claude about this paper

Posts a comment with @claude so the runner spins up a Claude Code session scoped to Zero-Copy Semantic Contagion: An In-Memory Streaming Architecture for Evolving Attention Graphs. Replies appear in the conversation below.

Comments

No comments yet.

Related records

No links yet.