Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2610.10441

CrossWeave: Bridging Perspectives Across Online Communities with a Dual-Pane Design

Fei Fang·Reva Hirave·William Jurayj·Yuqi Li·Brian Lu·Tarik Metin·Tsugunobu Miyake·Kateryna Morhun·Yash Permalla·Kenan Rustamov·Allen Shen·Haojun Shi·Prabhav Singh·Xiheng Tom Wang·Kevin Xu·Qingcheng Zeng·Jiayi Zhang·Daniel Khashabi·Andrew Perrin·Tiziano Piccardi·Ziang Xiao·Jason Eisner
View original source ↗Read source document ↗Export metadata ↓

Abstract

Social media systems typically display conversations among already familiar contributors, which can be predictable and one-sided. In civic discourse, this design narrows discussion, reinforces divides, and distorts the perception of public opinion. To encourage cross-community engagement, we present CrossWeave, an AI-powered bridging system that augments the standard social media feed. As the user reads a post, CrossWeave surfaces diverse relevant posts from other threads in a side pane and highlights the connections. Users are invited to venture out of their echo chamber, explore a broader range of views and arguments, and ``click across'' to engage with their authors. When they do, CrossWeave facilitates constructive posting, not only by showcasing relevant past content but also by simulating possible reactions as the user drafts a post.

Explore related subjects

cs.SIcs.HCcs.IR

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Fei Fang, Reva Hirave, William Jurayj, Yuqi Li, Brian Lu, Tarik Metin, Tsugunobu Miyake, Kateryna Morhun, Yash Permalla, Kenan Rustamov, Allen Shen, Haojun Shi, Prabhav Singh, Xiheng Tom Wang, Kevin Xu, Qingcheng Zeng, Jiayi Zhang, Daniel Khashabi, Andrew Perrin, Tiziano Piccardi, Ziang Xiao, Jason Eisner. 2026-10-07. CrossWeave: Bridging Perspectives Across Online Communities with a Dual-Pane Design. https://doi.org/10.1145/3785651.3831421

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

SparkAlign: A Star-Hopping Heuristic for Efficient Unsupervised Plain Graph Alignment

Unsupervised plain graph alignment (UPGA) seeks corresponding nodes between two graphs from topology alone, without attributes or seed anchors. The dominant embed-then-match paradigm is expensive on both fronts: it repeatedly retrains node embeddings and then solves a costly global assignment, so it scales poorly to large graphs. We present SparkAlign, a training-free heuristic that, inspired by star-hopping in celestial navigation, locates a node's counterpart by measuring its heat-diffusion proximity to a shared set of high-confidence landmark matches. Although heuristic in spirit, the descriptor is principled: diffusion makes structurally equivalent nodes comparable across graphs, and a short stability analysis justifies a finite diffusion depth. Matching then uses two sparse, highly parallel strategies that avoid dense global assignment, one favoring speed and one preserving one-to-one consistency on a restricted candidate set. On three benchmarks SparkAlign attains accuracy approaching a structural identifiability reference while running up to two orders of magnitude faster than the strongest baseline and seeding markedly more accurate pseudo-anchors. Our code is available at https://github.com/MaxQ545/SparkAlign

cs.SI↗
arXiv2026

Theoretical Analysis of DomiRank Centrality: Automorphism, Entropy, and Graph Transformations

DomiRank is a node-importance algorithm for unweighted networks, defined by a dynamical-system model whose steady state is governed by a competition-strength parameter, a dominance threshold, and a natural decay rate. We study its intrinsic relations with graph automorphism: vertices mapped to each other by an automorphism share the same DomiRank value, and a graph whose DomiRank values are pairwise distinct must be asymmetric; we derive DomiRank properties of regular and vertex-transitive graphs and bound the number of orbits by that of distinct DomiRank values. For DomiRank entropy, the maximum over connected graphs is attained only by regular graphs, and under sufficient conditions (rigorously in the low-competition regime) the entropy decreases monotonically with the competition parameter, a behavior observed on all tested networks and conjectured to hold generally; tuning sigma shifts the identification from important to dominant key nodes. We also study how graph transformations (vertex similarity, vertex partitions, edge swaps, m-products) affect the DomiRank vector, and characterize analytically the sensitivity and limiting behavior of sigma: the normalized DomiRank distribution is sigma-invariant iff the degree vector is an eigenvector of the adjacency matrix, and sigma interpolates continuously between degree and least-eigenvector centrality; experiments on four real networks confirm these results. These results position DomiRank as a tunable complement to principal-eigenvector centrality, with distinctive behavior under strong competition and new tools for node-importance evaluation. Because the parameterization by sigma is a structural property of the measure, not a guarantee of advantage on a downstream task, we also relate these results to the companion null-model study of how much of DomiRank's task-level edge over a degree baseline survives an explicit degree correction.

cs.SI↗
arXiv2026

A General Capacity Frontier of Complex Networks

From cells to cities, ecosystems to economies, complex networks exhibit peak intensities that define their empirical limit. Estimating these limits traditionally requires domain-specific knowledge. We demonstrate that a wide range of complex networks share a capacity frontier that constrains these maxima. We formalize this regularity by proposing Structural Capacity Theory for Network Substrate Structured Systems. These systems couple a fixed network substrate with an observable dynamical process. The frontier is learned from a vector representation of the network substrate and modulated log-additively by a vector representation of the dynamical process. Frontiers trained on one set of domains reliably bound empirical maxima of entirely different ones without observing their peak intensities or simulating their dynamics. Independent learning paradigms converge on consistent upper bounds. Frontier performance is stable under perturbation, yet degrades under deliberate falsification, with no performance gain under ablation. These findings support the capacity frontier as a generalizable constraint that describes how network structure bounds dynamical processes across otherwise unrelated systems.

cs.SI↗