Tootfinder

This https://arxiv.org/abs/2412.00639 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

Needle: A Generative AI-Powered Multi-modal Database for Answering Complex Natural Language Queries
Multi-modal datasets, like those involving images, often miss the detailed descriptions that properly capture the rich information encoded in each item. This makes answering complex natural language queries a major challenge in this domain. In particular, unlike the traditional nearest neighbor search, where the tuples and the query are represented as points in a single metric space, these settings involve queries and tuples embedded in fundamentally different spaces, making the traditional que…

This https://arxiv.org/abs/2502.09891 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

ArchRAG: Attributed Community-based Hierarchical Retrieval-Augmented Generation
Retrieval-Augmented Generation (RAG) has proven effective in integrating external knowledge into large language models (LLMs) for solving question-answer (QA) tasks. The state-of-the-art RAG approaches often use the graph data as the external data since they capture the rich semantic information and link relationships between entities. However, existing graph-based RAG approaches cannot accurately identify the relevant information from the graph and also consume large numbers of tokens in the o…

This https://arxiv.org/abs/2502.09304 has been replaced.
initial toot: https://mastoxiv.page/@arXiv_csIR_…

KET-RAG: A Cost-Efficient Multi-Granular Indexing Framework for Graph-RAG
Graph-RAG constructs a knowledge graph from text chunks to improve retrieval in Large Language Model (LLM)-based question answering. It is particularly useful in domains such as biomedicine, law, and political science, where retrieval often requires multi-hop reasoning over proprietary documents. Some existing Graph-RAG systems construct KNN graphs based on text chunk relevance, but this coarse-grained approach fails to capture entity relationships within texts, leading to sub-par retrieval and…

Seeing is not believing in limited visibility cops and robbers
Bojan Ba\v{s}i\'c, Alfie Davies, Aleksa D\v{z}uklevski, Strahinja Gvozdi\'c, Yannick Mogge
https://arxiv.org/abs/2507.00941

Seeing is not believing in limited visibility cops and robbers
We consider the model of limited visibility Cops and Robbers, where the cops can only see within their $l$-neighbourhood. We prove that the number of cops needed to see the robber can be arbitrarily smaller than the number needed to capture the robber, answering an open question from the literature. We then consider how close we can get to seeing the robber when we do not have enough cops, along with a probabilistic interpretation.

Temporally Extending Existing Web Archive Collections for Longitudinal Analysis
Lesley Frew, Michael L. Nelson, Michele C. Weigle
https://arxiv.org/abs/2505.24091

Temporally Extending Existing Web Archive Collections for Longitudinal Analysis
The Environmental Governance and Data Initiative (EDGI) regularly crawled US federal environmental websites between 2016 and 2020 to capture changes between two presidential administrations. However, because it does not include the previous administration ending in 2008, the collection is unsuitable for answering our research question, Were the website terms deleted by the Trump administration (2017--2021) added by the Obama administration (2009--2017)? Thus, like many researchers using the Way…

Peer Review as Structured Commentary: Immutable Identity, Public Dialogue, and Reproducible Scholarship
Craig Steven Wright
https://arxiv.org/abs/2506.22497

Peer Review as Structured Commentary: Immutable Identity, Public Dialogue, and Reproducible Scholarship
This paper reconceptualises peer review as structured public commentary. Traditional academic validation is hindered by anonymity, latency, and gatekeeping. We propose a transparent, identity-linked, and reproducible system of scholarly evaluation anchored in open commentary. Leveraging blockchain for immutable audit trails and AI for iterative synthesis, we design a framework that incentivises intellectual contribution, captures epistemic evolution, and enables traceable reputational dynamics.…

Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
Travis Thompson, Seung-Hwan Lim, Paul Liu, Ruoying He, Dongkuan Xu
https://arxiv.org/abs/2506.19967

Inference Scaled GraphRAG: Improving Multi Hop Question Answering on Knowledge Graphs
Large Language Models (LLMs) have achieved impressive capabilities in language understanding and generation, yet they continue to underperform on knowledge-intensive reasoning tasks due to limited access to structured context and multi-hop information. Retrieval-Augmented Generation (RAG) partially mitigates this by grounding generation in retrieved context, but conventional RAG and GraphRAG methods often fail to capture relational structure across nodes in knowledge graphs. We introduce Infere…

Statistical Insights into Flux and Photon Index Distributions of VHE FSRQs from Fermi-LAT Observations
Zahoor Malik, Sikandar Akbar, Zahir Shah, Ranjeev Misra, Athar A. Dar, Aaqib Manzoor, Sajad Ahanger, Zeeshan Nazir, Naseer Iqbal, Seemin Rubab, Javaid Tantry
https://arxiv.org/abs/2505.23338

Statistical Insights into Flux and Photon Index Distributions of VHE FSRQs from Fermi-LAT Observations
This study examines the flux and photon index distributions of 11 Very High Energy (VHE) Flat Spectrum Radio Quasars (FSRQs) using over 16 years of Fermi-LAT $γ$-ray data. The distributions reveal double lognormal profiles in both flux and index, primarily in the 3-day and 7-day binnings, supporting the ``two-flux-state hypothesis" for blazars. These profiles, which become insignificant at 30-day binning, suggest that shorter timescales are better at capturing distinct states, while longer tim…

ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset
Yilin Wang, Peixuan Lei, Jie Song, Yuzhe Hao, Tao Chen, Yuxuan Zhang, Lei Jia, Yuanxiang Li, Zhongyu Wei
https://arxiv.org/abs/2506.20093

ITFormer: Bridging Time Series and Natural Language for Multi-Modal QA with Large-Scale Multitask Dataset
Time-series data are critical in diverse applications, such as industrial monitoring, medical diagnostics, and climate research. However, effectively integrating these high-dimensional temporal signals with natural language for dynamic, interactive tasks remains a significant challenge. To address this, we introduce the Time-Series Question Answering (Time-Series QA) task and release EngineMT-QA, the first large-scale, multi-task, temporal-textual QA dataset designed to capture complex interact…

The exact region and an inequality between Chatterjee's and Spearman's rank correlations
Jonathan Ansari, Marcus Rockel
https://arxiv.org/abs/2506.15897

The exact region and an inequality between Chatterjee's and Spearman's rank correlations
The rank correlation xi(X,Y), recently introduced by Chatterjee [12] and already popular in the statistics literature, takes values in [0,1], where 0 characterizes independence of X and Y, and 1 characterizes perfect dependence of Y on X. Unlike classical concordance measures such as Spearman's rho, which capture the degree of positive or negative dependence, xi quantifies the strength of functional dependence. In this paper, we determine, for each fixed value of xi, the full range of possible …