NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site terms com pp site www datacom com site www law com site bayviewtech site:arxiv.org” of 144 matched · 1008 ms

Scope: Nishi’s own index (our crawl + Common Crawl) — not the whole live web. Some sites block all automated crawlers (anti-bot walls), so their pages may be absent here even though we never filter lawful content.

Freshness: newest result fetched 25 d ago · median age of these results 25 d · 1 of 30 carry a fetch time

The query asks the model to recall the topic of an earlier conversation about Tesla; the gold answer is anchored in one specific session about Pooja’s dig site
from the top result below

Report GitHub Issue

https://arxiv.org/html/2608.02613v1
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends

1 Introduction

https://arxiv.org/html/2501.13956v1
com Abstract We introduce Zep, a novel memory layer service for AI agents that outperforms the current state-of-the-art system, MemGPT, in the Deep Memory Retrieval (DMR) benchmark

Report GitHub Issue

https://arxiv.org/html/2608.03048v1
com/JetAstra/PI-Mem Introduction The ability to reason over long contexts is increasingly important for large language models (LLMs), supporting applications such as long-document question answering (Gemini Team 2025; Yang et al

Rainfall is rough

https://arxiv.org/html/2607.27099v1
Analysis of high-frequency rainfall data (at the minute scale over several years) indicates that critical Hawkes processes with heavy-tailed power-law kernels yield a superior fit relative to classical models and alternative kernel specifications

Computation and Language

https://arxiv.org/list/cs.CL/new
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends

[2608.03883] DS@GT-ARC at eRisk 2026 Task 3: Sparse, Semantic, and LLM

https://arxiv.org/abs/2608.03883
Our systems combine sparse BM25 retrieval, evidence-aware rescoring for self-referential symptom reports, embedding-based reranking, query-prototype expansion, and LLM-based reranking

1 Introduction

https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands Slack http://bit

[2006.04236] Distributed-Memory Vertex-Centric Network Embedding for

https://arxiv.org/abs/2006.04236
Comments: 2019 IEEE 5th International Conference on Big Data Intelligence and Computing (DATACOM) Subjects: Distributed, Parallel, and Cluster Computing (cs

[2104.08663] BEIR: A Heterogenous Benchmark for Zero-shot Evaluation of

https://arxiv.org/abs/2104.08663
Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs

[2608.03860] SciRet: A Compute-Aware Empirical Study of Retrieval and

https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation

Information Retrieval

https://arxiv.org/list/cs.IR/recent
Skip to main content System maintenance August 4th and 5th Learn more × Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Information Retrieval Authors and titles for recent submissions Wed, 5 Aug 2026

Information Retrieval

https://arxiv.org/list/cs.IR/new
Skip to main content System maintenance August 4th and 5th Learn more × Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Information Retrieval New submissions Cross-lists Replacements See recent

Distributed, Parallel, and Cluster Computing Jun 2020

https://arxiv.org/list/cs.DC/2020-06
Skip to main content System maintenance August 4th and 5th Learn more × Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Distributed, Parallel, and Cluster Computing Authors and titles for June 2020

Artificial Intelligence

https://arxiv.org/list/cs.AI/new
Skip to main content System maintenance August 4th and 5th Learn more × Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Artificial Intelligence New submissions Cross-lists Replacements See recent

Optimal Execution with Passive Market Impact

https://arxiv.org/html/2607.28323v1
Across asset classes and datasets, empirical studies have found that price impact is typically concave in executed volume and depends on participation rate, execution duration, and market liquidity in a manner often summarised by square-root or related power-law specifications [4, 7, 13, 21, 27, 36, 39, 40, 43]

Producing Policy Recommendations: from Statistical Decision Theory to

https://arxiv.org/html/2607.29281v2
The problem of making such choices becomes ever more challenging if they need to be made ex-ante, meaning when only minimal or no information about (i) the probability laws of the population of interest and (ii) the causal law of a given intervention is available

Sphere Retraction Normalizations

https://arxiv.org/html/2608.02668v1
com/hazdzz/deep_connection \ncudata[Correspondence]Jie Zhang (), Correspondence: Cheng-Fang Su () “Geometry is not true, it is advantageous

Automatic Patient-Specific Microwave Ablation Planning Accelerated by a

https://arxiv.org/html/2608.03086v1
Physics-Guided Deep Learning Model Report GitHub Issue × Title: Content selection saved. Describe the issue below: Description: Submit without GitHub Submit in GitHub arXiv is now an independent nonprofit! Learn more × Back to arXiv

Efficient Multilingual Neural Machine Translation via Corpus-Driven

https://arxiv.org/html/2608.03480v1
com Arabic Institute for Translation, Algiers, Algeria CERIST, Algeria Nasredine Semmar CEA LIST, Paris-Saclay, France Hassina Aliane CERIST, Algeria Abstract The adoption of large pre-trained multilingual models for neural machine translation (MNMT) faces a major challenge: excessive memory and computational

Can Large Language Models Execute Parent Orders?

https://arxiv.org/html/2607.28410v1
com/zaneopen/PACE 1 Introduction Reducing execution costs is a central objective for financial institutions (Bertsimas and Lo 1998)

I INTRODUCTION

https://arxiv.org/html/2407.10811v1
II RELATED WORK II-A Traditional methods II-B RL methods. III PRELIMINARIES IV METHOD IV-A RL Setup IV-B Network design IV-C Training IV-D Theoretical Analysis V EXPERIMENT V-A Towards Real-world Dataset and Simulation V-B Benchmark

%PDF-1.7 % 1 0 obj > stream xXMo7 WXW @ i&99i@

https://arxiv.org/pdf/2608.03157
44C0M8$SHRpk4>e8Q{ћPp/I1Mc2^Q#T#NrFRKcl w'0I}JUh+`d@Wul`r0=hJlf6'hީ&8bA| kJwԄFLŷJ6Q,'DU {P_GObiwI& zkHF)Ҫ0^SogR7C68W l2N *cO8S

Report GitHub Issue

https://arxiv.org/html/2608.03154v1
com/COMBINI-Hub/Multi_Agent_Relation_Extraction

Finance-Informed Neural Network: Learning the Geometry of Option Pricing

https://arxiv.org/html/2412.12213v2
Report GitHub Issue × Title: Content selection saved. Describe the issue below: Description: Submit without GitHub Submit in GitHub arXiv is now an independent nonprofit! Learn more × Back to arXiv Why HTML? Report Issue Back to

Inverse Learning of Latent Risk-Neutral Densities from Irregular Option

https://arxiv.org/html/2607.27188v1
In machine-learning terms, RND recovery is an inverse problem from irregular observations (Arridge et al

Asking Questions the Right Way: A Multi-Agent Conversational System for

https://arxiv.org/html/2608.01366v2
com Affiliation: Department of Design and Manufacturing, Indian Institute of Science (IISc) , Bangalore , India , Srinidhi Ranjini Girish email: srinidhirgirish@gmail

Coordinated Primary Frequency Regulation and Grid-Forming Control for

https://arxiv.org/html/2608.02813v1
Wind Turbine Generators Report GitHub Issue × Title: Content selection saved. Describe the issue below: Description: Submit without GitHub Submit in GitHub arXiv is now an independent nonprofit! Learn more × Back to arXiv Why HTML?

Consensus Measures for Unstructured Biomedical Text Annotations

https://arxiv.org/html/2608.03529v1
(2024), where a human expert and an automated system might describe information in different terms

Report GitHub Issue

https://arxiv.org/html/2609.02852v1
A linguistically-decodable feature is one that is defined in terms of natural language, and is extracted directly from a model’s natural-language outputs or indirectly via mechanistic probes like sparse autoencoders Bricken et al

Report GitHub Issue

https://arxiv.org/html/2608.00458v1
× Title: Content selection saved. Describe the issue below: Description: Submit without GitHub Submit in GitHub arXiv is now an independent nonprofit! Learn more × Back to arXiv Why HTML? Report Issue Back to Abstract Download PDF