NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site hotchips pp site github com site docs cercos dev site www proxy com site:arxiv.org” of 32 matched · 4092 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 26 d ago · median age of these results 26 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/2407.16741v3
com/All-Hands-AI/OpenHands Slack http://bit

Report GitHub Issue

https://arxiv.org/html/2609.02852v1
Report GitHub Issue Description: arXiv is now an independent nonprofit

Predicting Multilingual Classification and Translation Performance of

https://arxiv.org/html/2608.03446v1
com/KathyHaem/cla-metrics 2 Background and Related Work Cross-lingual alignment

Testing the effects of an unobservable factor: Do marriage prospects

https://arxiv.org/html/2410.19947v2
affect college major choice?1footnote 11footnote 1We are grateful for the valuable feedback from seminar participants at the National University of Singapore, the University of Notre Dame, the University of Pennsylvania, Mississippi State

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

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

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

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

Rainfall is rough

https://arxiv.org/html/2607.27099v1
This prediction is supported by empirical evidence from low-frequency data (annual observations spanning centuries to millennia), where the Hurst exponent is estimated to lie between 10−210^{-2} and 10−110^{-1} based on either direct observations from weather stations or proxy reconstructions such as tree-ring

Mapping the City Through the Lens of Language Models

https://arxiv.org/html/2608.02971v1
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

What Language Does and What the Evidence Supports: A Functional Role

https://arxiv.org/html/2608.03099v1
Taxonomy and Evidence Audit of Language Grounding in Embodied Agents Report GitHub Issue × Title: Content selection saved. Describe the issue below: Description: Submit without GitHub Submit in GitHub arXiv is now an independent

Very Large-Scale Multi-Agent Simulation in AgentScope

https://arxiv.org/html/2407.17789v2
com/modelscope/agentscope/tree/main/examples/paper_large_scale_simulation to inspire further research and development in large-scale multi-agent simulations

Producing Policy Recommendations: from Statistical Decision Theory to

https://arxiv.org/html/2607.29281v2
Empirical Practice 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?

Effort-Centric Fairness in Lending Decisions

https://arxiv.org/html/2607.28847v1
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

Preying on Leveraged ETFsPreliminary and incomplete. This project was

https://arxiv.org/html/2608.03703v1
begun on July 20, 2026; the present version is dated August 4, 2026. Claude Opus 5 and Fable 5 provided research assistance throughout, spanning code development, data construction and empirical analysis, and the drafting of the manuscript.

[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

[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

Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical

https://arxiv.org/html/2608.02617v1
CL] 25 May 2026 Preferred, Not Safer: Pairwise Preference Is a Poor Proxy for Clinical Safety Fay Elhassan LiGHT Laboratory, EPFL, Lausanne, Switzerland David Sasu LiGHT Laboratory, EPFL, Lausanne, Switzerland Alexandra Kulinkina LiGHT Laboratory, EPFL, Lausanne, Switzerland Lars Henning Klein LiGHT Laboratory, EPFL

Report GitHub Issue

https://arxiv.org/html/2608.03411v1
com Abstract Accurate Uncertainty Quantification (UQ) is critical for reliable deployment of Large Language Models (LLMs), yet traditional probability-based metrics often fail to capture the model’s true epistemic state

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

Beyond Initialization Loss: A Systematic Study of Token Embedding

https://arxiv.org/html/2608.03494v1
com 1 Introduction Modern large language models (LLMs) process text using subword tokenizers such as Byte-Pair Encoding (BPE) Sennrich et al

Looking under the Wrong Lamppost: On the Limitations of Automated

https://arxiv.org/html/2608.03577v1
Translation Quality Estimation 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

Computer Science and Game Theory

https://arxiv.org/list/cs.GT/new
Skip to main content Search Submit Donate Log in Search arXiv Press Enter to search · Advanced search Computer Science and Game Theory New submissions Replacements See recent articles Showing new listings for Monday, 17 August 2026

A Heterogeneous Spatiotemporal GARCH Model: A Predictive Framework for

https://arxiv.org/html/2508.20101v1
The model combines classical GARCH(pp, qq) dynamics with spatially correlated innovations and spatially varying parameters, estimated using local likelihood methods

[2604.07181] Better Measurement or Larger Samples? Data Collection for

https://arxiv.org/abs/2604.07181
In an empirical application in development economics, I show that including a proxy for entrepreneurs' business skills in targeting cash transfers increases welfare by 5%, and halves the probability of generating welfare losses

Computer Vision and Pattern Recognition

https://arxiv.org/list/cs.CV/new
World modeling offers a natural intermediate proxy that allows agents to query lower-cost, more controllable feedback before committing to real actions

Electrical Engineering and Systems Science

https://arxiv.org/list/eess/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 Electrical Engineering and Systems Science New submissions Cross-lists