NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site terms com pp site github com site led would site pass my site:arxiv.org” of 33 matched · 675 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: no result on this page carries a fetch time yet (indexed before the fetch epoch was stored beside the doc)

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/2608.03063v1
8 pp in a production fraud detector serving billion-scale transaction traffic

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

Efficient Audio Enhancement with a Differentiable Psychoacoustic Loss

https://arxiv.org/html/2608.02918v1
Miranda is also with LCTI, Télécom Paris, IP Paris, France

Report GitHub Issue

https://arxiv.org/html/2607.22511v2
The source code, formal library, and run records are available at https://github

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

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

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

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.

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

1 Introduction

https://arxiv.org/html/2402.03300v3
com/deepseek-ai/DeepSeek-Math Abstract Mathematical reasoning poses a significant challenge for language models due to its complex and structured nature

Internalizing Academic Writing Workflows for Introduction Generation via

https://arxiv.org/html/2608.03138v1
We propose StructPO, a struct-aware policy learning framework that internalizes the entire multi-stage writing workflow into a single-pass policy controlled by explicit stage tokens

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

1 Introduction

https://arxiv.org/html/2403.08299v1
The landscape of software development has witnessed a paradigm shift with the advent of AI-powered assistants, exemplified by GitHub Copilot

Software Engineering

https://arxiv.org/list/cs.SE/new
Despite their ubiquity across tools and programming languages, a lack of standardization has led to a fragmented ecosystem rife with inconsistent behaviors, security vulnerabilities, and usability pitfalls

Report GitHub Issue

https://arxiv.org/html/2608.03372v1
org  GitHub sourcecontextcandidatememoryalign claimscontent-word overlapseven checkspolarity ⋅\cdot condition ⋅\cdot temporalhedge ⋅\cdot attributionbrittle ⋅\cdot truncatedflagsevidence + citationverdict policyhard-codedpasspass_w_flagsrewriterejectuncheckablenever a passwitness (optional)one sentence, one

Report GitHub Issue

https://arxiv.org/html/2608.03624v1
In domains such as healthcare, this is a hard requirement; sensitive data cannot leave the premises, so models must run on-site, often on limited hardware Garg et al

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

Reviving Micro Real Rigidities: The Importance of Demand ShocksThe views

https://arxiv.org/html/2608.02817v1
The authors would like to thank Nir Jaimovich (editor) and four anonymous referees, as well as Isaac Baley, Mark Bils, Laura Castillo-Martínez (discussant), Basile Grassi, Susanto Basu, John Haltiwanger, Pete Klenow, Francesco Lippi, Virgiliu Midrigan, Tobias Renkin, Luminita Stevens, Javier Turén, Rosen Valchev

Speculative Correction: Draft-then-Refine Decoding for Diffusion

https://arxiv.org/html/2608.02625v1
Despite showing early promise, especially in terms of efficiency, DLMs face a fundamental challenge when applied to language generation: DLMs are by design inherently bidirectional

Aligned in Form, Not in Meaning: The Comprehension–Containment

https://arxiv.org/html/2608.02941v1
72% Pass) while systematically dismantling containment (96

\dotsttsfontdots.tts.edit: Precisely Controlled Speech Editing with a

https://arxiv.org/html/2608.02673v1
Continuous Autoregressive 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

Stress-Relief Annealing: Polynomial-Time Simulation-Free Layout

https://arxiv.org/html/2608.01024v1
Optimization for Automated Warehouses 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

SFT Conflicts, RL Coexists: A Theoretical and Empirical Analysis of

https://arxiv.org/html/2608.03573v1
Multi-Task Learning Paradigms for LLMs 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

Computer Vision and Pattern Recognition

https://arxiv.org/list/cs.CV/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 Computer Vision and Pattern Recognition New submissions Cross-lists Replacements

[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