NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site my shortage blogspot com site www uscourts gov site won iza org site:arxiv.org” of 35 matched · 705 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.

Did you mean okapi bm25 site my shortage blogspot com site www uscourts gov site won ia org site:arxiv.org?

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

1 Search Zep implements three search functions: cosine semantic similarity search (φcos)subscript𝜑cos(\varphi_{\text{cos}})( italic_φ start_POSTSUBSCRIPT cos end_POSTSUBSCRIPT ), Okapi BM25 full-text search (φbm25)subscript𝜑bm25(\varphi_{\text{bm25}})( italic_φ start_POSTSUBSCRIPT bm25 end_POSTSUBSCRIPT )
from the top result below

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

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

W{s_AAIvl-*susM&N;HI@wDJϗ[

https://info.arxiv.org/help/policies/privacy_policy.html
Yv]Q|iza$ @'LxHކPUz

%PDF-1.5 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream

https://arxiv.org/pdf/2504.17033
Breaking the Sorting Barrier for Directed Single-Source Shortest PathsRan DuanJiayi MaoXiao MaoXinkai ShuLonghui Yinhttp://arxiv.org/licenses/nonexclusive-distrib/1.0/cs.DS endstream endobj 4 0 obj > endobj 5 0 obj > endobj 6 0 obj > endobj

%PDF-1.7 % 1 0 obj > stream xYo@+Ux])0mC  %Pqe

https://arxiv.org/pdf/2609.18842
HE*QC6TnnHi{9@}ڌ}mx9pkr u\oV`8zAͷdz_w_V|0r+{vYU-|> endobj 28 0 obj > stream x\[s۸~_ݚJ@܁SSqvn35:-$gHA"ȶ2[" З hu*-+**+++%

%PDF-1.5 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream

https://arxiv.org/pdf/2508.02685
Benchmarking Classical and Quantum Models for DeFi Yield Prediction on Curve FinanceChi-Sheng ChenAidan Hung-Wen Tsaihttp://arxiv.org/licenses/nonexclusive-distrib/1.0/q-fin.STcs.LGq-fin.TR endstream endobj 4 0 obj > endobj 5 0 obj > endobj

%PDF-1.7 % 1 0 obj > stream xo0W{5%glj-U J Pئ>xĢ

https://arxiv.org/pdf/2607.28410v1
/``#bRwƀ^,mY[[>۫)u*0YnTfmOi붶}LGJZk{neS8l'7`GFﻻww+2^V'h^Jd^`\9')3GsUu ,>`_1^)&%TbCҬHP(sˉ{%,;uv

%PDF-1.5 % 1 0 obj > stream xY]o6}_fuo ( ,omE}ZADږ

https://arxiv.org/pdf/2608.02851v1
%6G"8/1tx493C`LԒ)c9S18YecܨՌ;4LCς eQ0F3pLVVһL -ѳc8zt4h(SdSLՂ5\ҳaZ*LkC|r*1)3I83Ҥ) hL1F2aYebt,qU1+(nřG.|-;tϾvcynЏ

%PDF-1.7 % 1 0 obj > stream x}TɎ0 +x\SASgڢ˩

https://arxiv.org/pdf/2608.02244
‹gfL^U+}*l$[>l/T,oXo3yz>W{Wrzmyd3^MǚucWNWz>}V#͓-go[vF0"iͬA] 9

%PDF-1.5 % 7 0 obj > stream xP(endstream endobj 9 0 obj >

https://arxiv.org/pdf/2303.12712v5
stream xP(endstream endobj 11 0 obj > stream xP(endstream endobj 17 0 obj > stream xP(endstream endobj 20 0 obj > stream xP(endstream endobj 23 0 obj > stream xP(endstream endobj

%PDF-1.7 % 1 0 obj > stream xN0E|,#oʎ+MF

https://arxiv.org/pdf/2608.03833
SJ%V{ǖ!!8D e1"B Q@1oV+` rf^ I !lkmǩf0KXbp$Q #t3SBF'=o2ehvUzk]p+|)g{&61yny!sykZS?==ZU*\>zhj쁶gO-͔D`+m\

[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

1 Introduction

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

^ce]6m۬mRUi۶mfm۶m۝u;?^s\cX{X{

https://arxiv.org/src/2006.02893
mckkZ#M{2sHBmH} EG{];;kk3+K( -3韲 (zk=3(nn(:9;kG}C; ]}CQY9%C;{Sk+FZ&Zzşrⲿ8 a- tmLL) uu (9{i)xy Fft҆V&L":QS

%PDF-1.7 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > endobj 4 0

https://arxiv.org/pdf/2608.03437
obj > endobj 5 0 obj /Dest 2814 0 R>> endobj 6 0 obj > endobj 7 0 obj > endobj 8 0 obj > endobj 9 0 obj > endobj 10 0 obj > endobj 11 0 obj > endobj 12 0 obj > endobj 13 0 obj > endobj 14 0 obj > endobj 15 0 obj > endobj 16 0 obj > endobj

%PDF-1.5 % 15 0 obj > /ProcSet [ /PDF /ImageB /ImageC /ImageI ]

https://arxiv.org/pdf/2101.00190
/XObject > >> >> stream x+TT(T0B K33 3Tp> stream xw$U/aIWTDE3Q aq9g]̺ݼauװ-9vx|S'= @ @ @ @ @ @ @ @

%PDF-1.7 % 1 0 obj > stream x\YoI~_XUyglhu˧d[D

https://arxiv.org/pdf/2608.03086
\X7ьO*ezl,d mY50ymȋ,aYʘ8 xAf_14g%cxU>ob쉬f 9돱ncsO{(g1

%PDF-1.5 % 91 0 obj > stream xڭ[YƑ~ׯG#) 6h$Hv4P݄h

https://arxiv.org/pdf/2006.01402
%&:2)nc7nnb*1oW^7vViA*᥂òݼ_HY%r(eg^JfcC3hv6bERՆ~>(^oJ8aO[Z>singny+MyC v98ՐOgr4cPŔg `7Llz

%PDF-1.5 % 162 0 obj > stream x[KƑϯ`"vD7:#Y5hD

https://arxiv.org/pdf/2407.00132
+fuIU],c`*uSmY:) ¬&:

n^}ٰ1FQ9nJU. M=$ssw#;qDĖ"K v

https://arxiv.org/src/2006.01318
Joŏ3ND(m79f=|'_Jk,vn֊=ve^I7&R>s^VFM_^N˝Va>&DSe~pu㠚YԖ:khlq^N9ᵉ) #kAꃃ- *+ۉ}TW31n- ovLAU{E*#SE)FA@D* ԘFW8ž$w[%OMdEjF礓Myp

%PDF-1.7 % 1 0 obj > stream x}Mo0 H =΃ 8(

https://arxiv.org/pdf/2608.04008
o@,mU*[h/x?pwX_ba]n:,P5%\yC@?g{hu.ir |OY, =;]asg~CWj\Fՠ)%^Mϧ;0|rfWy+Μ,v#6pmY)gn)+x*TEfa)8{W=֎$}J+뺰*(\[Y;> endobj 14 0 obj >

%PDF-1.5 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream Event

https://arxiv.org/pdf/2508.07408
-Aware Sentiment Factors from LLM-Augmented Financial Tweets: A Transparent Framework for Interpretable Quant TradingYueyi WangQiyao Weihttp://creativecommons.org/licenses/by/4.0/q-fin.STcs.CLcs.LG endstream endobj 4 0 obj > endobj 5 0 obj

%PDF-1.5 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream

https://arxiv.org/pdf/2412.20138
TradingAgents: Multi-Agents LLM Financial Trading FrameworkYijia XiaoEdward SunDi LuoWei Wanghttp://creativecommons.org/licenses/by/4.0/q-fin.TRcs.AIcs.CEcs.LG endstream endobj 4 0 obj > endobj 5 0 obj > endobj 6 0 obj > endobj 7 0 obj >

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

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

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