NishiSearch

Web This site Trusted

30 result(s) for “okapi bm25 site terms com pp site hotchips pp site doi org site pay nid nl site:arxiv.org” of 41 matched · 609 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
2 pp, exceeding MemSearch reader scaling (+10

%PDF-1.7 % 1 0 obj > stream xXM8 ]4Pn~L-E

https://arxiv.org/pdf/2205.01882v5
/)3j}{u~Th+oF^ Y $P|z)[RZw[ƒtzJCva/+uÀFazAtZ_^|[N]|f5=]8`mh/7Ku^]vK{;\o-n۫IL:tM٠h`|nlM

%PDF-1.7 % 1 0 obj > stream xWM6W[H֦-T

https://arxiv.org/pdf/2608.02758
@۬MXT`)iI}= go)p” 9I" ͸"PZ AJBE&BZ@ae00)SV( )+ gH 0Jx cYfq;{~7zy:Zgޝi{c,c%Л*Ӂ`VNWwL/fW2}(^tu0}efY]3Co+iY/ڙg=nr\p֘EBp

W{s6_*"؎-uvu:4 I@8]DI4

https://info.arxiv.org/help/econ/index.html
@  B+әU`Q W+Crqmr`\y$7kgnnIDL nE5AIxm\+b%V@zB&QM:mKYF㭸ql5

rj;srY9靟OO߰ޟ4'}Ʊڅ'o1d{l

https://arxiv.org/src/2608.03883
lއxG&JWXԴ&[v @V[uԇF7vz%N`pP \>$kb {K/05 U0[|ʋXcc S-bQEAE

%PDF-1.5 % 27 0 obj > stream xڍZYܶ~GNwّQVR)X3,

https://arxiv.org/pdf/2006.02759
Aj gkip4 t7Ǜ߅w~(Wanp_M,`n( ԨQ7 =: &━H!%II dH8f9(\45'U`NVG}6٣e k1KIz"SnZמDYFJ̘`6&D0[s ^{A(+$D2idv_E qw

%PDF-1.5 % 138 0 obj > stream xڭYK6ϯmՀ[7|Ix1MN

https://arxiv.org/pdf/2309.08431
тppJCyS N*ɸkg

%PDF-1.3 % 3 0 obj > stream x\rIv}W1*vTElͱ&;

https://arxiv.org/pdf/2407.01722
y( Y hܛKPT7A[DeVͻoOo`(N44 +,(qEEl߃V2Fx`t|Di8e!#I88/(4Me[DMo$`> \s@: $HɻW?, +a~s``8*M5?k`Cyߚ9`

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

https://arxiv.org/pdf/2608.03883
org/pdfua/ns/id/ pdfuaid PDF/UA ID Schema internal Part of PDF/UA standard part Integer PRISM metadata http://prismstandard

%PDF-1.7 % 1 0 obj > stream x\[s۶~?t7ٳg'idI'

https://arxiv.org/pdf/2608.02935
0rFBLS^C#)^ku7qy dZ1% rF>2tK0(OB{յ;7]  GJӽpM Gpp-dR-|qd

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

https://arxiv.org/pdf/2508.02691
Statistical modeling of SOFR term structureTeemu PennanenWaleed Taoumhttp://arxiv.org/licenses/nonexclusive-distrib/1.0/q-fin.ST endstream endobj 4 0 obj > endobj 5 0 obj > endobj 6 0 obj > endobj 7 0 obj > endobj 8 0 obj > endobj 9 0 obj >

%PDF-1.7 % 1 0 obj > stream x}Qn0+Ǝ_ BR>NC,)$1}

https://arxiv.org/pdf/2607.27070v1
IRGsro>tJ~~z|AOρ{U+(>[c;JA[/0Ҁg^9xӁwVo9ѳICÁ`xG]򩾥WW6W'vѴ>/+ڀmƷޝE{11E-Lw6 ܿ]_qеDuykG $AbpPЍkZ_E8JVkj&}0*V: HH

rj[rFϿ#!Y|X=J9W+Cr,@0I\S$8

https://arxiv.org/src/2608.03882
I[[٭Z#35==5Hү~Oo9o|_>?8}/i|JmB,3?g!,";P\>3MӥG&;&y+NכDBLBFw?v-\FB,%]; DJ{jt"l,\%T'&9 $X7o}~ BҎnoOyMq

%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\

%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

^xTAd $ I-iH $HHݝll ;VH

https://arxiv.org/src/2006.02924
LdȀ 2\DrxK%CLPñ`%$+1hkW2 N "u 5GB48b >7:ˠvp1,B5B}(Y^:X SA3Z6$à@n*¨C%YINL

Z:0f\r8nٙ9kNvn\l'?b+dL'1I0$(KѮD

https://arxiv.org/src/2402.03300
p #ϭ(~ NNlIJt‡ĴaxXYBkwM'+q 63w9(%(Nut=Etަ

Report GitHub Issue

https://arxiv.org/html/2608.03063v1
8 pp in a production fraud detector serving billion-scale transaction traffic

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

%PDF-1.7 % 1 0 obj > stream xX]s6}_G{;o`IԱ;}`$Xf

https://arxiv.org/pdf/2608.01657
#D9q~ 2zF#Q܃ $#Dj"UH¨&0#&\PbX" NhPJx(#.)'ZB1~$BWKBCn! 쬀_A0? ~!. fRl BP.Lp8 OjT ._`0 r P( VZZpi!^H4 Hpe%Hl-`

%PDF-1.5 % 2 0 obj > stream xmTˎ0+$$0  a#A%

https://arxiv.org/pdf/2002.02145
'뭭:=F`=t+T+&k =jbLRmQ+[jݰ#=x"a]+xZ\Oc-/YTMG·Znlte8;I @Sq,e" ˌu%8mie

%PDF-1.7 % 1 0 obj > stream xZkS:B"d[nmH&d+ef

https://arxiv.org/pdf/2608.00028
ffLl!i[,1$JOKj>j,K0󘐊LD>SL*u]2ϑ,b^ p`JT?bc+Y$K(ğc,fm5bXMVrXOQڊ x So+j,FWHSQ`+ҝ_e+ ݖyQR1 K>LEˆi!l-vVXݸH2 'vq.Wy8͢vr

%PDF-1.5 % 4 0 obj > stream xP( endstream endobj 7 0 obj

https://arxiv.org/pdf/2006.02464
> stream xP( endstream endobj 9 0 obj > stream xP( endstream endobj 11 0 obj > stream xP( endstream endobj 17 0 obj > stream xP( endstream endobj 20 0 obj > stream xP( endstream

The Last Costly Signal: How Generative AI Collapses Competence Signaling

https://arxiv.org/html/2607.26327v3
4 AI disclosure, trust, and willingness to pay 2

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

https://arxiv.org/pdf/2608.03086
[H5I__D$ɬ*.{fV2+ψ/"#"lTҍSNYW*ཊ*6^%ب(m,ҮFb_4wJz1;>/?}XUoKAUG?1>Ϗ&_ގhJa_lIhF]05JF(md` -*Pb4Wr~>8:|z޵ׇuA%5ϵ^jnTY4 eS*

%PDF-1.4 % 5910 0 obj > endobj xref 5910 359 0000000016 00000 n

https://arxiv.org/pdf/1802.07228
0000016651 00000 n 0000016817 00000 n 0000018950 00000 n 0000019067 00000 n 0000019192 00000 n 0000019395 00000 n 0000019510 00000 n 0000020692 00000 n 0000020873 00000 n 0000021345 00000 n 0000021891 00000 n 0000022501 00000 n 0000022626

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

https://arxiv.org/pdf/2407.00132
Pvͬ*Tഴ@*_f%& Qnʤd܈&K2%6Ϳm3͝4I]=Cj>Uz=қL|KH7gII7{&MTYlmFjކfwqueŶT{zƕd:ZcdzVE3`]Ano3@r)+/Ԭn`kYfy

[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