Web This site Trusted
30 result(s) for “okapi bm25 site mt shortage blogspot com site:arxiv.org” of 38 matched · 380 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)
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
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
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
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
https://arxiv.org/html/2407.16741v3
com/All-Hands-AI/OpenHands
Slack http://bit
https://arxiv.org/pdf/2608.01785
+1}$jdKmotubUQHF8B!0Ή"X rbdZJ ֜PAJb%; HIF(2fa@>$@d`#!*M }'3A1ǂ*sX ,҂Kf3jxxD""S l0H*Ǹ #3QD8,$BB(M6n0cDfDs
https://arxiv.org/abs/2608.03883
Our systems combine sparse BM25 retrieval, evidence-aware rescoring for self-referential symptom reports, embedding-based reranking, query-prototype expansion, and LLM-based reranking
https://arxiv.org/abs/2104.08663
Our results show BM25 is a robust baseline and re-ranking and late-interaction-based models on average achieve the best zero-shot performances, however, at high computational costs
https://arxiv.org/abs/2608.03860
The pipeline combines sentence-window chunking, BM25, BGE-M3 dense retrieval, reciprocal rank fusion, optional cross-encoder reranking, and grounded answer generation
https://arxiv.org/list/cs.IR/recent
IR)
Tue, 4 Aug 2026 (showing first 34 of 45 entries )
[17] arXiv:2608
https://arxiv.org/list/cs.IR/new
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Information Retrieval
New submissions
Cross-lists
Replacements
See recent
https://arxiv.org/list/cs.CL/new
We evaluate five open-weight readers with Vanilla context, BM25-RAG, Oracle retrieval, Memobase, and MemSearch as memory backends
https://arxiv.org/pdf/2608.00458
~ ޛ͝ٽ_L۶h*|:6~rxU/Ӏ:_A)7 SM:[*RO{M |k+u"rB cYCZe[A:ミ > stream xmTn0CƆ@LE" h
https://arxiv.org/list/cs.AI/new
Skip to main content
System maintenance August 4th and 5th Learn more ×
Search Submit Donate Log in
Search arXiv
Press Enter to search · Advanced search
Artificial Intelligence
New submissions
Cross-lists
Replacements
See recent
https://arxiv.org/pdf/2410.15608
&Bm%$O뷊Um'3@EQ$]dݾ6"܀z'7pwJ\Υ"M7Ʉ*|L~v8ԭ(?y?lwgz:&]O/?[yyfiҗ H RCR\ I S㘻o >)5mƈTrSm( y gy7^\(qOw"-RE3|
https://arxiv.org/src/2608.04007
Iiz45`&"/"s?}ohJBNy@;:){ %7I Ə, z$j4&A$K" "BE̎ M4I 8 \([HE4豄)I)M99-1N} vkV̹=yN tg_; /)+MHx5wծ}m3 owBVd
https://arxiv.org/pdf/2006.01354
5 % 5 0 obj > stream xmTˎ0+$$0 a#A%߯jD岻fc;Z̫MfG} q]/ޭmޯo⣩0Z^x]fkn{E+{*ʧypg6;5PVpH8$hmڢ*߄zR:")3qXysO'H)-"}[˺s 3 4{pYdrK+ a }ѫW{ Fvm7344AGc ڤ_86endstream
https://arxiv.org/src/2608.03966
Γotuϐ ɋv S;;{ >2els.Ƨ{+7vlھ[ȭDOӘ:|*qϻY )5S6U5yGOYt1Tkuձʯ "DZ^sV7B 負2FXwlܰ\[T%hcLyZ5?2]ᴂ)*
https://arxiv.org/pdf/2608.02943
q]o{)W^G~e _ DqAv3 ~ ƁGQ adw0 Y ^lw"`@/eD{Qh 3'7ʽ[H lmtU2m~aPPp8G$ mĄ 3">pOKt_
https://arxiv.org/pdf/2608.02918
Vʥ_rW"B_,xp rI23F0͠0SrV+\1˄ ΄mLB +Щ?Q I(i,(,-J )$f^b4Ɨ"ŔL"1UbP@[ s "i+4)"lIWieL$?Kˋwء{_mfT:}[9y_kouk?즙6U9;;
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
https://arxiv.org/pdf/2607.26405v1
ӣc> stream xmTn0C6*drضj^pHA@Cfy'n`g#govh/}eg羋m=Oo ٽ[uRۉ=Iۏw{VQҜ8ߛIߞ3 d_ ~~hZ# W c *'qU;HHV7xwuɻa;zopO_`_ݥNd0 m6G_
https://arxiv.org/pdf/2210.03493
=ܴZ3/HQO\SY,mT(YSEO$U7B$=H$ r E*`(T3 (wFH #MO8\02a[r &8 Z\f] _`@^>O4)_ |0mէO5O x>SIc$12_ۣvKht7}zYP
https://arxiv.org/src/2006.01048
uAUMM@gM`tؔ@Pк*Ӳ_e ۭ L Cٻ7M,i && mT,%v]^4}}vF]b~Ӵ D Dv)*"wGӂob2 {Y'qpPTp\
https://arxiv.org/src/2608.04008
4H"%`H $̉Sϼg^o5Grrk^{G} +B5/Gz_q%riJU8 Vvl EF aaQ?:)666¢#~qoy%p:|pGbm8gȉ#'d`H芨#q낤ew yqBqu
https://arxiv.org/src/2005.13905
j'fUsϲ1B5mQZRGpq x4ڰ6hҟ=U EbRg#h1Tgr6:RS} Mt)K2}$۱O[Bʇv=GHyB:VimhSw{O\
https://arxiv.org/src/2006.02893
mckkZ#M{2s HBmH} EG{]; ;kk3+K( -3韲 (zk=3(nn(:9;kG}C; ]}CQY9%C;{Sk+FZ&Zzşrⲿ8 a - tmLL) u u (9{i)xy Fft҆V&L":QS
https://arxiv.org/src/2506.01844
(Rvv۪3~ɋޞxo!gp?np QJ݃ f=ur{ҔPWxN ,_z=HNZ$Y0 ɼZ3 V; &,/vrFagW7z " gWҝY 4:|ԓy`"ņfA퍫+ k?a:vYR-"z )0A5
https://arxiv.org/pdf/2006.01128
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
https://arxiv.org/src/2006.03318
hԎDtbG aU&mtA'd 6 +B$2tFG OIo|؈|IP
https://arxiv.org/pdf/2508.02691
7 % 1 0 obj > endobj 2 0 obj > endobj 3 0 obj > stream Statistical modeling of SOFR term structureTeemu PennanenWaleed Taoumhttp://arxiv