Web This site Trusted
30 result(s) for “okapi bm25 site www eyespy cy site www is gov site consumer fjc gov site do site:arxiv.org” of 39 matched · 691 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 www eyespy cy site www is gov site consumer fc gov site do site:arxiv.org?
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)subscript�cos(\varphi_{\text{cos}})( italic_φ start_POSTSUBSCRIPT cos end_POSTSUBSCRIPT ), Okapi BM25 full-text search (φbm25)subscript�bm25(\varphi_{\text{bm25}})( italic_φ start_POSTSUBSCRIPT bm25 end_POSTSUBSCRIPT )
from the top result below
https://arxiv.org/html/2501.13956v1
Consequently, additional context is required to provide out-of-domain (OOD) knowledge and reduce hallucinations
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/list/cs.CL/new
Many practically important problems are naturally treated as black-box optimization (BBO) problems, in which only objective values are observable, and the functional form is unavailable
https://arxiv.org/pdf/2604.05327v4
[5ÝŽ¤öÌä×/@Qj‚z8¹ŒÜ ~ø ’ 4‚L2/˜b\¦™P3LxÃ,“F1Ç”¦YJÞ@†róO(Œšï‚Ò±‹üc\°-Oû¶úÚ‰Bõé¹i�`÷VÝòSszmŽÇ Tı>¡ïúôBÃ}וŽ]G®©Ï—öÜt‹æXwݹÚÕÏõnŠÉÕnן*î�ÜWÏ€pÔr©V{ìú¶9½à¤K.m¢¼²Ž ê™OM»/ 2мUm[•»Áý0¼oNýîµzEáëãùPƒt�ÇU/:6Š£Ú7÷ÔnWW§] 0¥x‡†u
https://arxiv.org/pdf/2607.28577v1
0/mm/ DocumentID URI internal UUID based identifier for all versions and renditions of a document InstanceID URI internal UUID based identifier for specific incarnation of a document VersionID Text internal Document version identifier RenditionClass RenditionClass internal The manner in which a document is rendered
https://arxiv.org/pdf/2210.03493
T÷×ï98$%9�ñŒ@\pnßù 'Á.H‚÷W_¯ü&� iI¬Û«û‡$Ø@ÿ¯A«ª žÝ¬6Hó~›àöêÓUÂ2¾÷»�œVY,²%½Šó\ÉÌ .šnÈ/Y‰¸Êe°Êdœ‰ Ç~ø¥Á¿zØöÓÅ+ØaµØâ§»«Þ‰$*”’wÛ@ĉ\§Èâ äßµÁ}ø®ÞdZ†âÇh¥D~1C¿ºÝ÷ãêm‡CUxÿ[¤²°ÿ_Ýjê0#ÑMü†Z2‘ò�š$Yr´u·£¹ãž7øCJucÆDYZê
https://arxiv.org/pdf/2608.02978
2831 0 R>> endobj 2 0 obj > endobj 3 0 obj >/ExtGState>/ProcSet[/PDF/Text/ImageB/ImageC/ImageI] >>/MediaBox[ 0 0 612 792] /Contents 4 0 R/Group>/Tabs/S/StructParents 0>> endobj 4 0 obj > stream xœÅ}Ys7’î»#üøÈ3a–[-wŠÐ:ãÓ«Õ·¦ç�i‰Ó’¨‘
https://arxiv.org/list/cs.AI/new
, the meaning of a customized field) originates from users' domain knowledge and is rarely documented publicly
https://arxiv.org/src/2006.00441
§ ¿¾ÖÎØ°¬«çZß%~èïP¥ñ Í3(Ò¹•HLÏIVq€ÚKì�àÇÀÄáéëX©;G$ïsÚ`cYî¶1
https://arxiv.org/src/2006.00064
¹;wÛ@0«�“¸ SÁûÂü…Rqâ\ë«h‚Ü�r“nË@«1 ‡Ž)C|”ŠÙ9ø_IZhÅ,�T@OúÈåm4›ñD3žþ¼G%3…&3SÎB+#͈ä˜EˆŒÆcÄ©Z]Fõcy„ —‚“‘g®uÇ \gn;¨ôȳ¹8q%���
https://arxiv.org/pdf/2608.02976
2784 0 R>> endobj 2 0 obj > endobj 3 0 obj >/ExtGState>/ProcSet[/PDF/Text/ImageB/ImageC/ImageI] >>/Annots[ 18 0 R] /MediaBox[ 0 0 612 792] /Contents 4 0 R/Group>/Tabs/S/StructParents 0>> endobj 4 0 obj > stream xœÍ}[s¹‘îûDÌè·Cnˆ¥Âµª"Š�F
https://arxiv.org/pdf/2006.00064
ìËZeÁIsÙ�7N¨•Ã\/I'H~r|Üm�Ÿt;ççù¯ÎäyuÓ¶ë¿åùýý}6_´7›«lZÝå‹«»|*ÅëѪ+^�ÖCñúÍ€b%zf«bÖuQ1=)ÚÃ,Zó—þ¿ Íé�Z¿ Í{”šÒôû,9»×Ìî{¢ìo‹è[¤ÿŒ6S -¬„ “l–RÚÃc{Næ'�_#vwA®axáZ áqòŒK‚Ð^ñp‰�qâ1‡ƒÎœä]äc¹ ∑õ_•Å"èíÙÃ
https://arxiv.org/pdf/2210.00185
ŒØÂØ’+É“¦¿~Ïá9´)Åšd²‘4ïÜü~“J�ã+DIÿSfµ –";óÃA.þÖÞüÓþWÖÛSW-W™Îùír¥DžüëóRš¤ê>×Õ23É#ýÚ>ÐwØqõ¾:Ô«£ëÜ¡ºzM…‡Ó~¨×¢ì±kÇ¡ÚpÓÎÕMÝlSçƒ[ïÆ?PÎ5\ßÿÿ¹ýÉ uÛPyÝôƒkÖòÇ_¶'@TÍPUýÜXežf9�õ€ÞF>y«R„Ò`k– ë[úÅm.8(ŸÌ£T¯Ãª„>¡ HªÞ³rÝÜ)„N³Ü¤RÉq§dý
https://arxiv.org/pdf/2608.03709
IL‡–óë¿%[&¾ÅÐÎ0$ÞÚ–Ö^û&)‚YÌf\I&™-s˜Ã}æ2×w™bžÌc¾ç0Ÿqn[ŒãOØŒÛÊÅãŽÐŒ».ž%ãžt÷üs™°|0!$”âá"´!Üae/\¥ãš¯Ñ$™®à:™ŽýóOíÍÁÑÅU§‚ö2|Xÿ&Z!«`�¦,ok7ƒ=8èí_°ýxñ¤ðU�X¯Š‘ÙŠU´`ÍXïzwÝÓ‹b�“`ö»ä:¿K®Ý˜7^u>Ÿ^ìöûÇ( ¾í Ðà¶ì«Á µªdµÆ…0\6
https://arxiv.org/src/2006.03720
*�[>Ž¡OæÁpOè »Å©+�°¿Cyk„Ýé÷aò :‹ëºA“ ÃÜj48¹D}Êu‚ng�×&\Ã…¸ˆRceeIÛøø…”sc)ªÕ'¥"�Cæ[»±– ¤å/ò,Ìziw ¿iôy©Š§¼h>f&%+Z4WŸ5ÀýU˜`g öxŽ`iå‰ Ÿ–ÅXÉxöußӜbÎÜSó›{ò= 3#²lF±ï•Ý#ì4>¼EeN:Ä�^2�6Ê;JJÅm«}ÆKË%‡´˜9Êž
https://arxiv.org/pdf/2407.00215
stream xÚÓÎP(Îà ýðendstream endobj 11 0 obj > stream xÚÓÎP(Îà ýðendstream endobj 17 0 obj > stream xÚÓÎP(Îà ýðendstream endobj 20 0 obj > stream xÚÓÎP(Îà ýðendstream endobj 23 0 obj > stream xÚÓÎP(Îà ýðendstream endobj
https://arxiv.org/pdf/2303.12712v5
stream xÚÓÎP(Îà ýðendstream endobj 11 0 obj > stream xÚÓÎP(Îà ýðendstream endobj 17 0 obj > stream xÚÓÎP(Îà ýðendstream endobj 20 0 obj > stream xÚÓÎP(Îà ýðendstream endobj 23 0 obj > stream xÚÓÎP(Îà ýðendstream endobj
https://arxiv.org/src/2006.01598
IK”Ö¿l÷¹÷Æ®ªE‘¢ô�)Qä_¾~ÿú¿óî§oÿéÃßúæãë¿ý›üFþK)´?忇?mòÉÄôo¬OÉ瘓—vÖÛdþÍÌÿ¼¨ÿ~ùðñë÷øÃ¿yÿîÝÇgí^‚ÿÿéÿE¾ú}ýüáÿõúý‡7ï~úÒ~öÏ?ýüËÇ/í—ÿî˯þÛùõ«ÿøæ‡~üú§Ÿ¾ú÷¯?¼ýøî篜±ñÿå?ÿ§þÃýå§×Þ¼þé«¿t1º“p¿ŽÄ?ÿ‡ÿð>¾ÿú§úæ‡w ÿûûwß½ÿúÇ?
https://arxiv.org/src/2006.02833
¾÷¤5~°Ð Š=>'ÔŽG>Ïßv´�˜oþœ‘õ•QûÀŸ›vS;Isâöx“Gb½U«mzÓ\vÙ&£$àóáìZv|ÎÍH‹tÊòÔ�£ÍLU^’&9>`޵%X M$‹#$ƒ}$ƒgzyî¶ M ؉ pܾ·àHÛý��
https://arxiv.org/src/2303.12712
ýÊù‘èÖœ µhË7X¾I ë‰@ö»þ{=œKL*óì�ç1‰‘cÝSXƒÝBSЉßÕjŒäß+ŸÈý€ ÛÛÛî6�“µ�ÕÞ(Ja'3³œÒÒ:[e8#ø·” ozb‚J§áëW—ÑLqŸcy™\3r8ÃóȆ«�4ûö»¿J L¬á2ÿN$Brd9Öר>CPÓf²6-Ïkú;N:
https://arxiv.org/pdf/2407.00132
P ¨vÿûͬÌ*T�à´´§½@½³*_f%ÓÍÓ&Ýüðæýý›·ßQnʤÌd¶¹Üˆ´Øä&K2%6÷ûÍ¿·ŸÎm3êýÍ�4é¶ùI�]ß=ÖCÝíjú>U§zà=üóÇÒ›L¥¹ùÏýßÞ|¸óëKH7‚g”I¡³ÍîøæßÿI7{¨øÛ&MTYlžm³ãF•Ûj÷…Þ†fwèêqÄueŶêöTî{þz®‡¦Æ•d:ZcØ„‡Ç³ŒVE3ë`æ]–Anüo3½Ü@r°)¶÷+¶/Ô¬n`¨ÁñkY†¤fy
https://arxiv.org/src/2006.03318
€†Öa¡Ì^'èæ¹ŽêÎ8 H @÷§IS‘H2a]"ÐŒÛCš˜0‘MJ
https://arxiv.org/src/2005.14165
ÐïEzè;ð:±×-ï«W¥^°uÕääÿÂz�ä(l�²£Ø sþ‡ÚìÑÙª®1Þ·uWÎ4ð=¨;Çef„þs@àz¶ÉØ™s�߯c׉�âݶ¡}¯‹éEÚïìO_t=ûkûê~�Ÿÿ/#ñ±�RÂgó›3@¯ñÿ2Øû‡{ãñ°ÿïh÷‹ÿ÷³üHZ“ÅX´ø læ‚XLA«6�lâÂMiåf&°cyÇ;D}5k"PrÐë©öy×»^-´5�ÜÝ·eºbx ƨ ã´È¬>̺ളŒ³Ã†„\Ÿ‹Çí
https://arxiv.org/pdf/2006.02833
ŧ^ÒaÈ™Qš¡„ÕᛀpôÇ Gæò1ÚÏ'g‰ =|Ü@ÒŠé�_¿ƒt—_üi»íendstream endobj 208 0 obj > stream xÚ�YK“ܶ¾ëWÌ%UÜ* D€oeǶ’ØŽã�œŠ¼Î»Ã,‡¤×ë_Ÿ~��Wöeh �F£ñõƒáîaî¾yÊÿÛÛWo¾ÖÉNkU$‰ÙÝÞï²PåiºË’B…i¾»v‚ﻟ~üÇÍ>ÖiP•Cy(�uÜý%LÂ÷7¹ º¦²ý¹ë‡›»Û¿½ùÚè]¦Š,ÔÈR¯8Ëv±Š¢‚9æžÛ>Þ$IPž‘u^vàÿ²QÀÓ˜àƒ6wL:vm5[a7ìo^šúl[ÜppâÑÐ~€í3Om—{T–Î,É07N
https://arxiv.org/src/2006.01318
[lñ‹QAcƒ5„ÿ)o›ÙÙ�æKþ/—ÂÝîÌ[ž÷éím±sÛr^!“Œç�®�¾“Ÿø4¨�þ…ŸÐ¿u�ƒëk6ªÔÏ4 j„Ïkë7²j¾›å ~ÞÎYÖF9ÏË÷ôÜú¾ÿýiö�DÞõ2óF+D(6§ì'5¾Ö¢?�U4û…ùø$§�³SÖ$'ßéåæúÅX¬b^sK«üÜê7iR¥5*—hwóðb!ç‡Y£¬ ?”%¼ŒïúyßòZ-Ûò�œëÐïðyÞr’VÊîvr¾•o·óVÂÎXÙœ—p|
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
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