[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-82788-en":3,"doc-seo-82788-105":30,"detail-sidebar-cat-0-en-105":91},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":20,"is_deleted":4,"is_public":21,"is_downloadable":21,"audit_status":21,"page_count":22,"language":23,"language_code":24,"site_id":25,"html_lang":24,"table_of_contents":26,"faqs":27,"seo_title":13,"seo_description":14,"update_tm":28,"read_time":29},82788,137441390410,"Hazel","https://ap-avatar.wpscdn.com/avatar/2000252f4ab5702993?_k=1776741390130283984",8,"Research & Report","Submitted and Diagnostic Analysis of Full-Text Temporal Retrieval for LongEval-Sci","LongEval-Sci evaluates scientific retrieval under collection change, requiring systems to work on the current corpus while remaining effective as documents accumulate over time. The paper presents official Task 1 results and development diagnostics for LongEval-Sci 2026, comparing BM25 and dense baselines with additive/router variants, temporal full-text retrieval, temporal+citation retrieval, RM3 expansion, cross-encoder reranking, and RRF fusion. Temporalized full-text BM25 achieves the strongest ARP and best robustness across snapshots, while citation evidence needs cleaner ablation and calibration.","Submitted and Diagnostic Analysis of Full-Text Temporal Retrieval for LongEval-Sci  \nLongEval-Sci at CLEF 2026  \nHaijian Wu1, *,†, Yingdong Yang1,†  \nAbstract  \nLongEval-Sci evaluates scientific retrieval under collection change, where a system should be effective on the current corpus and remain usable as documents accumulate over time. This paper reports both official Task 1 results and development diagnostics for LongEval-Sci 2026 . We compare the official PyTerrier BM25 and Qwen3 dense baselines with full-text BM25, additive and router variants, temporal full-text retrieval, temporal+citation retrieval, RM3 query expansion, cross-encoder reranking, and reciprocal rank fusion (RRF) . In the official DCTR evaluation, the temporalized full-text runs are our strongest submissions: FT BM25+temporal and FT BM25+temporal+citation obtain the best ARP on all three snapshots (0.285, 0.267, and 0.180 nDCG@10) and reduce snapshot-3 relative change from 0.481 for the BM25 pivot to 0.368 . Citation features match the temporalonly variant but do not provide a measurable additional gain in the official summary. Our internal snapshot-1 diagnostics show a complementary pattern: full-text BM25 is the strongest single development retriever (DCTR nDCG@10 = 0.3302, MAP = 0.2853), RRF gives the best deep recall (Recall@1000 = 0.9667), and some uncalibrated overlays can sharply degrade top-rank quality. We therefore conclude that full-text retrieval is the strongest foundation, temporal integration can improve official longitudinal effectiveness when applied to that foundation, and citation evidence still requires cleaner ablation and calibration. Beyond ranking, we also report a qualitative weekly IR-system update-monitoring analysis based on ingestion velocity and stale-coverage drift.  \nKeywords  \nLongEval-Sci, scientific retrieval, reciprocal rank fusion, temporal reranking, citation reranking  \n1. Introduction  \nScientific search collections are not static. New papers are published, metadata changes, citation links accumulate, and terminology shifts as fields mature. A retrieval system that is tuned once may remain strong under one snapshot yet become less reliable as the collection changes. This is the core motivation of LongEval, which frames information retrieval as a longitudinal evaluation problem rather than a one-time ranking task [1, 2] .  \nWe study LongEval-Sci 2026 Task 1 from both a ranking and a maintenance perspective. Our main validated ranking result is that temporalized full-text retrieval performs best among our official submissions, while the snapshot-1 development experiments explain why this result should be interpreted as calibrated use of temporal evidence rather than as a general license to boost all recent or temporally favored documents. In particular, we ask: (i) which submitted systems are strongest in the official three-snapshot DCTR evaluation; (ii) which reusable lexical, dense, expansion, reranking, and fusion baselines are strongest in snapshot-1 development diagnostics; (iii) whether publication-time and citation overlays add value beyond full-text lexical retrieval; and (iv) what simple collection-drift signals could indicate that an IR system should be refreshed.  \nOur contributions are threefold. First, we analyze the official Task 1 results and show that FT BM25+temporal and FT BM25+temporal+citation achieve the strongest ARP and best robustness among our submitted models. Second, we compare official title+abstract BM25 and Qwen3 dense baselines with  \nCLEF 2026 Working Notes, 21 – 24 September 2026, Jena, Germany  \n* Corresponding author.  \n†  \nThese authors contributed equally and share first authorship.  \n$ [willwuhj@gmail.com](willwuhj@gmail.com) (H. Wu); [yingdongyang0305@outlook.com](yingdongyang0305@outlook.com) (Y. Yang)  \n􀂀 https://wijowill.github.io/ (H. Wu); [https://github.com/yyd859/](https://github.com/yyd859/) (Y. Yang)  \n􀀚 0009-0007-0311-6235 (H. Wu); 0009-0007-5546-5293 (Y. Yang)  \n © 202","cbCaiaAh96EyW1SV","https://ap.wps.com/l/cbCaiaAh96EyW1SV","pdf",804159,2,1,15,"English","en",105,"# Introduction\n# Related Work\n## Longitudinal IR and LongEval\n## Scientific Retrieval Baselines\n## Fusion, Query Expansion, and Reranking","[{\"question\":\"What problem does LongEval-Sci focus on for scientific retrieval?\",\"answer\":\"It targets retrieval effectiveness when the collection changes over time, so systems must remain useful as new papers, metadata, citations, and terminology evolve.\"},{\"question\":\"Which approach performed best in the official DCTR evaluation?\",\"answer\":\"Temporalized full-text retrieval with FT BM25+temporal and FT BM25+temporal+citation delivered the strongest ARP across all three snapshots and reduced snapshot-3 relative change versus the BM25 pivot.\"},{\"question\":\"Why does the paper question the added value of citation features?\",\"answer\":\"Citation features match the temporal-only variant but do not provide a measurable additional gain in the official summary, and internal diagnostics suggest the need for cleaner ablation and calibration.\"}]",1784182940,38,{"code":4,"msg":31,"data":32},"ok",{"site_id":25,"language":24,"slug":33,"title":13,"keywords":34,"description":14,"schema_data":35,"social_meta":86,"head_meta":88,"extra_data":90,"updated_unix":28},"submitted-and-diagnostic-analysis-of-full-text-temporal-retrieval-for-longeval-sci","",{"@graph":36,"@context":85},[37,53,68],{"@type":38,"itemListElement":39},"BreadcrumbList",[40,44,47,50],{"item":41,"name":42,"@type":43,"position":21},"https://docshare.wps.com","Home","ListItem",{"item":45,"name":46,"@type":43,"position":20},"https://docshare.wps.com/document/","Document",{"item":48,"name":12,"@type":43,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":43,"position":52},"https://docshare.wps.com/document/submitted-and-diagnostic-analysis-of-full-text-temporal-retrieval-for-longeval-sci/82788/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":24,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":41,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-23","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71,77,81],{"name":72,"@type":73,"acceptedAnswer":74},"What problem does LongEval-Sci focus on for scientific retrieval?","Question",{"text":75,"@type":76},"It targets retrieval effectiveness when the collection changes over time, so systems must remain useful as new papers, metadata, citations, and terminology evolve.","Answer",{"name":78,"@type":73,"acceptedAnswer":79},"Which approach performed best in the official DCTR evaluation?",{"text":80,"@type":76},"Temporalized full-text retrieval with FT BM25+temporal and FT BM25+temporal+citation delivered the strongest ARP across all three snapshots and reduced snapshot-3 relative change versus the BM25 pivot.",{"name":82,"@type":73,"acceptedAnswer":83},"Why does the paper question the added value of citation features?",{"text":84,"@type":76},"Citation features match the temporal-only variant but do not provide a measurable additional gain in the official summary, and internal diagnostics suggest the need for cleaner ablation and calibration.","https://schema.org",{"og:url":51,"og:type":87,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":89,"canonical":51},"index,follow",{"doc_id":7,"site_id":25},{"code":4,"msg":5,"data":92},[93,97,101,105,110,115,120,123,128,131,135],{"id":21,"doc_module":4,"doc_module_name":46,"category_name":94,"show_sort_weight":95,"slug":96},"Story & Novel",90,"story-novel",{"id":20,"doc_module":4,"doc_module_name":46,"category_name":98,"show_sort_weight":99,"slug":100},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":46,"category_name":102,"show_sort_weight":103,"slug":104},"Exam",70,"exam",{"id":106,"doc_module":4,"doc_module_name":46,"category_name":107,"show_sort_weight":108,"slug":109},5,"Comic",60,"comic",{"id":111,"doc_module":4,"doc_module_name":46,"category_name":112,"show_sort_weight":113,"slug":114},6,"Technology",50,"technology",{"id":116,"doc_module":4,"doc_module_name":46,"category_name":117,"show_sort_weight":118,"slug":119},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":46,"category_name":12,"show_sort_weight":121,"slug":122},30,"research-report",{"id":124,"doc_module":4,"doc_module_name":46,"category_name":125,"show_sort_weight":126,"slug":127},9,"Religion & Spirituality",20,"religion-spirituality",{"id":126,"doc_module":4,"doc_module_name":46,"category_name":129,"show_sort_weight":126,"slug":130},"World Cup","world-cup",{"id":132,"doc_module":4,"doc_module_name":46,"category_name":133,"show_sort_weight":132,"slug":134},10,"Lifestyle","lifestyle",{"id":136,"doc_module":4,"doc_module_name":46,"category_name":137,"show_sort_weight":106,"slug":138},19,"General","general"]