[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-84551-en":3,"doc-seo-84551-105":29,"detail-sidebar-cat-0-en-105":83},{"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":20,"is_downloadable":20,"audit_status":20,"page_count":21,"language":22,"language_code":23,"site_id":24,"html_lang":23,"table_of_contents":25,"faqs":26,"seo_title":13,"seo_description":14,"update_tm":27,"read_time":28},84551,34359740700684,"Finn","https://ap-avatar.wpscdn.com/avatar/1f400023980c374ae676?_k=1777273430885731487",8,"Research & Report","TRACE State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data","Conversational data increasingly serves as persistent user state for long-running assistants and AI agents, but querying it is difficult because conversations evolve through plan revisions, preference changes, and contradictions. Existing long-memory pipelines often retrieve semantically similar yet stale evidence, limiting state-aware reasoning. TRACE introduces a hierarchical temporal evidence graph with typed causal, update, contradiction relations and validity annotations to discount obsolete facts for current answers while keeping access for historical queries. Query-time retrieval fuses vector note recall with graph-guided evidence search, enabling bounded multi-hop reasoning over long histories. Experiments on long-conversation QA benchmarks show improved temporal and multi-hop performance, with ablations supporting hierarchy and path-grounded evidence.","TRACE: State-Aware Query Processing over Temporal Evidence Graphs for Conversational Data  \nMaolin Wang 1 , Yu Wang 1 , Zichun Liu 1 , Baiyuan Qiu2 ,  \nChenbin Zhang 2 , Jiguang Shen2 , Haoran Yang3 , Hao Miao4  \n1Hong Kong Institute of AI for Science, City University of Hong Kong, Hong Kong SAR, China  \n{[morin.wang@](morin.wang@), [wangyu6-c@my.](wangyu6-c@my.}cityu.edu.hk)[}](wangyu6-c@my.}cityu.edu.hk)[cityu.edu.hk](wangyu6-c@my.}cityu.edu.hk)  \n2Independent Researcher, Beijing, China  \n3 Central South University, Changsha, China  \n4The Hong Kong Polytechnic University, Hong Kong SAR, China  \narXiv :2607 .00339v 1 [ cs .CL] 1 Jul 2026  \nAbstract—Conversational data is increasingly used as a persistent source of user state for long-running assistants and AI agents. However, querying this data remains challenging because conversations naturally evolve: plans are revised, preferences change, and later messages frequently supersede or contradict earlier information. Existing long-memory pipelines largely treat memories as independent text or vector objects. This approach often retrieves semantically similar but stale evidence, offering limited support for state-aware reasoning. To address this problem, we present TRACE, a query processing framework over temporal evidence graphs for evolving conversational data. TRACE models conversations as a hierarchical graph spanning events, sessions, and topics, enriched with typed temporal, causal, update, and contradiction relations. Crucially, the framework maintains validity annotations so obsolete facts remain accessible for historical queries but are discounted for current-state answers. At query time, TRACE combines vector-based note retrieval with graph-guided evidence search, generating validity-aware support paths and a hybrid context for answer generation. This design separates lexical recall from evidence reconstruction, enabling bounded query-time reasoning over long conversational histories. Experiments on long-conversation query-answering (QA) benchmarks show that TRACE improves temporal and multi-hop reasoning, with ablations highlighting the importance of hierarchy, update-aware seeding, and path-grounded evidence. Source code is provided at [https://github.com/MorinWang/TRACE](https://github.com/MorinWang/TRACE).  \nIndex Terms—Conversational data, temporal evidence graph, state-aware query processing, graph retrieval, vector search, evolving memory, temporal validity  \nI. INTRODUCTION  \nConversational data is now a permanent fixture in personal assistants, enterprise copilots, customer service systems, and autonomous AI agents [1]–[4] . Unlike static documents, this data captures shifting user states: preferences evolve, plans change, commitments expire, and new messages often update or contradict older ones. Querying such data requires more than retrieving relevant text spans: a system must identify which facts are still valid, which are outdated history, and how scattered pieces of evidence connect. These are precisely the concerns addressed by temporal databases and stream processing [5]–[8], yet current conversational memory systems lack analogous mechanisms for valid-time tracking, update propagation, and versioned-state querying. Long-term conversational QA is therefore a data-management challenge over  \ntemporal, heterogeneous, continuously evolving interaction histories. Failing to address it leads to hallucinated answers grounded in stale context, missed updates, or incoherent reasoning over fragmented evidence, ultimately undermining user trust and system reliability in deployed applications.  \nThe core difficulty stems from a mismatch between how conversational data is stored and how it is queried. Interactions arrive as a linear, timestamped stream of messages, while many questions require a reconstructed state. A user may share a travel plan, later change the destination, and eventually ask about the current itinerary or the reasoning behind the decision. Ans","cbCaijf9J4cmffJT","https://ap.wps.com/l/cbCaijf9J4cmffJT","pdf",2116425,1,14,"English","en",105,"# Abstract\n# Introduction\n## Conversational data as evolving state\n## Core difficulty: mismatch between storage and querying\n## Related work and partial solutions\n## Requirements for an ideal data model","[{\"question\":\"What evidence supports TRACE’s effectiveness according to the document?\",\"answer\":\"Experiments on long-conversation QA benchmarks show improvements in temporal and multi-hop reasoning. Ablation studies highlight the importance of hierarchy, update-aware seeding, and path-grounded evidence, and the document states that source code is provided.\"}]",1784196632,35,{"code":4,"msg":30,"data":31},"ok",{"site_id":24,"language":23,"slug":32,"title":13,"keywords":33,"description":14,"schema_data":34,"social_meta":78,"head_meta":80,"extra_data":82,"updated_unix":27},"trace-state-aware-query-processing-over-temporal-evidence-graphs-for-conversational-data","",{"@graph":35,"@context":77},[36,53,68],{"@type":37,"itemListElement":38},"BreadcrumbList",[39,43,47,50],{"item":40,"name":41,"@type":42,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":44,"name":45,"@type":42,"position":46},"https://docshare.wps.com/document/","Document",2,{"item":48,"name":12,"@type":42,"position":49},"https://docshare.wps.com/document/research-report/",3,{"item":51,"name":13,"@type":42,"position":52},"https://docshare.wps.com/document/trace-state-aware-query-processing-over-temporal-evidence-graphs-for-conversational-data/84551/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":62,"encodingFormat":60,"isAccessibleForFree":63,"interactionStatistic":64},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-17","2026-07-16",true,{"@type":65,"interactionType":66,"userInteractionCount":20},"InteractionCounter",{"@type":67},"ViewAction",{"@type":69,"mainEntity":70},"FAQPage",[71],{"name":72,"@type":73,"acceptedAnswer":74},"What evidence supports TRACE’s effectiveness according to the document?","Question",{"text":75,"@type":76},"Experiments on long-conversation QA benchmarks show improvements in temporal and multi-hop reasoning. Ablation studies highlight the importance of hierarchy, update-aware seeding, and path-grounded evidence, and the document states that source code is provided.","Answer","https://schema.org",{"og:url":51,"og:type":79,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":81,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":84},[85,89,93,97,102,107,112,115,120,123,127],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":86,"show_sort_weight":87,"slug":88},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":90,"show_sort_weight":91,"slug":92},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":94,"show_sort_weight":95,"slug":96},"Exam",70,"exam",{"id":98,"doc_module":4,"doc_module_name":45,"category_name":99,"show_sort_weight":100,"slug":101},5,"Comic",60,"comic",{"id":103,"doc_module":4,"doc_module_name":45,"category_name":104,"show_sort_weight":105,"slug":106},6,"Technology",50,"technology",{"id":108,"doc_module":4,"doc_module_name":45,"category_name":109,"show_sort_weight":110,"slug":111},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":113,"slug":114},30,"research-report",{"id":116,"doc_module":4,"doc_module_name":45,"category_name":117,"show_sort_weight":118,"slug":119},9,"Religion & Spirituality",20,"religion-spirituality",{"id":118,"doc_module":4,"doc_module_name":45,"category_name":121,"show_sort_weight":118,"slug":122},"World Cup","world-cup",{"id":124,"doc_module":4,"doc_module_name":45,"category_name":125,"show_sort_weight":124,"slug":126},10,"Lifestyle","lifestyle",{"id":128,"doc_module":4,"doc_module_name":45,"category_name":129,"show_sort_weight":98,"slug":130},19,"General","general"]