[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-85211-en":3,"doc-seo-85211-105":29,"detail-sidebar-cat-0-en-105":90},{"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":4,"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},85211,962075114101,"Seraphina","https://ap-avatar.wpscdn.com/avatar/e000253a75eb197efd?x-image-process=image/resize,m_fixed,w_180,h_180&k=1780044092746381165",8,"Research & Report","Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models","A persistent interactive world model keeps its running state resident on the GPU that serves it, relying on a massive attention cache that is almost fully rewritten every generation step. Because this state cannot be recomputed or approximated without changing the world, exact continuity requires one user to remain pinned to one GPU. WorldMove treats exact-state relocation as a scheduling problem with a bit-identical guarantee or no install, using checksum-verified migrations and admission control.","Stateful Worlds, Stateless Elasticity: Exact-State Serving for Interactive World Models  \nJin Li∗ Harvard University Cambridge, MA, USA  \nJiawei (Alexon) Chen Independent Researcher  \narXiv :2607 . 10389v1 [ cs .DC] 11 Jul 2026  \nAbstract  \nA persistent interactive world model keeps its running state resident on the GPU that serves it: a multi-gigabyte attention cache, almost all of it rewritten at every generation step. That state cannot be recomputed in interactive time or approximated without changing the world, so a live session pins its device: one user, one GPU. We show the pin is a scheduling problem. WorldMove moves a live session under one guarantee: the destination is bit-identical to the source, or nothing is installed. It relocates the cache in 18.8 ms samenode, 101× faster than save/load, to our knowledge the only other deployed exact-class primitive. It holds a checksumverified 92.1–94. 8Gb/s on a 100Gb fabric. At that rate the cache fits inside one interactive block. Migrating an actively generating session, it converges at a block boundary, and the destination continues the world bit for bit. An admissibility condition decides each move. The move must complete inside the readout horizon, over bandwidth that covers the state plus its dirty rate. The condition lifts to a fleet schedulability test; the consolidation loop it governs executed 48 of 48 fleet migrations bit-identical across two providers. Two constraints are structural. Bit-exactness survives only inside a controlled configuration of one GPU architecture, so moving the state is the only way to preserve it exactly in interactive time. On this fabric, verification cannot hide inside the wire. Receive-path checksums stall the transport at protocol-timer timescales under fan-in, and, separately, unscheduled incast silently collapses a receiver while every delivered byte stays correct. An incast-aware admission controller holds zero misses to 1.4× offered load and sheds overload as explicit rejects. A lossless GPU codec widens the admission gate to fabrics that raw motion cannot use. We exercise the serving loop and themover separately, each end to end. Their composition on one fabric is unbuilt. Exact-state elasticity is a joint scheduling problem over transport and verification.  \n1 Introduction  \nAn interactive world model’s running state lives on the GPU that serves it: an attention cache of 1. 67 GB on one production engine (§3), three-quarters of it rewritten every generation step, and growing with per-session context length. The model advances that state one action-conditioned block at a time, and  \n∗ Work done while on a leave of absence from Harvard University.  \nonce a user is inside the world the state is the running computation. It cannot be recomputed from a prompt, re-derived from its log in interactive time, or approximated without visibly changing the world. The contract a viewer holds is exact continuity: the next frame must be the one this exact trajectory would have produced. Because no deployed serving primitive can relocate that state under that contract, a live session pins its device for its whole lifetime: one user, one GPU. The vendors say so plainly. World Labs runs one interactive stream per dedicated H100 and prices persistence as “neither feasible nor economically viable given today’s computing infrastructure” [13]; Decart, operating Oasis in production, calls serving cost “the hidden bottleneck to releasing generative video in production” [14], and its successor ships at $0.02 per simulated second ($72 per user-hour) [58] . At one device per stream, 104 concurrent sessions provision 104 GPUs, the same cost cliff that forced virtualization into the datacenter two decades ago.  \nWe measured the pin directly. Under the exact-continuity contract every lossy handle we evaluated (eviction, quantization, low-rank projection, cross-session dedup) breaks the world (60–92dB divergence, §3), so the destination must receive the whole stat","cbCaipF1gjrBWmJL","https://ap.wps.com/l/cbCaipF1gjrBWmJL","pdf",1044874,1,20,"English","en",105,"# Abstract\n# Introduction\n## Stateful GPU resident world state\n## Pinning cost and continuity contract\n## Lossless migration and admission gating","[{\"question\":\"What problem does the document address for interactive world model serving?\",\"answer\":\"It addresses how to serve interactive world models while preserving exact continuity of the running GPU-resident state, which cannot be recomputed or approximated without changing the world.\"},{\"question\":\"Why does a live session normally get pinned to one GPU?\",\"answer\":\"Under the exact-continuity contract, any lossy change to the attention cache breaks the world, so the only way to preserve bit-exact behavior in interactive time is to keep the state intact on the same device.\"},{\"question\":\"How does WorldMove enable elasticity without sacrificing exactness?\",\"answer\":\"WorldMove relocates the cache via migrations that are bit-identical when successful, using checksum verification and an admissibility condition that ensures the move completes within the readout horizon and required bandwidth.\"}]",1784201779,50,{"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":85,"head_meta":87,"extra_data":89,"updated_unix":27},"stateful-worlds-stateless-elasticity-exact-state-serving-for-interactive-world-models","",{"@graph":35,"@context":84},[36,53,67],{"@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/stateful-worlds-stateless-elasticity-exact-state-serving-for-interactive-world-models/85211/",4,{"url":51,"name":13,"@type":54,"author":55,"headline":13,"publisher":57,"fileFormat":60,"inLanguage":23,"description":14,"dateModified":61,"datePublished":61,"encodingFormat":60,"isAccessibleForFree":62,"interactionStatistic":63},"DigitalDocument",{"name":9,"@type":56},"Person",{"url":40,"name":58,"@type":59},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":64,"interactionType":65,"userInteractionCount":4},"InteractionCounter",{"@type":66},"ViewAction",{"@type":68,"mainEntity":69},"FAQPage",[70,76,80],{"name":71,"@type":72,"acceptedAnswer":73},"What problem does the document address for interactive world model serving?","Question",{"text":74,"@type":75},"It addresses how to serve interactive world models while preserving exact continuity of the running GPU-resident state, which cannot be recomputed or approximated without changing the world.","Answer",{"name":77,"@type":72,"acceptedAnswer":78},"Why does a live session normally get pinned to one GPU?",{"text":79,"@type":75},"Under the exact-continuity contract, any lossy change to the attention cache breaks the world, so the only way to preserve bit-exact behavior in interactive time is to keep the state intact on the same device.",{"name":81,"@type":72,"acceptedAnswer":82},"How does WorldMove enable elasticity without sacrificing exactness?",{"text":83,"@type":75},"WorldMove relocates the cache via migrations that are bit-identical when successful, using checksum verification and an admissibility condition that ensures the move completes within the readout horizon and required bandwidth.","https://schema.org",{"og:url":51,"og:type":86,"og:title":13,"og:site_name":58,"og:description":14},"article",{"robots":88,"canonical":51},"index,follow",{"doc_id":7,"site_id":24},{"code":4,"msg":5,"data":91},[92,96,100,104,109,113,118,121,125,128,132],{"id":20,"doc_module":4,"doc_module_name":45,"category_name":93,"show_sort_weight":94,"slug":95},"Story & Novel",90,"story-novel",{"id":46,"doc_module":4,"doc_module_name":45,"category_name":97,"show_sort_weight":98,"slug":99},"Literature",80,"literature",{"id":52,"doc_module":4,"doc_module_name":45,"category_name":101,"show_sort_weight":102,"slug":103},"Exam",70,"exam",{"id":105,"doc_module":4,"doc_module_name":45,"category_name":106,"show_sort_weight":107,"slug":108},5,"Comic",60,"comic",{"id":110,"doc_module":4,"doc_module_name":45,"category_name":111,"show_sort_weight":28,"slug":112},6,"Technology","technology",{"id":114,"doc_module":4,"doc_module_name":45,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":45,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":45,"category_name":123,"show_sort_weight":21,"slug":124},9,"Religion & Spirituality","religion-spirituality",{"id":21,"doc_module":4,"doc_module_name":45,"category_name":126,"show_sort_weight":21,"slug":127},"World Cup","world-cup",{"id":129,"doc_module":4,"doc_module_name":45,"category_name":130,"show_sort_weight":129,"slug":131},10,"Lifestyle","lifestyle",{"id":133,"doc_module":4,"doc_module_name":45,"category_name":134,"show_sort_weight":105,"slug":135},19,"General","general"]