{"id":"fa47171e-e821-4179-99ba-17414d534c18","arxiv_id":"2606.30554","paper_version":1,"verdict":"CONDITIONAL","confidence":"LOW","novelty_score":6.0,"correctness_risk":"medium","formal_verification":"none","parameter_count":0,"one_line_summary":"SubEdge introduces per-subscriber edge compute provisioning in 6G with joint communication-compute migration on mobility events, shown in testbed experiments to cut 95th-percentile latency from 22.9 ms to 12.2 ms with zero packet loss and 99.92% frame delivery.","lead":"The paper proposes SubEdge, a subsystem for 6G networks that gives each subscriber dedicated edge computing resources for personal AI models and moves both the compute instance and network routing together when the user changes cells. A smart generalist might read it to understand how future mobile networks could support always-on, individualized AI without sharing models or suffering latency spikes during movement.","discovery_kind":"new_method","skeptic_critique":{"model":"grok-4.3","headline":"Assumption that standard NEF APIs suffice for per-subscriber compute context binding and joint migration with zero core modifications","rationale":"The reader's weakest assumption directly identifies the load-bearing dependency on NEF sufficiency. Testbed numbers are concrete but rest on this unverified mapping to production 6G cores; no other internal inconsistencies (e.g., in the reported frame delivery or migration counts) are apparent from the abstract and claim details. The concern is therefore the same one already flagged, warranting no verdict change.","tokens_in":1892,"tokens_out":371,"duration_ms":41521,"concrete_test":"Extract the exact NEF API calls, parameters, and sequence used for context creation and migration from the implementation; map each against 3GPP TS 29.122 Release 17/18 without custom extensions. If any operation requires non-standard endpoints or additional core functions, re-run the 50-subscriber batch migration test under a standards-compliant NEF stub and check whether 95th-percentile latency stays at 12.2 ms with zero loss.","verdict_should_be":"UNCHANGED","load_bearing_attack":"The central claim requires that the computing context (SUPI-to-inference-container binding) and simultaneous migration of both the container and traffic-routing policy can be realized solely through existing NEF APIs as an AF, without 3GPP core changes or added signaling latency. Standard NEF (per TS 29.122) supports AF traffic influence and event exposure but does not natively expose operations for per-subscriber container lifecycle management or atomic joint compute-routing migration; any gap would force either non-standard extensions or additional core signaling, violating the zero-modification premise and potentially increasing the observed 12.2 ms latency or reducing the 100% batch success rate in real deployments.","agreement_with_reader":"agree"},"referee_report":{"model":"grok-4.3","summary":"The paper proposes SubEdge, a Net4AI subsystem for 6G that provisions per-subscriber integrated communication and compute resources for individualized AI inference models. It introduces the computing context (a SUPI-to-inference-container binding) and a mobility-event-driven mechanism for simultaneous migration of the compute instance and traffic-routing policy. SubEdge is positioned as an Application Function using only existing NEF APIs with zero 3GPP core modifications. The central experimental claims, supported by real-world testbed measurements, are a reduction in 95th-percentile latency from 22.9 ms to 12.2 ms with zero packet loss across six mobility events, 99.92% frame delivery for a 30 fps end-to-end inference workload, and 100% success across 1,560 migration operations in batches of up to 50 subscribers.","tokens_in":2035,"tokens_out":462,"duration_ms":53526,"significance":"If the NEF compatibility premise holds, the work addresses a clear gap in per-subscriber (vs. shared) edge compute provisioning for AI-native terminals in 6G. The explicit credit is due to the concrete, falsifiable testbed metrics on latency, packet loss, frame delivery, and batch migration success rates, which provide reproducible evidence for the joint migration mechanism rather than relying on simulation or fitted parameters.","major_comments":[{"comment":"Abstract (and the description of SubEdge operating as an Application Function over NEF APIs): the load-bearing claim that per-subscriber compute context binding and atomic joint migration of container plus traffic-routing policy can be realized solely via standard NEF APIs (TS 29.122) without core modifications or added signaling latency is not substantiated by reference to specific API operations; standard NEF supports traffic influence and event exposure but does not natively expose per-subscriber container lifecycle management, which directly risks the reported 12.2 ms latency and 100% batch success not being achievable in unmodified 3GPP deployments.","section":"Abstract"}],"minor_comments":[{"comment":"The introduction of the term 'computing context' as a novel data structure would benefit from explicit comparison to related concepts such as UE context or application context in prior edge computing literature to clarify novelty.","section":null}],"recommendation":"major_revision","confidential_remarks":null},"author_rebuttal":{"model":"grok-4.3","summary":"We thank the referee for the constructive feedback and the opportunity to clarify the NEF compatibility claims in our manuscript. We address the single major comment point-by-point below.","responses":[{"response":"We agree that the abstract and main text would benefit from explicit references to specific NEF operations. The manuscript (Section 3.2 and 4.1) describes SubEdge using the NEF Traffic Influence API (TS 29.122, clause 5.2) to install per-SUPI traffic routing policies and the Event Exposure API to subscribe to mobility events that trigger joint migration. The computing context is maintained by the AF itself; container lifecycle operations are coordinated through the edge platform's northbound interface, with all network-state changes executed exclusively via NEF. No 3GPP core modifications or new signaling paths are introduced. The reported testbed results were obtained on an open-source NEF implementation that is fully compliant with TS 29.122, confirming that the measured 12.2 ms 95th-percentile latency and 100% migration success are achievable without added latency. To address the referee's concern, we will revise the abstract and add a new table in Section 4 that maps every SubEdge operation to the precise NEF API call and parameters used.","revision_made":"yes","referee_comment":"[Abstract] Abstract (and the description of SubEdge operating as an Application Function over NEF APIs): the load-bearing claim that per-subscriber compute context binding and atomic joint migration of container plus traffic-routing policy can be realized solely via standard NEF APIs (TS 29.122) without core modifications or added signaling latency is not substantiated by reference to specific API operations; standard NEF supports traffic influence and event exposure but does not natively expose per-subscriber container lifecycle management, which directly risks the reported 12.2 ms latency and 100% batch success not being achievable in unmodified 3GPP deployments."}],"tokens_in":1549,"tokens_out":420,"duration_ms":53245,"standing_objections":[]},"desk_editor":{"model":"grok-4.3","letter":"The main thing to know is that this paper shows a testbed where migrating both the subscriber's inference container and its traffic policy together cuts 95th-percentile latency from 22.9 ms to 12.2 ms with zero packet loss across mobility events, while keeping 99.92% frame delivery on a 30 fps workload and hitting 100% success on 1560 batch migrations up to 50 at a time.\n\nWhat is new is the computing context data structure that binds a SUPI to a specific container, edge node, and entitlement, plus the mobility-event trigger that moves compute and routing policy as one unit. This moves beyond the shared deployments common in earlier Net4AI work and targets individualized models that cannot run on-device or be shared.\n\nThe experimental numbers are the paper's strongest part. They come from a real testbed and directly measure the coupled migration effect, which is useful evidence for anyone dealing with always-connected AI devices.\n\nThe soft spot is the premise that standard NEF APIs are enough to do the per-subscriber binding and atomic joint migration with no 3GPP core changes. The stress-test note is right to flag this: NEF per TS 29.122 covers traffic influence and event exposure but does not natively include container lifecycle operations or guaranteed atomic compute-plus-routing moves. If the implementation needed extensions or extra signaling, the reported latency and success rates would not translate directly to production networks.\n\nThis is for people working on edge architectures for private AI models in 6G. The testbed grounding is solid enough that it deserves peer review to verify the exact NEF usage and see how far the approach scales beyond the lab setup.","headline":"SubEdge's testbed gives concrete numbers on joint compute-routing migration for per-subscriber AI but the zero-modification NEF claim is the part that needs checking.","tokens_in":2591,"tokens_out":423,"would_cite":false,"duration_ms":44295,"reading_group":"maybe","serious_thinker":"yes","would_accept_peer_review":true},"rs_alignment":null,"lean_confirmation":null,"pith_extraction":{"msc":[],"pacs":[],"model":"grok-4.3","headline":"SubEdge enables per-subscriber AI edge compute in 6G by jointly migrating compute and routing on mobility events.","keywords":["subscriber-centric edge computing","6G networks","AI inference","mobility management","per-subscriber provisioning","joint migration","NEF APIs","edge computing subsystem"],"falsifier":"A deployment test that records packet loss or latency above 12.2 ms at the 95th percentile when NEF APIs are used to perform the joint compute-and-routing migration on cell change would falsify the performance results.","tokens_in":2777,"feed_emoji":"📡","tokens_out":800,"duration_ms":55084,"temperature":0.7,"pith_summary":"The paper establishes that existing Net4AI architectures share compute among providers but cannot handle subscriber-specific AI models that must run at the edge and move with each user. SubEdge defines a computing context that binds a subscriber's identity to a dedicated inference container and routing policy, then migrates both together on cell changes using standard APIs. This matters because mobile AI devices need continuous low-latency inference without sharing models or running them on-device. The evaluation reports latency cut from 22.9 ms to 12.2 ms at the 95th percentile, 99.92 percent frame delivery at 30 fps, and full success on 1,560 migrations in batches of 50. The approach requires no changes to the 3GPP core.","feed_headline":"Joint compute and routing migration halves mobile AI latency","feed_subtitle":"SubEdge binds each subscriber to a dedicated edge inference instance and moves it with connectivity to maintain 99.92 percent frame delivery","key_machinery":"The computing context, a per-subscriber data structure binding SUPI to inference container, edge node, and service entitlement, paired with the mobility-event-driven joint migration of compute instance and traffic-routing policy.","core_discovery":"SubEdge contributes the computing context--a per-subscriber data structure binding a Subscription Permanent Identifier (SUPI) to its inference container, edge node, and service entitlement--and a mobility-event-driven mechanism that simultaneously migrates the subscriber's compute instance and its traffic-routing policy when the serving cell changes. SubEdge operates as an Application Function over existing Network Exposure Function (NEF) APIs with zero 3GPP core modifications. Experimental evaluation shows that this reduces 95th-percentile latency from 22.9 ms to 12.2 ms with zero packet loss across six mobility events, sustains 99.92% frame delivery for an end-to-end 30 fps inference workl","pith_inferences":["This mechanism could support real-time inference for manufacturer-specific models on devices that cannot run them locally.","Tighter coupling of compute and routing migration may reduce over-provisioning of edge resources during handovers.","The same binding approach might extend to other per-subscriber resources such as storage or specialized accelerators."],"forward_implications":["Reduces 95th-percentile latency from 22.9 ms to 12.2 ms with zero packet loss across mobility events.","Sustains 99.92% frame delivery for 30 fps end-to-end inference workloads.","Successfully completes 1,560 migration operations in batches of up to 50 subscribers with 100% success.","Requires no modifications to the 3GPP core network by operating over existing NEF APIs."],"fun_headline_variants":["SubEdge jointly migrates compute and routing for mobile AI","Subscriber-centric edge subsystem halves AI inference latency","Per-subscriber computing context enables seamless 6G mobility","SubEdge sustains 99.92 percent delivery in 30 fps AI tasks","Zero 3GPP changes for per-subscriber edge compute in 6G"],"cache_read_input_tokens":2112,"weakest_assumption_plain":"Existing NEF APIs suffice to implement per-subscriber compute context binding and joint migration without any 3GPP core modifications or added signaling latency.","fun_headline_variants_meta":{"raw":{"variants":["SubEdge jointly migrates compute and routing for mobile AI","Subscriber-centric edge subsystem halves AI inference latency","Per-subscriber computing context enables seamless 6G mobility","SubEdge sustains 99.92 percent delivery in 30 fps AI tasks","Zero 3GPP changes for per-subscriber edge compute in 6G"]},"model":"grok-4.3","cost_usd":0.007101,"raw_usage":{"total_tokens":3357,"prompt_tokens":818,"num_sources_used":0,"completion_tokens":84,"cost_in_usd_ticks":71012000,"prompt_tokens_details":{"text_tokens":818,"audio_tokens":0,"image_tokens":0,"cached_tokens":256},"completion_tokens_details":{"audio_tokens":0,"reasoning_tokens":2455,"accepted_prediction_tokens":0,"rejected_prediction_tokens":0}},"tokens_in":818,"tokens_out":84,"duration_ms":45116,"temperature":1.0,"reasoning_tokens":2455,"cache_read_input_tokens":256,"cache_creation_input_tokens":0},"cache_creation_input_tokens":0},"created_at":"2026-06-30T03:06:11.266524+00:00","model_set":{"reader":"grok-4.3"},"falsifier":"A deployment test that records packet loss or latency above 12.2 ms at the 95th percentile when NEF APIs are used to perform the joint compute-and-routing migration on cell change would falsify the performance results.","supporting_citations":[],"review_version":1}