{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:5RON5DI4Z3CTY3IYOUXMHBLKMW","short_pith_number":"pith:5RON5DI4","schema_version":"1.0","canonical_sha256":"ec5cde8d1ccec53c6d18752ec3856a65a02be8472a7efa1b6fde2d5b80f632b3","source":{"kind":"arxiv","id":"2505.09214","version":1},"attestation_state":"computed","paper":{"title":"The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Xu, Marco Di Renzo, Mikael Skoglund, Ming Xiao, Zhonghao Lyu","submitted_at":"2025-05-14T08:18:55Z","abstract_excerpt":"The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications. In particular, edge-device co-inference, which partitions LAIMs between edge devices and servers, has emerged as a promising strategy for resource-efficient LAIM execution in wireless networks. In this paper, we investigate a pruning-aware LAIM co-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment. For analysi"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2505.09214","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-14T08:18:55Z","cross_cats_sorted":[],"title_canon_sha256":"fba685ba8002215b8f10d48ea55349b4ff3b7fa8fded6d59239cf753f9018f3f","abstract_canon_sha256":"3cc33cda57717ce28eff770b16d5434cef43d0f13832cf47410283d2fa98dc54"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:02:52.328421Z","signature_b64":"3D2cYq8uGOoKyH9Rd07oOrI0zsF54tsDZgV79uUdFN7J3sb7u6oxYsINMu/426IKxKAtxvYf2iNCA08AhNDUDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec5cde8d1ccec53c6d18752ec3856a65a02be8472a7efa1b6fde2d5b80f632b3","last_reissued_at":"2026-07-05T11:02:52.327821Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:02:52.327821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Larger the Merrier? Efficient Large AI Model Inference in Wireless Edge Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jie Xu, Marco Di Renzo, Mikael Skoglund, Ming Xiao, Zhonghao Lyu","submitted_at":"2025-05-14T08:18:55Z","abstract_excerpt":"The growing demand for large artificial intelligence model (LAIM) services is driving a paradigm shift from traditional cloud-based inference to edge-based inference for low-latency, privacy-preserving applications. In particular, edge-device co-inference, which partitions LAIMs between edge devices and servers, has emerged as a promising strategy for resource-efficient LAIM execution in wireless networks. In this paper, we investigate a pruning-aware LAIM co-inference scheme, where a pre-trained LAIM is pruned and partitioned into on-device and on-server sub-models for deployment. For analysi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.09214","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2505.09214/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2505.09214","created_at":"2026-07-05T11:02:52.327887+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.09214v1","created_at":"2026-07-05T11:02:52.327887+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.09214","created_at":"2026-07-05T11:02:52.327887+00:00"},{"alias_kind":"pith_short_12","alias_value":"5RON5DI4Z3CT","created_at":"2026-07-05T11:02:52.327887+00:00"},{"alias_kind":"pith_short_16","alias_value":"5RON5DI4Z3CTY3IY","created_at":"2026-07-05T11:02:52.327887+00:00"},{"alias_kind":"pith_short_8","alias_value":"5RON5DI4","created_at":"2026-07-05T11:02:52.327887+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.22343","citing_title":"Empowering Intelligent Low-altitude Economy with Large AI Model Deployment","ref_index":2025,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW","json":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW.json","graph_json":"https://pith.science/api/pith-number/5RON5DI4Z3CTY3IYOUXMHBLKMW/graph.json","events_json":"https://pith.science/api/pith-number/5RON5DI4Z3CTY3IYOUXMHBLKMW/events.json","paper":"https://pith.science/paper/5RON5DI4"},"agent_actions":{"view_html":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW","download_json":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW.json","view_paper":"https://pith.science/paper/5RON5DI4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.09214&json=true","fetch_graph":"https://pith.science/api/pith-number/5RON5DI4Z3CTY3IYOUXMHBLKMW/graph.json","fetch_events":"https://pith.science/api/pith-number/5RON5DI4Z3CTY3IYOUXMHBLKMW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW/action/storage_attestation","attest_author":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW/action/author_attestation","sign_citation":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW/action/citation_signature","submit_replication":"https://pith.science/pith/5RON5DI4Z3CTY3IYOUXMHBLKMW/action/replication_record"}},"created_at":"2026-07-05T11:02:52.327887+00:00","updated_at":"2026-07-05T11:02:52.327887+00:00"}