{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:VC3ZHWMLISY23CLXTWQHE764C4","short_pith_number":"pith:VC3ZHWML","schema_version":"1.0","canonical_sha256":"a8b793d98b44b1ad89779da0727fdc17336fa66a3fb6b9a7064b867d2ff5127e","source":{"kind":"arxiv","id":"2506.19030","version":2},"attestation_state":"computed","paper":{"title":"WiLLM: an Open Framework for LLM Services over Wireless Systems","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Boyi Liu, Jagmohan Chauhan, Jianguo Zhao, Jun Zhang, Lin Chen, Qiang Yang, Wen Wu, Yongguang Lu","submitted_at":"2025-06-23T18:37:55Z","abstract_excerpt":"Large Language Model (LLM) services fundamentally differ from traditional Deep Neural Network (DNN) applications in wireless networks. We identify three critical distinctions: (1) unlike traditional DNNs with unidirectional data flows, LLM's multimodal interactions create bidirectional heavy loads with contrasting bottlenecks, requiring direction-aware resource scheduling; (2) while traditional DNNs exhibit fixed computational patterns, LLM's highly variable inference times interact complexly with network slicing, causing dynamic bottleneck migration; and (3) in contrast to predictable DNN tra"},"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":"2506.19030","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.NI","submitted_at":"2025-06-23T18:37:55Z","cross_cats_sorted":[],"title_canon_sha256":"2fa7d33d8a99828722af6e3082265dcab1d8ae5c0e1e08aa4a6f6032e1dfb576","abstract_canon_sha256":"1b1e8e48705c1760a5cdfe4e4f7a404fd8e67d0999a65d8f76b22d624bd2f719"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:09.728106Z","signature_b64":"Ub1pjjYnUZ9mVd6QuK8JEtsflagtNfPx3/8O1r4j+T8mk2Q/MeafLU1u9kDWwHTm1OdM/UlAtkDVZ9bU6OcZBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a8b793d98b44b1ad89779da0727fdc17336fa66a3fb6b9a7064b867d2ff5127e","last_reissued_at":"2026-07-05T11:34:09.727651Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:09.727651Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WiLLM: an Open Framework for LLM Services over Wireless Systems","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Boyi Liu, Jagmohan Chauhan, Jianguo Zhao, Jun Zhang, Lin Chen, Qiang Yang, Wen Wu, Yongguang Lu","submitted_at":"2025-06-23T18:37:55Z","abstract_excerpt":"Large Language Model (LLM) services fundamentally differ from traditional Deep Neural Network (DNN) applications in wireless networks. We identify three critical distinctions: (1) unlike traditional DNNs with unidirectional data flows, LLM's multimodal interactions create bidirectional heavy loads with contrasting bottlenecks, requiring direction-aware resource scheduling; (2) while traditional DNNs exhibit fixed computational patterns, LLM's highly variable inference times interact complexly with network slicing, causing dynamic bottleneck migration; and (3) in contrast to predictable DNN tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2506.19030","kind":"arxiv","version":2},"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/2506.19030/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":"2506.19030","created_at":"2026-07-05T11:34:09.727708+00:00"},{"alias_kind":"arxiv_version","alias_value":"2506.19030v2","created_at":"2026-07-05T11:34:09.727708+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2506.19030","created_at":"2026-07-05T11:34:09.727708+00:00"},{"alias_kind":"pith_short_12","alias_value":"VC3ZHWMLISY2","created_at":"2026-07-05T11:34:09.727708+00:00"},{"alias_kind":"pith_short_16","alias_value":"VC3ZHWMLISY23CLX","created_at":"2026-07-05T11:34:09.727708+00:00"},{"alias_kind":"pith_short_8","alias_value":"VC3ZHWML","created_at":"2026-07-05T11:34:09.727708+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.16689","citing_title":"Against the Monolithic Wireless World Model: Why NextG Needs Composable and Agentic Intelligence","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4","json":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4.json","graph_json":"https://pith.science/api/pith-number/VC3ZHWMLISY23CLXTWQHE764C4/graph.json","events_json":"https://pith.science/api/pith-number/VC3ZHWMLISY23CLXTWQHE764C4/events.json","paper":"https://pith.science/paper/VC3ZHWML"},"agent_actions":{"view_html":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4","download_json":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4.json","view_paper":"https://pith.science/paper/VC3ZHWML","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2506.19030&json=true","fetch_graph":"https://pith.science/api/pith-number/VC3ZHWMLISY23CLXTWQHE764C4/graph.json","fetch_events":"https://pith.science/api/pith-number/VC3ZHWMLISY23CLXTWQHE764C4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4/action/storage_attestation","attest_author":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4/action/author_attestation","sign_citation":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4/action/citation_signature","submit_replication":"https://pith.science/pith/VC3ZHWMLISY23CLXTWQHE764C4/action/replication_record"}},"created_at":"2026-07-05T11:34:09.727708+00:00","updated_at":"2026-07-05T11:34:09.727708+00:00"}