{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:PW23S6W5YJWIWSUFH77ZLT4C2J","short_pith_number":"pith:PW23S6W5","schema_version":"1.0","canonical_sha256":"7db5b97addc26c8b4a853fff95cf82d278f7cafc69014dafa8a8fd03a563ba18","source":{"kind":"arxiv","id":"2503.01704","version":1},"attestation_state":"computed","paper":{"title":"DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hana Khamfroush, Minoo Hosseinzadeh","submitted_at":"2025-03-03T16:16:33Z","abstract_excerpt":"With a recent trend of using Large Language Models (LLMs) for different applications within smart cities, there is a need for pushing these models toward the edge of network while still preserving their performance. Edge Computing (EC) as a physically closer computing resource to the end users can help to reduce the communication delay for serving end users' tasks for LLM-dependent services. However, EC servers have limited capacity in terms of communication, computation, and storage capacity. This paper introduces DILEMMA, a novel framework addressing the challenges of deploying LLMs in EC sy"},"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":"2503.01704","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.LG","submitted_at":"2025-03-03T16:16:33Z","cross_cats_sorted":[],"title_canon_sha256":"8e04fdd50a3db00520bd201b02e59a50f5fdf3feef5af3c6fb54dfd039fcf250","abstract_canon_sha256":"6bf2e4ac0580619187f7f3e54726313caf36fa165658c88e639e627d07b09821"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:23:12.878658Z","signature_b64":"GvlGb0vxVWklkdr3TsG7HZCAa2btOSabS3d/H1lYBuaqf4yCkpjAEEap9XgEl4X+ZKLbtdNCViPZJ7/LB0SqCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7db5b97addc26c8b4a853fff95cf82d278f7cafc69014dafa8a8fd03a563ba18","last_reissued_at":"2026-07-05T10:23:12.878089Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:23:12.878089Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DILEMMA: Joint LLM Quantization and Distributed LLM Inference Over Edge Computing Systems","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Hana Khamfroush, Minoo Hosseinzadeh","submitted_at":"2025-03-03T16:16:33Z","abstract_excerpt":"With a recent trend of using Large Language Models (LLMs) for different applications within smart cities, there is a need for pushing these models toward the edge of network while still preserving their performance. Edge Computing (EC) as a physically closer computing resource to the end users can help to reduce the communication delay for serving end users' tasks for LLM-dependent services. However, EC servers have limited capacity in terms of communication, computation, and storage capacity. This paper introduces DILEMMA, a novel framework addressing the challenges of deploying LLMs in EC sy"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.01704","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/2503.01704/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":"2503.01704","created_at":"2026-07-05T10:23:12.878154+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.01704v1","created_at":"2026-07-05T10:23:12.878154+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.01704","created_at":"2026-07-05T10:23:12.878154+00:00"},{"alias_kind":"pith_short_12","alias_value":"PW23S6W5YJWI","created_at":"2026-07-05T10:23:12.878154+00:00"},{"alias_kind":"pith_short_16","alias_value":"PW23S6W5YJWIWSUF","created_at":"2026-07-05T10:23:12.878154+00:00"},{"alias_kind":"pith_short_8","alias_value":"PW23S6W5","created_at":"2026-07-05T10:23:12.878154+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2607.08116","citing_title":"MORES: Mobile Reasoning-as-a-Service via Distributed LLM Inference-Time Scaling","ref_index":27,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J","json":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J.json","graph_json":"https://pith.science/api/pith-number/PW23S6W5YJWIWSUFH77ZLT4C2J/graph.json","events_json":"https://pith.science/api/pith-number/PW23S6W5YJWIWSUFH77ZLT4C2J/events.json","paper":"https://pith.science/paper/PW23S6W5"},"agent_actions":{"view_html":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J","download_json":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J.json","view_paper":"https://pith.science/paper/PW23S6W5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.01704&json=true","fetch_graph":"https://pith.science/api/pith-number/PW23S6W5YJWIWSUFH77ZLT4C2J/graph.json","fetch_events":"https://pith.science/api/pith-number/PW23S6W5YJWIWSUFH77ZLT4C2J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J/action/storage_attestation","attest_author":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J/action/author_attestation","sign_citation":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J/action/citation_signature","submit_replication":"https://pith.science/pith/PW23S6W5YJWIWSUFH77ZLT4C2J/action/replication_record"}},"created_at":"2026-07-05T10:23:12.878154+00:00","updated_at":"2026-07-05T10:23:12.878154+00:00"}