{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MS7E3OHZPYZDSHKXIV6CSPELTB","short_pith_number":"pith:MS7E3OHZ","schema_version":"1.0","canonical_sha256":"64be4db8f97e32391d57457c293c8b9878cc2cb09f2361b0075111a47edade07","source":{"kind":"arxiv","id":"2410.11845","version":2},"attestation_state":"computed","paper":{"title":"A Review on Edge Large Language Models: Design, Execution, and Applications","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bin Qian, Jiming Chen, Xiufang Shi, Yuanchao Shu, Yue Zheng, Yuhao Chen","submitted_at":"2024-09-29T08:29:11Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing with their exceptional understanding, synthesizing, and reasoning capabilities. However, deploying LLMs on resource-constrained edge devices presents significant challenges due to computational limitations, memory constraints, and edge hardware heterogeneity. This survey provides a comprehensive overview of recent advancements in edge LLMs, covering the entire lifecycle: from resource-efficient model design and pre-deployment strategies to runtime inference optimizations. It also explores on-device applications across"},"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":"2410.11845","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.DC","submitted_at":"2024-09-29T08:29:11Z","cross_cats_sorted":[],"title_canon_sha256":"15369df63a9b9b4d09f63e821b3af9d4ba9f2c023783143a82d44ff9b48aaafa","abstract_canon_sha256":"8cb77d1df2fc6743e8f9623f9407835aa2388f73bb8b81226d9d9db3ea662949"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:18:43.389768Z","signature_b64":"ioBkDvhvhOx2aT1EP7AWLUaF4Vjm0r9Y7BApTn2Qxnaz2PM5VkXUWVrFraRIF/nXlo8/rKI1Tf3NmLf0W0lPAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"64be4db8f97e32391d57457c293c8b9878cc2cb09f2361b0075111a47edade07","last_reissued_at":"2026-07-05T10:18:43.389259Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:18:43.389259Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Review on Edge Large Language Models: Design, Execution, and Applications","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Bin Qian, Jiming Chen, Xiufang Shi, Yuanchao Shu, Yue Zheng, Yuhao Chen","submitted_at":"2024-09-29T08:29:11Z","abstract_excerpt":"Large language models (LLMs) have revolutionized natural language processing with their exceptional understanding, synthesizing, and reasoning capabilities. However, deploying LLMs on resource-constrained edge devices presents significant challenges due to computational limitations, memory constraints, and edge hardware heterogeneity. This survey provides a comprehensive overview of recent advancements in edge LLMs, covering the entire lifecycle: from resource-efficient model design and pre-deployment strategies to runtime inference optimizations. It also explores on-device applications across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.11845","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/2410.11845/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":"2410.11845","created_at":"2026-07-05T10:18:43.389324+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.11845v2","created_at":"2026-07-05T10:18:43.389324+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.11845","created_at":"2026-07-05T10:18:43.389324+00:00"},{"alias_kind":"pith_short_12","alias_value":"MS7E3OHZPYZD","created_at":"2026-07-05T10:18:43.389324+00:00"},{"alias_kind":"pith_short_16","alias_value":"MS7E3OHZPYZDSHKX","created_at":"2026-07-05T10:18:43.389324+00:00"},{"alias_kind":"pith_short_8","alias_value":"MS7E3OHZ","created_at":"2026-07-05T10:18:43.389324+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.12876","citing_title":"Multi-Bitwidth Quantization for LLMs Using Additive Codebooks","ref_index":103,"is_internal_anchor":false},{"citing_arxiv_id":"2606.12487","citing_title":"DynamicPTQ: Mitigating Activation Quantization Collapse via Residual-Stream Dynamics","ref_index":38,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB","json":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB.json","graph_json":"https://pith.science/api/pith-number/MS7E3OHZPYZDSHKXIV6CSPELTB/graph.json","events_json":"https://pith.science/api/pith-number/MS7E3OHZPYZDSHKXIV6CSPELTB/events.json","paper":"https://pith.science/paper/MS7E3OHZ"},"agent_actions":{"view_html":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB","download_json":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB.json","view_paper":"https://pith.science/paper/MS7E3OHZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.11845&json=true","fetch_graph":"https://pith.science/api/pith-number/MS7E3OHZPYZDSHKXIV6CSPELTB/graph.json","fetch_events":"https://pith.science/api/pith-number/MS7E3OHZPYZDSHKXIV6CSPELTB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB/action/storage_attestation","attest_author":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB/action/author_attestation","sign_citation":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB/action/citation_signature","submit_replication":"https://pith.science/pith/MS7E3OHZPYZDSHKXIV6CSPELTB/action/replication_record"}},"created_at":"2026-07-05T10:18:43.389324+00:00","updated_at":"2026-07-05T10:18:43.389324+00:00"}