{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:5QOBB6N4SUZR2EV22ONLRYYRBF","short_pith_number":"pith:5QOBB6N4","schema_version":"1.0","canonical_sha256":"ec1c10f9bc95331d12bad39ab8e3110977f088ab8ada964bcfd8fca52e6a61f1","source":{"kind":"arxiv","id":"2410.16070","version":2},"attestation_state":"computed","paper":{"title":"On-Device LLMs for SMEs: Challenges and Opportunities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aik Beng Ng, Ian McLoughlin, Jeremy Stephen Gabriel Yee, Pai Chet Ng, Simon See, Zhengkui Wang","submitted_at":"2024-10-21T14:48:35Z","abstract_excerpt":"This paper presents a systematic review of the infrastructure requirements for deploying Large Language Models (LLMs) on-device within the context of small and medium-sized enterprises (SMEs), focusing on both hardware and software perspectives. From the hardware viewpoint, we discuss the utilization of processing units like GPUs and TPUs, efficient memory and storage solutions, and strategies for effective deployment, addressing the challenges of limited computational resources typical in SME settings. From the software perspective, we explore framework compatibility, operating system optimiz"},"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":"2410.16070","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-10-21T14:48:35Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"ae22d7afb02c5954b04b4f304ed85ee0269099e2dba13b47f391f26366fbfedd","abstract_canon_sha256":"cf4e9462205f662e1274cf419162b0a7238d14a8bbeb485f706995300ed54d73"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:24:01.889935Z","signature_b64":"fsFg1e2WBuivcl59x6THa2KsxQU8PDWUj/Qc8Hh5Gt4d818wMqRhBLBo9Ftc4PZXdQ0h+IKDR3OIE9uJXlBPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ec1c10f9bc95331d12bad39ab8e3110977f088ab8ada964bcfd8fca52e6a61f1","last_reissued_at":"2026-07-05T09:24:01.889385Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:24:01.889385Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On-Device LLMs for SMEs: Challenges and Opportunities","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.AI","authors_text":"Aik Beng Ng, Ian McLoughlin, Jeremy Stephen Gabriel Yee, Pai Chet Ng, Simon See, Zhengkui Wang","submitted_at":"2024-10-21T14:48:35Z","abstract_excerpt":"This paper presents a systematic review of the infrastructure requirements for deploying Large Language Models (LLMs) on-device within the context of small and medium-sized enterprises (SMEs), focusing on both hardware and software perspectives. From the hardware viewpoint, we discuss the utilization of processing units like GPUs and TPUs, efficient memory and storage solutions, and strategies for effective deployment, addressing the challenges of limited computational resources typical in SME settings. From the software perspective, we explore framework compatibility, operating system optimiz"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.16070","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/2410.16070/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":"2410.16070","created_at":"2026-07-05T09:24:01.889448+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.16070v2","created_at":"2026-07-05T09:24:01.889448+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.16070","created_at":"2026-07-05T09:24:01.889448+00:00"},{"alias_kind":"pith_short_12","alias_value":"5QOBB6N4SUZR","created_at":"2026-07-05T09:24:01.889448+00:00"},{"alias_kind":"pith_short_16","alias_value":"5QOBB6N4SUZR2EV2","created_at":"2026-07-05T09:24:01.889448+00:00"},{"alias_kind":"pith_short_8","alias_value":"5QOBB6N4","created_at":"2026-07-05T09:24:01.889448+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.28843","citing_title":"The Heterogeneous Safety Impacts of Benign Multilingual Fine-Tuning","ref_index":33,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF","json":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF.json","graph_json":"https://pith.science/api/pith-number/5QOBB6N4SUZR2EV22ONLRYYRBF/graph.json","events_json":"https://pith.science/api/pith-number/5QOBB6N4SUZR2EV22ONLRYYRBF/events.json","paper":"https://pith.science/paper/5QOBB6N4"},"agent_actions":{"view_html":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF","download_json":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF.json","view_paper":"https://pith.science/paper/5QOBB6N4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.16070&json=true","fetch_graph":"https://pith.science/api/pith-number/5QOBB6N4SUZR2EV22ONLRYYRBF/graph.json","fetch_events":"https://pith.science/api/pith-number/5QOBB6N4SUZR2EV22ONLRYYRBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF/action/storage_attestation","attest_author":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF/action/author_attestation","sign_citation":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF/action/citation_signature","submit_replication":"https://pith.science/pith/5QOBB6N4SUZR2EV22ONLRYYRBF/action/replication_record"}},"created_at":"2026-07-05T09:24:01.889448+00:00","updated_at":"2026-07-05T09:24:01.889448+00:00"}