{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MNLMC4QLDCBT36FTVCIQ3RILFU","short_pith_number":"pith:MNLMC4QL","schema_version":"1.0","canonical_sha256":"6356c1720b18833df8b3a8910dc50b2d12b9228a8694bb1343e0c396dc835047","source":{"kind":"arxiv","id":"2405.17147","version":1},"attestation_state":"computed","paper":{"title":"Large Language Models (LLMs): Deployment, Tokenomics and Sustainability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Haiwei Dong, Shuang Xie","submitted_at":"2024-05-27T13:16:29Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has significantly impacted human-computer interaction, epitomized by the release of GPT-4o, which introduced comprehensive multi-modality capabilities. In this paper, we first explored the deployment strategies, economic considerations, and sustainability challenges associated with the state-of-the-art LLMs. More specifically, we discussed the deployment debate between Retrieval-Augmented Generation (RAG) and fine-tuning, highlighting their respective advantages and limitations. After that, we quantitatively analyzed the requirement of xPUs"},"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":"2405.17147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.MM","submitted_at":"2024-05-27T13:16:29Z","cross_cats_sorted":[],"title_canon_sha256":"adeff9e59e16231a2e687bef577b2d546c4b47bbb8c164439c97dc038afb8af3","abstract_canon_sha256":"ffa097652f0cd2842b773bc6520dc85877135928d43cc75bc9287ef47ac93007"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:23:40.521015Z","signature_b64":"apISMYvPKcVcSelJYZNEGivJvmJH04SvwL2hVj8/Xa2x80kkA/0cNjc4Y9Ytvp8r1a2GxzNSjfeZ/NBfUyj3Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6356c1720b18833df8b3a8910dc50b2d12b9228a8694bb1343e0c396dc835047","last_reissued_at":"2026-07-05T08:23:40.520609Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:23:40.520609Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Large Language Models (LLMs): Deployment, Tokenomics and Sustainability","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.MM","authors_text":"Haiwei Dong, Shuang Xie","submitted_at":"2024-05-27T13:16:29Z","abstract_excerpt":"The rapid advancement of Large Language Models (LLMs) has significantly impacted human-computer interaction, epitomized by the release of GPT-4o, which introduced comprehensive multi-modality capabilities. In this paper, we first explored the deployment strategies, economic considerations, and sustainability challenges associated with the state-of-the-art LLMs. More specifically, we discussed the deployment debate between Retrieval-Augmented Generation (RAG) and fine-tuning, highlighting their respective advantages and limitations. After that, we quantitatively analyzed the requirement of xPUs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.17147","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/2405.17147/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":"2405.17147","created_at":"2026-07-05T08:23:40.520667+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.17147v1","created_at":"2026-07-05T08:23:40.520667+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.17147","created_at":"2026-07-05T08:23:40.520667+00:00"},{"alias_kind":"pith_short_12","alias_value":"MNLMC4QLDCBT","created_at":"2026-07-05T08:23:40.520667+00:00"},{"alias_kind":"pith_short_16","alias_value":"MNLMC4QLDCBT36FT","created_at":"2026-07-05T08:23:40.520667+00:00"},{"alias_kind":"pith_short_8","alias_value":"MNLMC4QL","created_at":"2026-07-05T08:23:40.520667+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.10177","citing_title":"Detoxify: A framework for abusive text transformation using LLMs","ref_index":24,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU","json":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU.json","graph_json":"https://pith.science/api/pith-number/MNLMC4QLDCBT36FTVCIQ3RILFU/graph.json","events_json":"https://pith.science/api/pith-number/MNLMC4QLDCBT36FTVCIQ3RILFU/events.json","paper":"https://pith.science/paper/MNLMC4QL"},"agent_actions":{"view_html":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU","download_json":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU.json","view_paper":"https://pith.science/paper/MNLMC4QL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.17147&json=true","fetch_graph":"https://pith.science/api/pith-number/MNLMC4QLDCBT36FTVCIQ3RILFU/graph.json","fetch_events":"https://pith.science/api/pith-number/MNLMC4QLDCBT36FTVCIQ3RILFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU/action/storage_attestation","attest_author":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU/action/author_attestation","sign_citation":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU/action/citation_signature","submit_replication":"https://pith.science/pith/MNLMC4QLDCBT36FTVCIQ3RILFU/action/replication_record"}},"created_at":"2026-07-05T08:23:40.520667+00:00","updated_at":"2026-07-05T08:23:40.520667+00:00"}