{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FIRE6HC3DFZXCRY3P6IYYNZRFL","short_pith_number":"pith:FIRE6HC3","schema_version":"1.0","canonical_sha256":"2a224f1c5b197371471b7f918c37312af09f71af35a428754ca36464edcdb4cd","source":{"kind":"arxiv","id":"2501.14784","version":1},"attestation_state":"computed","paper":{"title":"DeServe: Towards Affordable Offline LLM Inference via Decentralization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Dawn Song, Linyu Wu, Tianneng Shi, Xiaoyuan Liu, Zhe Ye","submitted_at":"2025-01-04T02:10:50Z","abstract_excerpt":"The rapid growth of generative AI and its integration into everyday workflows have significantly increased the demand for large language model (LLM) inference services. While proprietary models remain popular, recent advancements in open-source LLMs have positioned them as strong contenders. However, deploying these models is often constrained by the high costs and limited availability of GPU resources. In response, this paper presents the design of a decentralized offline serving system for LLM inference. Utilizing idle GPU resources, our proposed system, DeServe, decentralizes access to LLMs"},"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":"2501.14784","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2025-01-04T02:10:50Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"fc1c3d8ad005b6e0fab0081882ec839b8d04cbd2b241a4ae31664c8bfc7f7fef","abstract_canon_sha256":"cff739881e3217a48c1b5a08c1834d98de7e8fa4adaa4830b12d7f37be357531"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:05:18.387696Z","signature_b64":"S8+uFdxnKGy/E7IcaYEBRk3SLj4v/NW0LxVN0UczQFeQp0kIt7lbL5OO2jQsb+rbEaZGb2JhDb9Dv4kRsqqiBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2a224f1c5b197371471b7f918c37312af09f71af35a428754ca36464edcdb4cd","last_reissued_at":"2026-07-05T10:05:18.387235Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:05:18.387235Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DeServe: Towards Affordable Offline LLM Inference via Decentralization","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DC","authors_text":"Dawn Song, Linyu Wu, Tianneng Shi, Xiaoyuan Liu, Zhe Ye","submitted_at":"2025-01-04T02:10:50Z","abstract_excerpt":"The rapid growth of generative AI and its integration into everyday workflows have significantly increased the demand for large language model (LLM) inference services. While proprietary models remain popular, recent advancements in open-source LLMs have positioned them as strong contenders. However, deploying these models is often constrained by the high costs and limited availability of GPU resources. In response, this paper presents the design of a decentralized offline serving system for LLM inference. Utilizing idle GPU resources, our proposed system, DeServe, decentralizes access to LLMs"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.14784","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/2501.14784/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":"2501.14784","created_at":"2026-07-05T10:05:18.387292+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.14784v1","created_at":"2026-07-05T10:05:18.387292+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.14784","created_at":"2026-07-05T10:05:18.387292+00:00"},{"alias_kind":"pith_short_12","alias_value":"FIRE6HC3DFZX","created_at":"2026-07-05T10:05:18.387292+00:00"},{"alias_kind":"pith_short_16","alias_value":"FIRE6HC3DFZXCRY3","created_at":"2026-07-05T10:05:18.387292+00:00"},{"alias_kind":"pith_short_8","alias_value":"FIRE6HC3","created_at":"2026-07-05T10:05:18.387292+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2601.21972","citing_title":"Learning Decentralized LLM Collaboration with Multi-Agent Actor Critic","ref_index":32,"is_internal_anchor":false},{"citing_arxiv_id":"2604.21072","citing_title":"Distributed Generative Inference of LLM at Internet Scales with Multi-Dimensional Communication Optimization","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL","json":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL.json","graph_json":"https://pith.science/api/pith-number/FIRE6HC3DFZXCRY3P6IYYNZRFL/graph.json","events_json":"https://pith.science/api/pith-number/FIRE6HC3DFZXCRY3P6IYYNZRFL/events.json","paper":"https://pith.science/paper/FIRE6HC3"},"agent_actions":{"view_html":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL","download_json":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL.json","view_paper":"https://pith.science/paper/FIRE6HC3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.14784&json=true","fetch_graph":"https://pith.science/api/pith-number/FIRE6HC3DFZXCRY3P6IYYNZRFL/graph.json","fetch_events":"https://pith.science/api/pith-number/FIRE6HC3DFZXCRY3P6IYYNZRFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL/action/storage_attestation","attest_author":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL/action/author_attestation","sign_citation":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL/action/citation_signature","submit_replication":"https://pith.science/pith/FIRE6HC3DFZXCRY3P6IYYNZRFL/action/replication_record"}},"created_at":"2026-07-05T10:05:18.387292+00:00","updated_at":"2026-07-05T10:05:18.387292+00:00"}