{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ESF7GNMRLKBX55VG5ZCB5DISFO","short_pith_number":"pith:ESF7GNMR","schema_version":"1.0","canonical_sha256":"248bf335915a837ef6a6ee441e8d122bb3f57f1b2b38be0263c91fde71fcd57a","source":{"kind":"arxiv","id":"2410.10759","version":2},"attestation_state":"computed","paper":{"title":"SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NI"],"primary_cat":"cs.DC","authors_text":"Akrit Mudvari, Leandros Tassiulas, Yuang Jiang","submitted_at":"2024-10-14T17:38:41Z","abstract_excerpt":"Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language understanding, information retrieval and search, translation, chatbots, virtual assistance, and many more. However, it is well known that LLMs are massive in terms of the number of parameters. Additionally, the self-attention mechanism in the underlying architecture of LLMs, Transformers, has quadratic complexity in terms of both computation and memory with res"},"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":"2410.10759","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2024-10-14T17:38:41Z","cross_cats_sorted":["cs.LG","cs.NI"],"title_canon_sha256":"03e83c19ce532f901ec8e08d98c5ac7ac026e4e64e253f429231d4ff34428792","abstract_canon_sha256":"df736349a5cd8ffe04b50eee1c9a4b29cc2a55839a5db8bf3d0ab50a18e89f34"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:21:28.879504Z","signature_b64":"5uKRYITJZUP2l77m7FVLogPJ3QyFAf6CkwOq/B1T45aAzwgo1ism1w+uhym5aHtNXz516Mvl+dcFvQhgipFODw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"248bf335915a837ef6a6ee441e8d122bb3f57f1b2b38be0263c91fde71fcd57a","last_reissued_at":"2026-07-05T09:21:28.879023Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:21:28.879023Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SplitLLM: Collaborative Inference of LLMs for Model Placement and Throughput Optimization","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG","cs.NI"],"primary_cat":"cs.DC","authors_text":"Akrit Mudvari, Leandros Tassiulas, Yuang Jiang","submitted_at":"2024-10-14T17:38:41Z","abstract_excerpt":"Large language models (LLMs) have been a disruptive innovation in recent years, and they play a crucial role in our daily lives due to their ability to understand and generate human-like text. Their capabilities include natural language understanding, information retrieval and search, translation, chatbots, virtual assistance, and many more. However, it is well known that LLMs are massive in terms of the number of parameters. Additionally, the self-attention mechanism in the underlying architecture of LLMs, Transformers, has quadratic complexity in terms of both computation and memory with res"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2410.10759","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/2410.10759/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":"2410.10759","created_at":"2026-07-05T09:21:28.879076+00:00"},{"alias_kind":"arxiv_version","alias_value":"2410.10759v2","created_at":"2026-07-05T09:21:28.879076+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2410.10759","created_at":"2026-07-05T09:21:28.879076+00:00"},{"alias_kind":"pith_short_12","alias_value":"ESF7GNMRLKBX","created_at":"2026-07-05T09:21:28.879076+00:00"},{"alias_kind":"pith_short_16","alias_value":"ESF7GNMRLKBX55VG","created_at":"2026-07-05T09:21:28.879076+00:00"},{"alias_kind":"pith_short_8","alias_value":"ESF7GNMR","created_at":"2026-07-05T09:21:28.879076+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.22496","citing_title":"Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing","ref_index":23,"is_internal_anchor":false},{"citing_arxiv_id":"2507.09942","citing_title":"Green-LLM: Optimal Workload Allocation for Environmentally-Aware Distributed Inference","ref_index":6,"is_internal_anchor":false},{"citing_arxiv_id":"2601.11652","citing_title":"WISP: Waste- and Interference-Suppressed Distributed Speculative LLM Serving at the Edge via Dynamic Drafting and SLO-Aware Batching","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22906","citing_title":"Network Edge Inference for Large Language Models: Principles, Techniques, and Opportunities","ref_index":112,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO","json":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO.json","graph_json":"https://pith.science/api/pith-number/ESF7GNMRLKBX55VG5ZCB5DISFO/graph.json","events_json":"https://pith.science/api/pith-number/ESF7GNMRLKBX55VG5ZCB5DISFO/events.json","paper":"https://pith.science/paper/ESF7GNMR"},"agent_actions":{"view_html":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO","download_json":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO.json","view_paper":"https://pith.science/paper/ESF7GNMR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2410.10759&json=true","fetch_graph":"https://pith.science/api/pith-number/ESF7GNMRLKBX55VG5ZCB5DISFO/graph.json","fetch_events":"https://pith.science/api/pith-number/ESF7GNMRLKBX55VG5ZCB5DISFO/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO/action/storage_attestation","attest_author":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO/action/author_attestation","sign_citation":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO/action/citation_signature","submit_replication":"https://pith.science/pith/ESF7GNMRLKBX55VG5ZCB5DISFO/action/replication_record"}},"created_at":"2026-07-05T09:21:28.879076+00:00","updated_at":"2026-07-05T09:21:28.879076+00:00"}