{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:GXBCZPFZ6V735YYJPINJDZTDQS","short_pith_number":"pith:GXBCZPFZ","schema_version":"1.0","canonical_sha256":"35c22cbcb9f57fbee3097a1a91e663849bc545623d84a34db4bdb190c2bc580e","source":{"kind":"arxiv","id":"2307.02666","version":4},"attestation_state":"computed","paper":{"title":"Chiplet Cloud: Building AI Supercomputers for Serving Large Generative Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Huwan Peng, Michael Taylor, Richard Shi, Scott Davidson, Shuaiwen Leon Song","submitted_at":"2023-07-05T21:42:24Z","abstract_excerpt":"Large language models (LLMs) such as OpenAI's ChatGPT and Google's Gemini have demonstrated unprecedented capabilities of autoregressive AI models across multiple tasks triggering disruptive technology innovations around the world. However, as models continue to grow the cost to serve these models also continues to grow threatening the democratization of LLMs.\n  To address this issue, we propose Chiplet Cloud, a chiplet-based ASIC LLM-supercomputer architecture whose goal is to optimize the total cost of ownership (TCO) per generated token. This architecture is a highly parameterizable ASIC an"},"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":"2307.02666","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2023-07-05T21:42:24Z","cross_cats_sorted":[],"title_canon_sha256":"d44bc85d47242274cb1d5ff149e4e605192477edf9abec194261031e4fc6c796","abstract_canon_sha256":"1bdd81ac6440f8209ebf63c581050f0015e74f01b2ce9a54c9f4354ed2e1d68a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:21:05.585691Z","signature_b64":"ap08v7Ck8OdD7JbboV5FOu6bTItnIYENmoyha3paD5NT2xOidIQ/Nh6oW+N3tonSrEFasZI2TE0X050kaOJIDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"35c22cbcb9f57fbee3097a1a91e663849bc545623d84a34db4bdb190c2bc580e","last_reissued_at":"2026-07-05T08:21:05.585215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:21:05.585215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Chiplet Cloud: Building AI Supercomputers for Serving Large Generative Language Models","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Huwan Peng, Michael Taylor, Richard Shi, Scott Davidson, Shuaiwen Leon Song","submitted_at":"2023-07-05T21:42:24Z","abstract_excerpt":"Large language models (LLMs) such as OpenAI's ChatGPT and Google's Gemini have demonstrated unprecedented capabilities of autoregressive AI models across multiple tasks triggering disruptive technology innovations around the world. However, as models continue to grow the cost to serve these models also continues to grow threatening the democratization of LLMs.\n  To address this issue, we propose Chiplet Cloud, a chiplet-based ASIC LLM-supercomputer architecture whose goal is to optimize the total cost of ownership (TCO) per generated token. This architecture is a highly parameterizable ASIC an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2307.02666","kind":"arxiv","version":4},"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/2307.02666/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":"2307.02666","created_at":"2026-07-05T08:21:05.585273+00:00"},{"alias_kind":"arxiv_version","alias_value":"2307.02666v4","created_at":"2026-07-05T08:21:05.585273+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2307.02666","created_at":"2026-07-05T08:21:05.585273+00:00"},{"alias_kind":"pith_short_12","alias_value":"GXBCZPFZ6V73","created_at":"2026-07-05T08:21:05.585273+00:00"},{"alias_kind":"pith_short_16","alias_value":"GXBCZPFZ6V735YYJ","created_at":"2026-07-05T08:21:05.585273+00:00"},{"alias_kind":"pith_short_8","alias_value":"GXBCZPFZ","created_at":"2026-07-05T08:21:05.585273+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.05063","citing_title":"Hardware Design and Security in the Era of Chiplets and LLMs","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS","json":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS.json","graph_json":"https://pith.science/api/pith-number/GXBCZPFZ6V735YYJPINJDZTDQS/graph.json","events_json":"https://pith.science/api/pith-number/GXBCZPFZ6V735YYJPINJDZTDQS/events.json","paper":"https://pith.science/paper/GXBCZPFZ"},"agent_actions":{"view_html":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS","download_json":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS.json","view_paper":"https://pith.science/paper/GXBCZPFZ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2307.02666&json=true","fetch_graph":"https://pith.science/api/pith-number/GXBCZPFZ6V735YYJPINJDZTDQS/graph.json","fetch_events":"https://pith.science/api/pith-number/GXBCZPFZ6V735YYJPINJDZTDQS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS/action/storage_attestation","attest_author":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS/action/author_attestation","sign_citation":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS/action/citation_signature","submit_replication":"https://pith.science/pith/GXBCZPFZ6V735YYJPINJDZTDQS/action/replication_record"}},"created_at":"2026-07-05T08:21:05.585273+00:00","updated_at":"2026-07-05T08:21:05.585273+00:00"}