{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LHLUCE23AIIF7MBAHZXI7HJSXZ","short_pith_number":"pith:LHLUCE23","schema_version":"1.0","canonical_sha256":"59d741135b02105fb0203e6e8f9d32be4a6975c28870375db758fbd8dc1bfe87","source":{"kind":"arxiv","id":"2607.13068","version":1},"attestation_state":"computed","paper":{"title":"The Economics of AI Decoding Chips: Rebalancing Compute, Capacity, and Bandwidth for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Ju Long, Michael J. Yuan","submitted_at":"2026-07-10T23:33:57Z","abstract_excerpt":"Every mainstream GPU is built compute-heavy and capacity-light: it pairs enormous arithmetic throughput with too little memory to hold a modern model. In contrast, large language model decoding requires little compute and a large amount of memory: a GPU's floating-point units run at single-digit-percent utilization during decoding, and the memory the workload does need is sold only bundled with yet more compute. The compute is recovered only at hyperscale, where Mixture-of-Experts (MoE) models are spread across 96--320-GPU expert-parallel clusters serving thousands of concurrent users, a scale"},"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":"2607.13068","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AR","submitted_at":"2026-07-10T23:33:57Z","cross_cats_sorted":[],"title_canon_sha256":"ffb2f956a8eaea4a6fa7388f2de238971163bf5179d6104d787c365aeb5af8ff","abstract_canon_sha256":"cd5c13fff590a594e7ccd0790bfc504c90b8d49b57e82248c198a405c9fe523b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-16T00:21:54.392187Z","signature_b64":"7B6mkuaoSHCDWe0lAWFkKExmF8dqPuqftrJcrLe8QiGXpQ9D5Qc9YwUFNchr3Zr5vE80axBDB7pWSGo8vlZTCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"59d741135b02105fb0203e6e8f9d32be4a6975c28870375db758fbd8dc1bfe87","last_reissued_at":"2026-07-16T00:21:54.391305Z","signature_status":"signed_v1","first_computed_at":"2026-07-16T00:21:54.391305Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"The Economics of AI Decoding Chips: Rebalancing Compute, Capacity, and Bandwidth for Efficient LLM Inference","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Ju Long, Michael J. Yuan","submitted_at":"2026-07-10T23:33:57Z","abstract_excerpt":"Every mainstream GPU is built compute-heavy and capacity-light: it pairs enormous arithmetic throughput with too little memory to hold a modern model. In contrast, large language model decoding requires little compute and a large amount of memory: a GPU's floating-point units run at single-digit-percent utilization during decoding, and the memory the workload does need is sold only bundled with yet more compute. The compute is recovered only at hyperscale, where Mixture-of-Experts (MoE) models are spread across 96--320-GPU expert-parallel clusters serving thousands of concurrent users, a scale"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.13068","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/2607.13068/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":"2607.13068","created_at":"2026-07-16T00:21:54.391771+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.13068v1","created_at":"2026-07-16T00:21:54.391771+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.13068","created_at":"2026-07-16T00:21:54.391771+00:00"},{"alias_kind":"pith_short_12","alias_value":"LHLUCE23AIIF","created_at":"2026-07-16T00:21:54.391771+00:00"},{"alias_kind":"pith_short_16","alias_value":"LHLUCE23AIIF7MBA","created_at":"2026-07-16T00:21:54.391771+00:00"},{"alias_kind":"pith_short_8","alias_value":"LHLUCE23","created_at":"2026-07-16T00:21:54.391771+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ","json":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ.json","graph_json":"https://pith.science/api/pith-number/LHLUCE23AIIF7MBAHZXI7HJSXZ/graph.json","events_json":"https://pith.science/api/pith-number/LHLUCE23AIIF7MBAHZXI7HJSXZ/events.json","paper":"https://pith.science/paper/LHLUCE23"},"agent_actions":{"view_html":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ","download_json":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ.json","view_paper":"https://pith.science/paper/LHLUCE23","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.13068&json=true","fetch_graph":"https://pith.science/api/pith-number/LHLUCE23AIIF7MBAHZXI7HJSXZ/graph.json","fetch_events":"https://pith.science/api/pith-number/LHLUCE23AIIF7MBAHZXI7HJSXZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ/action/storage_attestation","attest_author":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ/action/author_attestation","sign_citation":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ/action/citation_signature","submit_replication":"https://pith.science/pith/LHLUCE23AIIF7MBAHZXI7HJSXZ/action/replication_record"}},"created_at":"2026-07-16T00:21:54.391771+00:00","updated_at":"2026-07-16T00:21:54.391771+00:00"}