{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:A7TKVI2IPBOTV26LRRJKPZ7Z4X","short_pith_number":"pith:A7TKVI2I","schema_version":"1.0","canonical_sha256":"07e6aaa348785d3aebcb8c52a7e7f9e5cb5c73a7761089c38196f2af5ae313e2","source":{"kind":"arxiv","id":"2503.11698","version":1},"attestation_state":"computed","paper":{"title":"A Comparison of the Cerebras Wafer-Scale Integration Technology with Nvidia GPU-based Systems for Artificial Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Kriti Kumar, Manish Arora, Manroop Kaur, Pushpanjali Kumari, Tripty Wig, Vivek Puri, Yudhishthira Kundu","submitted_at":"2025-03-11T22:57:42Z","abstract_excerpt":"Cerebras' wafer-scale engine (WSE) technology merges multiple dies on a single wafer. It addresses the challenges of memory bandwidth, latency, and scalability, making it suitable for artificial intelligence. This work evaluates the WSE-3 architecture and compares it with leading GPU-based AI accelerators, notably Nvidia's H100 and B200. The work highlights the advantages of WSE-3 in performance per watt and memory scalability and provides insights into the challenges in manufacturing, thermal management, and reliability. The results suggest that wafer-scale integration can surpass conventiona"},"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":"2503.11698","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AR","submitted_at":"2025-03-11T22:57:42Z","cross_cats_sorted":[],"title_canon_sha256":"cd7a41638b6a1b0d80974d9986c003e38f25fcff7968e0e74d7ed69565d25121","abstract_canon_sha256":"88f58b89e853ae0c29f02d803cd8966cf7d786e72b251c26823af1d1e0d2d960"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:31:58.283865Z","signature_b64":"7juntm7jT7n0xlJpYN+M+ixhHaoKbsLPjWk35c7QfLGM3WHZ96zOm736PWsm6AK9Pw/XdD5naLetEZhUq8KdBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07e6aaa348785d3aebcb8c52a7e7f9e5cb5c73a7761089c38196f2af5ae313e2","last_reissued_at":"2026-07-05T10:31:58.282978Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:31:58.282978Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Comparison of the Cerebras Wafer-Scale Integration Technology with Nvidia GPU-based Systems for Artificial Intelligence","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AR","authors_text":"Kriti Kumar, Manish Arora, Manroop Kaur, Pushpanjali Kumari, Tripty Wig, Vivek Puri, Yudhishthira Kundu","submitted_at":"2025-03-11T22:57:42Z","abstract_excerpt":"Cerebras' wafer-scale engine (WSE) technology merges multiple dies on a single wafer. It addresses the challenges of memory bandwidth, latency, and scalability, making it suitable for artificial intelligence. This work evaluates the WSE-3 architecture and compares it with leading GPU-based AI accelerators, notably Nvidia's H100 and B200. The work highlights the advantages of WSE-3 in performance per watt and memory scalability and provides insights into the challenges in manufacturing, thermal management, and reliability. The results suggest that wafer-scale integration can surpass conventiona"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.11698","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/2503.11698/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":"2503.11698","created_at":"2026-07-05T10:31:58.283132+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.11698v1","created_at":"2026-07-05T10:31:58.283132+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.11698","created_at":"2026-07-05T10:31:58.283132+00:00"},{"alias_kind":"pith_short_12","alias_value":"A7TKVI2IPBOT","created_at":"2026-07-05T10:31:58.283132+00:00"},{"alias_kind":"pith_short_16","alias_value":"A7TKVI2IPBOTV26L","created_at":"2026-07-05T10:31:58.283132+00:00"},{"alias_kind":"pith_short_8","alias_value":"A7TKVI2I","created_at":"2026-07-05T10:31:58.283132+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2511.09447","citing_title":"SpaDA: A Spatial Dataflow Architecture Programming Language","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X","json":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X.json","graph_json":"https://pith.science/api/pith-number/A7TKVI2IPBOTV26LRRJKPZ7Z4X/graph.json","events_json":"https://pith.science/api/pith-number/A7TKVI2IPBOTV26LRRJKPZ7Z4X/events.json","paper":"https://pith.science/paper/A7TKVI2I"},"agent_actions":{"view_html":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X","download_json":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X.json","view_paper":"https://pith.science/paper/A7TKVI2I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.11698&json=true","fetch_graph":"https://pith.science/api/pith-number/A7TKVI2IPBOTV26LRRJKPZ7Z4X/graph.json","fetch_events":"https://pith.science/api/pith-number/A7TKVI2IPBOTV26LRRJKPZ7Z4X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X/action/storage_attestation","attest_author":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X/action/author_attestation","sign_citation":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X/action/citation_signature","submit_replication":"https://pith.science/pith/A7TKVI2IPBOTV26LRRJKPZ7Z4X/action/replication_record"}},"created_at":"2026-07-05T10:31:58.283132+00:00","updated_at":"2026-07-05T10:31:58.283132+00:00"}