{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:J4GJHHESEL7VUGSCFLBXBFSNDB","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"a5c63421109dc17806f34709b7578877408593f08ae27ee92aec027f6790d111","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2021-08-20T21:09:34Z","title_canon_sha256":"bbee943ff96c9452965d8c15f4b36660a5d0859aa31de037a18b853397872cdf"},"schema_version":"1.0","source":{"id":"2108.09373","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2108.09373","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"arxiv_version","alias_value":"2108.09373v4","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2108.09373","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_12","alias_value":"J4GJHHESEL7V","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_16","alias_value":"J4GJHHESEL7VUGSC","created_at":"2026-07-05T04:17:03Z"},{"alias_kind":"pith_short_8","alias_value":"J4GJHHES","created_at":"2026-07-05T04:17:03Z"}],"graph_snapshots":[{"event_id":"sha256:fb896f78f4b90f579dadf15f8957ef8c382136647359f33ad04f3d90dd2cd312","target":"graph","created_at":"2026-07-05T04:17:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2108.09373/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Datacenter-scale AI training clusters consisting of thousands of domain-specific accelerators (DSA) are used to train increasingly-complex deep learning models. These clusters rely on a data storage and ingestion (DSI) pipeline, responsible for storing exabytes of training data and serving it at tens of terabytes per second. As DSAs continue to push training efficiency and throughput, the DSI pipeline is becoming the dominating factor that constrains the overall training performance and capacity. Innovations that improve the efficiency and performance of DSI systems and hardware are urgent, de","authors_text":"Aarti Basant, Bugra Gedik, Carole-Jean Wu, Christos Kozyrakis, Haowei Lu, Harsha Rastogi, Jack Langman, Jerry Pan, Kevin Wilfong, Mark Zhao, Mustafa Ozdal, Niket Agarwal, Parik Pol, Rakesh Komuravelli, Satadru Pan, Sundaram Narayanan, Tianshu Bao","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2021-08-20T21:09:34Z","title":"Understanding Data Storage and Ingestion for Large-Scale Deep Recommendation Model Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2108.09373","kind":"arxiv","version":4},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:9138f6096957e595b9cba8df3f60eaeaa426780ca8dbad0bad0611e5ebbf56be","target":"record","created_at":"2026-07-05T04:17:03Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"a5c63421109dc17806f34709b7578877408593f08ae27ee92aec027f6790d111","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2021-08-20T21:09:34Z","title_canon_sha256":"bbee943ff96c9452965d8c15f4b36660a5d0859aa31de037a18b853397872cdf"},"schema_version":"1.0","source":{"id":"2108.09373","kind":"arxiv","version":4}},"canonical_sha256":"4f0c939c9222ff5a1a422ac370964d1846885590c18d4466caf28dc4a870905e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4f0c939c9222ff5a1a422ac370964d1846885590c18d4466caf28dc4a870905e","first_computed_at":"2026-07-05T04:17:03.170781Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:17:03.170781Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t8ePOewnTqv+lKLD9/eY2QByj0altSPmPmEhFNlvU4IlYUvqOO3jOM2jWMzmOVZW5COxGoC1vNaDhKQE8asACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:17:03.171247Z","signed_message":"canonical_sha256_bytes"},"source_id":"2108.09373","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9138f6096957e595b9cba8df3f60eaeaa426780ca8dbad0bad0611e5ebbf56be","sha256:fb896f78f4b90f579dadf15f8957ef8c382136647359f33ad04f3d90dd2cd312"],"state_sha256":"64be1dc182ccb68f5067c02d588a3744f26513336ddd33ee62cc8fe633b816d7"}