{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:EPBZLOLIB6QR7CNND53BGQHBPS","short_pith_number":"pith:EPBZLOLI","schema_version":"1.0","canonical_sha256":"23c395b9680fa11f89ad1f761340e17ca8a2077688b89bb491cfbf56ebd5ec09","source":{"kind":"arxiv","id":"2309.01640","version":1},"attestation_state":"computed","paper":{"title":"Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eran Malach, Etay Livne, Gal Kaplun, Shai Shalev-Schwatz","submitted_at":"2023-09-04T14:49:27Z","abstract_excerpt":"When using Stochastic Gradient Descent (SGD) for training machine learning models, it is often crucial to provide the model with examples sampled at random from the dataset. However, for large datasets stored in the cloud, random access to individual examples is often costly and inefficient. A recent work \\cite{corgi}, proposed an online shuffling algorithm called CorgiPile, which greatly improves efficiency of data access, at the cost some performance loss, which is particularly apparent for large datasets stored in homogeneous shards (e.g., video datasets). In this paper, we introduce a nove"},"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":"2309.01640","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-09-04T14:49:27Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9ac5f087c8d57a0bce6b7198b8293af6c0c8d3aa175e3d5907270f6363b8ab40","abstract_canon_sha256":"87e4d58a7533a30520ef83006733d09af5581dba5666881dfebfbf8fe6e40acf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:47:56.682924Z","signature_b64":"ljshaNHoyZ6qN3xzEPLJrgMrfRr+WbTbw3A3pYI8xkAivTOfmetXjRpjC9D2UVVvGrQkhuyzv+CQSXXAN41cBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"23c395b9680fa11f89ad1f761340e17ca8a2077688b89bb491cfbf56ebd5ec09","last_reissued_at":"2026-07-05T06:47:56.682441Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:47:56.682441Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Corgi^2: A Hybrid Offline-Online Approach To Storage-Aware Data Shuffling For SGD","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Eran Malach, Etay Livne, Gal Kaplun, Shai Shalev-Schwatz","submitted_at":"2023-09-04T14:49:27Z","abstract_excerpt":"When using Stochastic Gradient Descent (SGD) for training machine learning models, it is often crucial to provide the model with examples sampled at random from the dataset. However, for large datasets stored in the cloud, random access to individual examples is often costly and inefficient. A recent work \\cite{corgi}, proposed an online shuffling algorithm called CorgiPile, which greatly improves efficiency of data access, at the cost some performance loss, which is particularly apparent for large datasets stored in homogeneous shards (e.g., video datasets). In this paper, we introduce a nove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.01640","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/2309.01640/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":"2309.01640","created_at":"2026-07-05T06:47:56.682499+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.01640v1","created_at":"2026-07-05T06:47:56.682499+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.01640","created_at":"2026-07-05T06:47:56.682499+00:00"},{"alias_kind":"pith_short_12","alias_value":"EPBZLOLIB6QR","created_at":"2026-07-05T06:47:56.682499+00:00"},{"alias_kind":"pith_short_16","alias_value":"EPBZLOLIB6QR7CNN","created_at":"2026-07-05T06:47:56.682499+00:00"},{"alias_kind":"pith_short_8","alias_value":"EPBZLOLI","created_at":"2026-07-05T06:47:56.682499+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/EPBZLOLIB6QR7CNND53BGQHBPS","json":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS.json","graph_json":"https://pith.science/api/pith-number/EPBZLOLIB6QR7CNND53BGQHBPS/graph.json","events_json":"https://pith.science/api/pith-number/EPBZLOLIB6QR7CNND53BGQHBPS/events.json","paper":"https://pith.science/paper/EPBZLOLI"},"agent_actions":{"view_html":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS","download_json":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS.json","view_paper":"https://pith.science/paper/EPBZLOLI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.01640&json=true","fetch_graph":"https://pith.science/api/pith-number/EPBZLOLIB6QR7CNND53BGQHBPS/graph.json","fetch_events":"https://pith.science/api/pith-number/EPBZLOLIB6QR7CNND53BGQHBPS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS/action/storage_attestation","attest_author":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS/action/author_attestation","sign_citation":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS/action/citation_signature","submit_replication":"https://pith.science/pith/EPBZLOLIB6QR7CNND53BGQHBPS/action/replication_record"}},"created_at":"2026-07-05T06:47:56.682499+00:00","updated_at":"2026-07-05T06:47:56.682499+00:00"}