{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:ZPARKLYW2KQ6FOIOF5H6ZCKZUS","short_pith_number":"pith:ZPARKLYW","schema_version":"1.0","canonical_sha256":"cbc1152f16d2a1e2b90e2f4fec8959a496ac0d262e41a33fb756a354a4945985","source":{"kind":"arxiv","id":"1910.01196","version":1},"attestation_state":"computed","paper":{"title":"Accelerating Data Loading in Deep Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.PF","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chih-Chieh Yang, Guojing Cong","submitted_at":"2019-10-02T20:03:02Z","abstract_excerpt":"Data loading can dominate deep neural network training time on large-scale systems. We present a comprehensive study on accelerating data loading performance in large-scale distributed training. We first identify performance and scalability issues in current data loading implementations. We then propose optimizations that utilize CPU resources to the data loader design. We use an analytical model to characterize the impact of data loading on the overall training time and establish the performance trend as we scale up distributed training. Our model suggests that I/O rate limits the scalability"},"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":"1910.01196","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T20:03:02Z","cross_cats_sorted":["cs.DC","cs.PF","stat.ML"],"title_canon_sha256":"32fe04861c50c7eb0add35b3df7ce2df8e91fee5deb85ff6274d8d25bc7cc413","abstract_canon_sha256":"f2c702568cf6725dba7af56297549967f8f027ae48f2c1ad1e426baf61f2e86d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T00:42:20.606782Z","signature_b64":"+VdABDPQfTRKWH2QMTGNDPOGZOISmmoMkn5buWSpKpszDS+gnfOpR5Urhu3USSahIIUWqx36eWECjivmpVNACQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cbc1152f16d2a1e2b90e2f4fec8959a496ac0d262e41a33fb756a354a4945985","last_reissued_at":"2026-07-05T00:42:20.606390Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T00:42:20.606390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Accelerating Data Loading in Deep Neural Network Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC","cs.PF","stat.ML"],"primary_cat":"cs.LG","authors_text":"Chih-Chieh Yang, Guojing Cong","submitted_at":"2019-10-02T20:03:02Z","abstract_excerpt":"Data loading can dominate deep neural network training time on large-scale systems. We present a comprehensive study on accelerating data loading performance in large-scale distributed training. We first identify performance and scalability issues in current data loading implementations. We then propose optimizations that utilize CPU resources to the data loader design. We use an analytical model to characterize the impact of data loading on the overall training time and establish the performance trend as we scale up distributed training. Our model suggests that I/O rate limits the scalability"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.01196","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/1910.01196/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":"1910.01196","created_at":"2026-07-05T00:42:20.606445+00:00"},{"alias_kind":"arxiv_version","alias_value":"1910.01196v1","created_at":"2026-07-05T00:42:20.606445+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01196","created_at":"2026-07-05T00:42:20.606445+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZPARKLYW2KQ6","created_at":"2026-07-05T00:42:20.606445+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZPARKLYW2KQ6FOIO","created_at":"2026-07-05T00:42:20.606445+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZPARKLYW","created_at":"2026-07-05T00:42:20.606445+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/ZPARKLYW2KQ6FOIOF5H6ZCKZUS","json":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS.json","graph_json":"https://pith.science/api/pith-number/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/graph.json","events_json":"https://pith.science/api/pith-number/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/events.json","paper":"https://pith.science/paper/ZPARKLYW"},"agent_actions":{"view_html":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS","download_json":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS.json","view_paper":"https://pith.science/paper/ZPARKLYW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1910.01196&json=true","fetch_graph":"https://pith.science/api/pith-number/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/graph.json","fetch_events":"https://pith.science/api/pith-number/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/action/storage_attestation","attest_author":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/action/author_attestation","sign_citation":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/action/citation_signature","submit_replication":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/action/replication_record"}},"created_at":"2026-07-05T00:42:20.606445+00:00","updated_at":"2026-07-05T00:42:20.606445+00:00"}