{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:ZPARKLYW2KQ6FOIOF5H6ZCKZUS","short_pith_number":"pith:ZPARKLYW","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"},"canonical_sha256":"cbc1152f16d2a1e2b90e2f4fec8959a496ac0d262e41a33fb756a354a4945985","source":{"kind":"arxiv","id":"1910.01196","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.01196","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"arxiv_version","alias_value":"1910.01196v1","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01196","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZPARKLYW2KQ6","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZPARKLYW2KQ6FOIO","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZPARKLYW","created_at":"2026-07-05T00:42:20Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:ZPARKLYW2KQ6FOIOF5H6ZCKZUS","target":"record","payload":{"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"},"canonical_sha256":"cbc1152f16d2a1e2b90e2f4fec8959a496ac0d262e41a33fb756a354a4945985","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"},"source_kind":"arxiv","source_id":"1910.01196","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:42:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LaE8EvpSnDk7VKDC9Qq+m6uGgDII+XnuYOuzBJMDutWL9BPsJSL8dzeCr5zCRmagDOEKRPjJTQycRiItG7DnDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:36:53.632282Z"},"content_sha256":"53a768a9ce55243fa4097b1dcc50e1ad9800e7b26dd724eabb535646bed773fe","schema_version":"1.0","event_id":"sha256:53a768a9ce55243fa4097b1dcc50e1ad9800e7b26dd724eabb535646bed773fe"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:ZPARKLYW2KQ6FOIOF5H6ZCKZUS","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T00:42:20Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aVQSnI6HQ0mYPLQPrYahBjQfzv5y5NvY/clhArqcOinAJQ05WgqUlga53Hu2z1tJ+2bPGs+sa1kWRBFeL2elAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-11T19:36:53.632753Z"},"content_sha256":"f19f165086c4b7228c1d626725048bc5a0664324f7159d726a145bc73aac07f6","schema_version":"1.0","event_id":"sha256:f19f165086c4b7228c1d626725048bc5a0664324f7159d726a145bc73aac07f6"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/bundle.json","state_url":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-11T19:36:53Z","links":{"resolver":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS","bundle":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/bundle.json","state":"https://pith.science/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZPARKLYW2KQ6FOIOF5H6ZCKZUS/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:ZPARKLYW2KQ6FOIOF5H6ZCKZUS","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":"f2c702568cf6725dba7af56297549967f8f027ae48f2c1ad1e426baf61f2e86d","cross_cats_sorted":["cs.DC","cs.PF","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T20:03:02Z","title_canon_sha256":"32fe04861c50c7eb0add35b3df7ce2df8e91fee5deb85ff6274d8d25bc7cc413"},"schema_version":"1.0","source":{"id":"1910.01196","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1910.01196","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"arxiv_version","alias_value":"1910.01196v1","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1910.01196","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"pith_short_12","alias_value":"ZPARKLYW2KQ6","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"pith_short_16","alias_value":"ZPARKLYW2KQ6FOIO","created_at":"2026-07-05T00:42:20Z"},{"alias_kind":"pith_short_8","alias_value":"ZPARKLYW","created_at":"2026-07-05T00:42:20Z"}],"graph_snapshots":[{"event_id":"sha256:f19f165086c4b7228c1d626725048bc5a0664324f7159d726a145bc73aac07f6","target":"graph","created_at":"2026-07-05T00:42:20Z","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/1910.01196/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chih-Chieh Yang, Guojing Cong","cross_cats":["cs.DC","cs.PF","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T20:03:02Z","title":"Accelerating Data Loading in Deep Neural Network Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1910.01196","kind":"arxiv","version":1},"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":"sha256:53a768a9ce55243fa4097b1dcc50e1ad9800e7b26dd724eabb535646bed773fe","target":"record","created_at":"2026-07-05T00:42:20Z","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":"f2c702568cf6725dba7af56297549967f8f027ae48f2c1ad1e426baf61f2e86d","cross_cats_sorted":["cs.DC","cs.PF","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2019-10-02T20:03:02Z","title_canon_sha256":"32fe04861c50c7eb0add35b3df7ce2df8e91fee5deb85ff6274d8d25bc7cc413"},"schema_version":"1.0","source":{"id":"1910.01196","kind":"arxiv","version":1}},"canonical_sha256":"cbc1152f16d2a1e2b90e2f4fec8959a496ac0d262e41a33fb756a354a4945985","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cbc1152f16d2a1e2b90e2f4fec8959a496ac0d262e41a33fb756a354a4945985","first_computed_at":"2026-07-05T00:42:20.606390Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T00:42:20.606390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+VdABDPQfTRKWH2QMTGNDPOGZOISmmoMkn5buWSpKpszDS+gnfOpR5Urhu3USSahIIUWqx36eWECjivmpVNACQ==","signature_status":"signed_v1","signed_at":"2026-07-05T00:42:20.606782Z","signed_message":"canonical_sha256_bytes"},"source_id":"1910.01196","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:53a768a9ce55243fa4097b1dcc50e1ad9800e7b26dd724eabb535646bed773fe","sha256:f19f165086c4b7228c1d626725048bc5a0664324f7159d726a145bc73aac07f6"],"state_sha256":"78223af465cc73ac27af6e21f9613fff477ab9fbafadae024e3f165eb521ca1d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uHyzyS4+8uYGvO4LWZzcge8oOSH42N9KIsubVox9fDfSNPnV9c6Hu4j/LlUEBCUBsUs/IeZ21F+i1xuAlfSjCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-11T19:36:53.635908Z","bundle_sha256":"168aedb223f292c3567f2dd7f65c126a4c9793c233891ea01bef0bab7ad93350"}}