{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:P26IKHH52BBI365EJZBEMSBOBF","short_pith_number":"pith:P26IKHH5","schema_version":"1.0","canonical_sha256":"7ebc851cfdd0428dfba44e4246482e0960030b4e9e06d8e522d6985af65a445d","source":{"kind":"arxiv","id":"2508.11035","version":1},"attestation_state":"computed","paper":{"title":"EMLIO: Minimizing I/O Latency and Energy Consumption for Large-Scale AI Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hasibul Jamil, MD S Q Zulkar Nine, Tevfik Kosar","submitted_at":"2025-08-14T19:42:59Z","abstract_excerpt":"Large-scale deep learning workloads increasingly suffer from I/O bottlenecks as datasets grow beyond local storage capacities and GPU compute outpaces network and disk latencies. While recent systems optimize data-loading time, they overlook the energy cost of I/O - a critical factor at large scale. We introduce EMLIO, an Efficient Machine Learning I/O service that jointly minimizes end-to-end data-loading latency T and I/O energy consumption E across variable-latency networked storage. EMLIO deploys a lightweight data-serving daemon on storage nodes that serializes and batches raw samples, st"},"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":"2508.11035","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2025-08-14T19:42:59Z","cross_cats_sorted":[],"title_canon_sha256":"c039d2c35e29fb7bb7e57fed7d0a241a636b90ce9ae17142c0ae81576c54bab4","abstract_canon_sha256":"3b44a6ba9a94bf7a981e179aaa0726914e9fc3c8700a501d1dc512d809d67d83"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:54:17.215380Z","signature_b64":"A1++FJwnjG+1pK4FYUc1jBTEAWTSa253A+D2/kCpq691Eo4ygzJZTKS+MNn1zdexzSHF/5rml32PrBLMFztOAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7ebc851cfdd0428dfba44e4246482e0960030b4e9e06d8e522d6985af65a445d","last_reissued_at":"2026-07-05T11:54:17.214925Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:54:17.214925Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"EMLIO: Minimizing I/O Latency and Energy Consumption for Large-Scale AI Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Hasibul Jamil, MD S Q Zulkar Nine, Tevfik Kosar","submitted_at":"2025-08-14T19:42:59Z","abstract_excerpt":"Large-scale deep learning workloads increasingly suffer from I/O bottlenecks as datasets grow beyond local storage capacities and GPU compute outpaces network and disk latencies. While recent systems optimize data-loading time, they overlook the energy cost of I/O - a critical factor at large scale. We introduce EMLIO, an Efficient Machine Learning I/O service that jointly minimizes end-to-end data-loading latency T and I/O energy consumption E across variable-latency networked storage. EMLIO deploys a lightweight data-serving daemon on storage nodes that serializes and batches raw samples, st"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.11035","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/2508.11035/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":"2508.11035","created_at":"2026-07-05T11:54:17.214985+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.11035v1","created_at":"2026-07-05T11:54:17.214985+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.11035","created_at":"2026-07-05T11:54:17.214985+00:00"},{"alias_kind":"pith_short_12","alias_value":"P26IKHH52BBI","created_at":"2026-07-05T11:54:17.214985+00:00"},{"alias_kind":"pith_short_16","alias_value":"P26IKHH52BBI365E","created_at":"2026-07-05T11:54:17.214985+00:00"},{"alias_kind":"pith_short_8","alias_value":"P26IKHH5","created_at":"2026-07-05T11:54:17.214985+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/P26IKHH52BBI365EJZBEMSBOBF","json":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF.json","graph_json":"https://pith.science/api/pith-number/P26IKHH52BBI365EJZBEMSBOBF/graph.json","events_json":"https://pith.science/api/pith-number/P26IKHH52BBI365EJZBEMSBOBF/events.json","paper":"https://pith.science/paper/P26IKHH5"},"agent_actions":{"view_html":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF","download_json":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF.json","view_paper":"https://pith.science/paper/P26IKHH5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.11035&json=true","fetch_graph":"https://pith.science/api/pith-number/P26IKHH52BBI365EJZBEMSBOBF/graph.json","fetch_events":"https://pith.science/api/pith-number/P26IKHH52BBI365EJZBEMSBOBF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF/action/storage_attestation","attest_author":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF/action/author_attestation","sign_citation":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF/action/citation_signature","submit_replication":"https://pith.science/pith/P26IKHH52BBI365EJZBEMSBOBF/action/replication_record"}},"created_at":"2026-07-05T11:54:17.214985+00:00","updated_at":"2026-07-05T11:54:17.214985+00:00"}