{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2019:MFB4YH5ROE256JUPXCULHXXWFK","short_pith_number":"pith:MFB4YH5R","schema_version":"1.0","canonical_sha256":"6143cc1fb17135df268fb8a8b3def62ab690d71bde63ee38e3f0d1d98e955fd2","source":{"kind":"arxiv","id":"1903.00045","version":2},"attestation_state":"computed","paper":{"title":"Speeding up Deep Learning with Transient Servers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC","cs.LG"],"primary_cat":"cs.PF","authors_text":"Lijie Xu, Robert J. Walls, Shijian Li, Tian Guo","submitted_at":"2019-02-28T19:47:59Z","abstract_excerpt":"Distributed training frameworks, like TensorFlow, have been proposed as a means to reduce the training time of deep learning models by using a cluster of GPU servers. While such speedups are often desirable---e.g., for rapidly evaluating new model designs---they often come with significantly higher monetary costs due to sublinear scalability. In this paper, we investigate the feasibility of using training clusters composed of cheaper transient GPU servers to get the benefits of distributed training without the high costs.\n  We conduct the first large-scale empirical analysis, launching more th"},"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":"1903.00045","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.PF","submitted_at":"2019-02-28T19:47:59Z","cross_cats_sorted":["cs.CV","cs.DC","cs.LG"],"title_canon_sha256":"3bf3116cb5c0f562930f67af3026e070c0b77000bc9d950ccf18216f568c8ea6","abstract_canon_sha256":"8f4cfc9b51640faa055eb7a73131ea6650ad97b2d37e27e6738463d7bfebe75c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:47:01.730905Z","signature_b64":"0MGndNNYUHM5UR31MMNX2zy9eo8bZcT4CY1W3X4K0UGfdd9UierQBvqJPgZInN+wJ9VPrW0728W18DoaDawtCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6143cc1fb17135df268fb8a8b3def62ab690d71bde63ee38e3f0d1d98e955fd2","last_reissued_at":"2026-05-17T23:47:01.730248Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:47:01.730248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Speeding up Deep Learning with Transient Servers","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.DC","cs.LG"],"primary_cat":"cs.PF","authors_text":"Lijie Xu, Robert J. Walls, Shijian Li, Tian Guo","submitted_at":"2019-02-28T19:47:59Z","abstract_excerpt":"Distributed training frameworks, like TensorFlow, have been proposed as a means to reduce the training time of deep learning models by using a cluster of GPU servers. While such speedups are often desirable---e.g., for rapidly evaluating new model designs---they often come with significantly higher monetary costs due to sublinear scalability. In this paper, we investigate the feasibility of using training clusters composed of cheaper transient GPU servers to get the benefits of distributed training without the high costs.\n  We conduct the first large-scale empirical analysis, launching more th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1903.00045","kind":"arxiv","version":2},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1903.00045","created_at":"2026-05-17T23:47:01.730380+00:00"},{"alias_kind":"arxiv_version","alias_value":"1903.00045v2","created_at":"2026-05-17T23:47:01.730380+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1903.00045","created_at":"2026-05-17T23:47:01.730380+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFB4YH5ROE25","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFB4YH5ROE256JUP","created_at":"2026-05-18T12:33:21.387695+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFB4YH5R","created_at":"2026-05-18T12:33:21.387695+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/MFB4YH5ROE256JUPXCULHXXWFK","json":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK.json","graph_json":"https://pith.science/api/pith-number/MFB4YH5ROE256JUPXCULHXXWFK/graph.json","events_json":"https://pith.science/api/pith-number/MFB4YH5ROE256JUPXCULHXXWFK/events.json","paper":"https://pith.science/paper/MFB4YH5R"},"agent_actions":{"view_html":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK","download_json":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK.json","view_paper":"https://pith.science/paper/MFB4YH5R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1903.00045&json=true","fetch_graph":"https://pith.science/api/pith-number/MFB4YH5ROE256JUPXCULHXXWFK/graph.json","fetch_events":"https://pith.science/api/pith-number/MFB4YH5ROE256JUPXCULHXXWFK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK/action/storage_attestation","attest_author":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK/action/author_attestation","sign_citation":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK/action/citation_signature","submit_replication":"https://pith.science/pith/MFB4YH5ROE256JUPXCULHXXWFK/action/replication_record"}},"created_at":"2026-05-17T23:47:01.730380+00:00","updated_at":"2026-05-17T23:47:01.730380+00:00"}