{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:5MRNOJGPXFZ52KYWGV3LG2RTXA","short_pith_number":"pith:5MRNOJGP","schema_version":"1.0","canonical_sha256":"eb22d724cfb973dd2b163576b36a33b804119b05542ab4214f481f3eeff2c2d2","source":{"kind":"arxiv","id":"1709.03316","version":1},"attestation_state":"computed","paper":{"title":"What does fault tolerant Deep Learning need from MPI?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Abhinav Vishnu, Charles Siegel, Jeff Daily, Vinay Amatya","submitted_at":"2017-09-11T10:08:24Z","abstract_excerpt":"Deep Learning (DL) algorithms have become the de facto Machine Learning (ML) algorithm for large scale data analysis. DL algorithms are computationally expensive - even distributed DL implementations which use MPI require days of training (model learning) time on commonly studied datasets. Long running DL applications become susceptible to faults - requiring development of a fault tolerant system infrastructure, in addition to fault tolerant DL algorithms. This raises an important question: What is needed from MPI for de- signing fault tolerant DL implementations? In this paper, we address thi"},"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":"1709.03316","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-09-11T10:08:24Z","cross_cats_sorted":[],"title_canon_sha256":"eb9be2f3dcb4f0711cd8d00638caf5bee486daeff01b8f1b46688a5028139658","abstract_canon_sha256":"ddc6197cf07de12f36570d535cb4c238e51ef26ce3dc3aaceefbfa1e7234d2b0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:35:38.760146Z","signature_b64":"qBD4dyFUvVHIyVfRm6o+7rHQQ108ps6kzhb9ysYzhgKSbrA4mnVcLbKZPFlapteDcjTXc0jazsF45APfcM5wBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"eb22d724cfb973dd2b163576b36a33b804119b05542ab4214f481f3eeff2c2d2","last_reissued_at":"2026-05-18T00:35:38.759548Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:35:38.759548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"What does fault tolerant Deep Learning need from MPI?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.DC","authors_text":"Abhinav Vishnu, Charles Siegel, Jeff Daily, Vinay Amatya","submitted_at":"2017-09-11T10:08:24Z","abstract_excerpt":"Deep Learning (DL) algorithms have become the de facto Machine Learning (ML) algorithm for large scale data analysis. DL algorithms are computationally expensive - even distributed DL implementations which use MPI require days of training (model learning) time on commonly studied datasets. Long running DL applications become susceptible to faults - requiring development of a fault tolerant system infrastructure, in addition to fault tolerant DL algorithms. This raises an important question: What is needed from MPI for de- signing fault tolerant DL implementations? In this paper, we address thi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03316","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":""},"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":"1709.03316","created_at":"2026-05-18T00:35:38.759639+00:00"},{"alias_kind":"arxiv_version","alias_value":"1709.03316v1","created_at":"2026-05-18T00:35:38.759639+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03316","created_at":"2026-05-18T00:35:38.759639+00:00"},{"alias_kind":"pith_short_12","alias_value":"5MRNOJGPXFZ5","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"5MRNOJGPXFZ52KYW","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"5MRNOJGP","created_at":"2026-05-18T12:31:00.734936+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/5MRNOJGPXFZ52KYWGV3LG2RTXA","json":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA.json","graph_json":"https://pith.science/api/pith-number/5MRNOJGPXFZ52KYWGV3LG2RTXA/graph.json","events_json":"https://pith.science/api/pith-number/5MRNOJGPXFZ52KYWGV3LG2RTXA/events.json","paper":"https://pith.science/paper/5MRNOJGP"},"agent_actions":{"view_html":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA","download_json":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA.json","view_paper":"https://pith.science/paper/5MRNOJGP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1709.03316&json=true","fetch_graph":"https://pith.science/api/pith-number/5MRNOJGPXFZ52KYWGV3LG2RTXA/graph.json","fetch_events":"https://pith.science/api/pith-number/5MRNOJGPXFZ52KYWGV3LG2RTXA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA/action/storage_attestation","attest_author":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA/action/author_attestation","sign_citation":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA/action/citation_signature","submit_replication":"https://pith.science/pith/5MRNOJGPXFZ52KYWGV3LG2RTXA/action/replication_record"}},"created_at":"2026-05-18T00:35:38.759639+00:00","updated_at":"2026-05-18T00:35:38.759639+00:00"}