{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:5MRNOJGPXFZ52KYWGV3LG2RTXA","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":"ddc6197cf07de12f36570d535cb4c238e51ef26ce3dc3aaceefbfa1e7234d2b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-09-11T10:08:24Z","title_canon_sha256":"eb9be2f3dcb4f0711cd8d00638caf5bee486daeff01b8f1b46688a5028139658"},"schema_version":"1.0","source":{"id":"1709.03316","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1709.03316","created_at":"2026-05-18T00:35:38Z"},{"alias_kind":"arxiv_version","alias_value":"1709.03316v1","created_at":"2026-05-18T00:35:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1709.03316","created_at":"2026-05-18T00:35:38Z"},{"alias_kind":"pith_short_12","alias_value":"5MRNOJGPXFZ5","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"5MRNOJGPXFZ52KYW","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"5MRNOJGP","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:077ecf129efb0bf850aa82dda38a4ddba01b380553735da30fd841ca31b14385","target":"graph","created_at":"2026-05-18T00:35:38Z","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"},"paper":{"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","authors_text":"Abhinav Vishnu, Charles Siegel, Jeff Daily, Vinay Amatya","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-09-11T10:08:24Z","title":"What does fault tolerant Deep Learning need from MPI?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1709.03316","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:a9a7b65b8840abf2ad6ff68d9ebfe244748590dbdfee3e17476a72fe38ce30f6","target":"record","created_at":"2026-05-18T00:35:38Z","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":"ddc6197cf07de12f36570d535cb4c238e51ef26ce3dc3aaceefbfa1e7234d2b0","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2017-09-11T10:08:24Z","title_canon_sha256":"eb9be2f3dcb4f0711cd8d00638caf5bee486daeff01b8f1b46688a5028139658"},"schema_version":"1.0","source":{"id":"1709.03316","kind":"arxiv","version":1}},"canonical_sha256":"eb22d724cfb973dd2b163576b36a33b804119b05542ab4214f481f3eeff2c2d2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"eb22d724cfb973dd2b163576b36a33b804119b05542ab4214f481f3eeff2c2d2","first_computed_at":"2026-05-18T00:35:38.759548Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:35:38.759548Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qBD4dyFUvVHIyVfRm6o+7rHQQ108ps6kzhb9ysYzhgKSbrA4mnVcLbKZPFlapteDcjTXc0jazsF45APfcM5wBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:35:38.760146Z","signed_message":"canonical_sha256_bytes"},"source_id":"1709.03316","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a9a7b65b8840abf2ad6ff68d9ebfe244748590dbdfee3e17476a72fe38ce30f6","sha256:077ecf129efb0bf850aa82dda38a4ddba01b380553735da30fd841ca31b14385"],"state_sha256":"63f7a3e5fe2345845eace4bd01a6ec45ca2541b58d26fa3fcde81fb27fe66f4c"}