{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:DSN7CWMLJYUVK2HBKYVACSSFO5","short_pith_number":"pith:DSN7CWML","canonical_record":{"source":{"id":"1904.01631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2019-03-24T00:18:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f8675e70af61bd0f93b40ce5bcb3ca046e1e01afd0ade9ae56f30a9ae420dd9e","abstract_canon_sha256":"f42d4abe010372a0b1fec0ff59e6b5892608385d73c6d0a4f0ac34e3b94c2582"},"schema_version":"1.0"},"canonical_sha256":"1c9bf1598b4e295568e1562a014a45774340dbfc8fefcb372af7b1860e7d58ba","source":{"kind":"arxiv","id":"1904.01631","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01631","created_at":"2026-05-17T23:49:30Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01631v1","created_at":"2026-05-17T23:49:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01631","created_at":"2026-05-17T23:49:30Z"},{"alias_kind":"pith_short_12","alias_value":"DSN7CWMLJYUV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DSN7CWMLJYUVK2HB","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DSN7CWML","created_at":"2026-05-18T12:33:15Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:DSN7CWMLJYUVK2HBKYVACSSFO5","target":"record","payload":{"canonical_record":{"source":{"id":"1904.01631","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2019-03-24T00:18:21Z","cross_cats_sorted":["cs.LG","stat.ML"],"title_canon_sha256":"f8675e70af61bd0f93b40ce5bcb3ca046e1e01afd0ade9ae56f30a9ae420dd9e","abstract_canon_sha256":"f42d4abe010372a0b1fec0ff59e6b5892608385d73c6d0a4f0ac34e3b94c2582"},"schema_version":"1.0"},"canonical_sha256":"1c9bf1598b4e295568e1562a014a45774340dbfc8fefcb372af7b1860e7d58ba","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:49:30.408790Z","signature_b64":"7xZzZwNPxjKNtQMqGwuOug531pd23XN6Ec+ELzz66Qm4190SehNroPGe1VPP8PmfRVmT7wfehEWL0YDSqjA2Aw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1c9bf1598b4e295568e1562a014a45774340dbfc8fefcb372af7b1860e7d58ba","last_reissued_at":"2026-05-17T23:49:30.408291Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:49:30.408291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1904.01631","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":"2026-05-17T23:49:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Sz0a9hRPXskK4FuCsGAxEW5yNz2qnvwy6Nd0fiwGmB4Kn4cSUxOCJxYzhi0ztUk6VFierGWJQ2eLQ+9kY56NAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:31:31.784712Z"},"content_sha256":"3055859c3aac65f17f0abac6f33be0b220914613dedef519795ff899ffe5c238","schema_version":"1.0","event_id":"sha256:3055859c3aac65f17f0abac6f33be0b220914613dedef519795ff899ffe5c238"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:DSN7CWMLJYUVK2HBKYVACSSFO5","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TonY: An Orchestrator for Distributed Machine Learning Jobs","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG","stat.ML"],"primary_cat":"cs.DC","authors_text":"Anthony Hsu, Arun Suresh, Jonathan Hung, Keqiu Hu, Zhe Zhang","submitted_at":"2019-03-24T00:18:21Z","abstract_excerpt":"Training machine learning (ML) models on large datasets requires considerable computing power. To speed up training, it is typical to distribute training across several machines, often with specialized hardware like GPUs or TPUs. Managing a distributed training job is complex and requires dealing with resource contention, distributed configurations, monitoring, and fault tolerance. In this paper, we describe TonY, an open-source orchestrator for distributed ML jobs built at LinkedIn to address these challenges."},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01631","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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:49:30Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"TIa/2GhArbaYaqBDZI4h8zGeYacDxvMO62W3/Pue4sOuHNB7pFZk7etMq0IRwukARYG23GAvTPuH5YHafHbxDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-07T12:31:31.785075Z"},"content_sha256":"0b6b0d1f0e388e5f8bbe37f986246d7dbcc2ba26c400c6b6856b040a71eaa183","schema_version":"1.0","event_id":"sha256:0b6b0d1f0e388e5f8bbe37f986246d7dbcc2ba26c400c6b6856b040a71eaa183"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/DSN7CWMLJYUVK2HBKYVACSSFO5/bundle.json","state_url":"https://pith.science/pith/DSN7CWMLJYUVK2HBKYVACSSFO5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/DSN7CWMLJYUVK2HBKYVACSSFO5/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":"2026-07-07T12:31:31Z","links":{"resolver":"https://pith.science/pith/DSN7CWMLJYUVK2HBKYVACSSFO5","bundle":"https://pith.science/pith/DSN7CWMLJYUVK2HBKYVACSSFO5/bundle.json","state":"https://pith.science/pith/DSN7CWMLJYUVK2HBKYVACSSFO5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/DSN7CWMLJYUVK2HBKYVACSSFO5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:DSN7CWMLJYUVK2HBKYVACSSFO5","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":"f42d4abe010372a0b1fec0ff59e6b5892608385d73c6d0a4f0ac34e3b94c2582","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2019-03-24T00:18:21Z","title_canon_sha256":"f8675e70af61bd0f93b40ce5bcb3ca046e1e01afd0ade9ae56f30a9ae420dd9e"},"schema_version":"1.0","source":{"id":"1904.01631","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1904.01631","created_at":"2026-05-17T23:49:30Z"},{"alias_kind":"arxiv_version","alias_value":"1904.01631v1","created_at":"2026-05-17T23:49:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1904.01631","created_at":"2026-05-17T23:49:30Z"},{"alias_kind":"pith_short_12","alias_value":"DSN7CWMLJYUV","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_16","alias_value":"DSN7CWMLJYUVK2HB","created_at":"2026-05-18T12:33:15Z"},{"alias_kind":"pith_short_8","alias_value":"DSN7CWML","created_at":"2026-05-18T12:33:15Z"}],"graph_snapshots":[{"event_id":"sha256:0b6b0d1f0e388e5f8bbe37f986246d7dbcc2ba26c400c6b6856b040a71eaa183","target":"graph","created_at":"2026-05-17T23:49:30Z","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":"Training machine learning (ML) models on large datasets requires considerable computing power. To speed up training, it is typical to distribute training across several machines, often with specialized hardware like GPUs or TPUs. Managing a distributed training job is complex and requires dealing with resource contention, distributed configurations, monitoring, and fault tolerance. In this paper, we describe TonY, an open-source orchestrator for distributed ML jobs built at LinkedIn to address these challenges.","authors_text":"Anthony Hsu, Arun Suresh, Jonathan Hung, Keqiu Hu, Zhe Zhang","cross_cats":["cs.LG","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2019-03-24T00:18:21Z","title":"TonY: An Orchestrator for Distributed Machine Learning Jobs"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1904.01631","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":"sha256:3055859c3aac65f17f0abac6f33be0b220914613dedef519795ff899ffe5c238","target":"record","created_at":"2026-05-17T23:49:30Z","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":"f42d4abe010372a0b1fec0ff59e6b5892608385d73c6d0a4f0ac34e3b94c2582","cross_cats_sorted":["cs.LG","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2019-03-24T00:18:21Z","title_canon_sha256":"f8675e70af61bd0f93b40ce5bcb3ca046e1e01afd0ade9ae56f30a9ae420dd9e"},"schema_version":"1.0","source":{"id":"1904.01631","kind":"arxiv","version":1}},"canonical_sha256":"1c9bf1598b4e295568e1562a014a45774340dbfc8fefcb372af7b1860e7d58ba","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1c9bf1598b4e295568e1562a014a45774340dbfc8fefcb372af7b1860e7d58ba","first_computed_at":"2026-05-17T23:49:30.408291Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:49:30.408291Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7xZzZwNPxjKNtQMqGwuOug531pd23XN6Ec+ELzz66Qm4190SehNroPGe1VPP8PmfRVmT7wfehEWL0YDSqjA2Aw==","signature_status":"signed_v1","signed_at":"2026-05-17T23:49:30.408790Z","signed_message":"canonical_sha256_bytes"},"source_id":"1904.01631","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3055859c3aac65f17f0abac6f33be0b220914613dedef519795ff899ffe5c238","sha256:0b6b0d1f0e388e5f8bbe37f986246d7dbcc2ba26c400c6b6856b040a71eaa183"],"state_sha256":"0df74244bb7b0d63dbf9e170ddea0ea00b6262f1cf02603566f34d4dfe20f5b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qyMz8FSAKjlfioqiif5e/X8wZSZN+rhfGyCuk+gOIu5IXrIY0xQeuCvFZlQI43wTgaZurC8BjobZoxIDhSRBBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-07T12:31:31.786998Z","bundle_sha256":"5532f552eac2f6681d19c4c831357548efd8cf2e0537fd8b82771738a72df913"}}