{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:52D4K5ENNEQVKV7GGWDAAPWJD6","short_pith_number":"pith:52D4K5EN","canonical_record":{"source":{"id":"2011.03605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-06T21:36:16Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"da8b6b0aaf3eec6912e3051c07747942ad235c245d358c1e7dc6ca406be68ae2","abstract_canon_sha256":"909bc91809b04b7b7d1ad381074a71c0bf31626ed735d506e5118c92ac7f013f"},"schema_version":"1.0"},"canonical_sha256":"ee87c5748d69215557e63586003ec91fa69f61fa492cefca273850b90bc27ab4","source":{"kind":"arxiv","id":"2011.03605","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03605","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03605v1","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03605","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"pith_short_12","alias_value":"52D4K5ENNEQV","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"pith_short_16","alias_value":"52D4K5ENNEQVKV7G","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"pith_short_8","alias_value":"52D4K5EN","created_at":"2026-07-05T01:49:57Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:52D4K5ENNEQVKV7GGWDAAPWJD6","target":"record","payload":{"canonical_record":{"source":{"id":"2011.03605","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-06T21:36:16Z","cross_cats_sorted":["cs.DC"],"title_canon_sha256":"da8b6b0aaf3eec6912e3051c07747942ad235c245d358c1e7dc6ca406be68ae2","abstract_canon_sha256":"909bc91809b04b7b7d1ad381074a71c0bf31626ed735d506e5118c92ac7f013f"},"schema_version":"1.0"},"canonical_sha256":"ee87c5748d69215557e63586003ec91fa69f61fa492cefca273850b90bc27ab4","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:49:57.701203Z","signature_b64":"k5ihWnTr5keE5VuffPc4bLeCLxs2/aJlI+ntY/p0SXJvA/8KieMP6BYyfIqADuJi9WM1AGOg/ku3uSoT52ffDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee87c5748d69215557e63586003ec91fa69f61fa492cefca273850b90bc27ab4","last_reissued_at":"2026-07-05T01:49:57.700752Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:49:57.700752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2011.03605","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":"2026-07-05T01:49:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"sR/Fj7S0ZS48URPH+JAfwgQW0PuKzUsCb995X62Av6KGb7UwEoWvXLw7H/Ffcxa9G8UEuyknoo86B8P5WrbhAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:35:02.665535Z"},"content_sha256":"f61da966ef9903ea19763e8e1a7f65e268be63a19212be0f40fe43585dfac1f2","schema_version":"1.0","event_id":"sha256:f61da966ef9903ea19763e8e1a7f65e268be63a19212be0f40fe43585dfac1f2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:52D4K5ENNEQVKV7GGWDAAPWJD6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Highly Available Data Parallel ML training on Mesh Networks","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.DC"],"primary_cat":"cs.LG","authors_text":"Norm Jouppi, Sameer Kumar","submitted_at":"2020-11-06T21:36:16Z","abstract_excerpt":"Data parallel ML models can take several days or weeks to train on several accelerators. The long duration of training relies on the cluster of resources to be available for the job to keep running for the entire duration. On a mesh network this is challenging because failures will create holes in the mesh. Packets must be routed around the failed chips for full connectivity. In this paper, we present techniques to route gradient summation allreduce traffic around failed chips on 2-D meshes. We evaluate performance of our fault tolerant allreduce techniques via the MLPerf-v0.7 ResNet-50 and BE"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03605","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/2011.03605/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:49:57Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MaCsYzYXbz/FeXuto1wEGHZLenTr2LhVY67dmYIC4Op98zPuxJMCWbWifcNXz2D6tgRcjjN6lk6RFD+Z2MR5AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:35:02.665854Z"},"content_sha256":"8d4920f3358f2dfadcbe62b0e4ce5406a3c20a4409358a84531953fcafddadb0","schema_version":"1.0","event_id":"sha256:8d4920f3358f2dfadcbe62b0e4ce5406a3c20a4409358a84531953fcafddadb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/52D4K5ENNEQVKV7GGWDAAPWJD6/bundle.json","state_url":"https://pith.science/pith/52D4K5ENNEQVKV7GGWDAAPWJD6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/52D4K5ENNEQVKV7GGWDAAPWJD6/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":"2026-08-19T11:35:02Z","links":{"resolver":"https://pith.science/pith/52D4K5ENNEQVKV7GGWDAAPWJD6","bundle":"https://pith.science/pith/52D4K5ENNEQVKV7GGWDAAPWJD6/bundle.json","state":"https://pith.science/pith/52D4K5ENNEQVKV7GGWDAAPWJD6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/52D4K5ENNEQVKV7GGWDAAPWJD6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:52D4K5ENNEQVKV7GGWDAAPWJD6","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":"909bc91809b04b7b7d1ad381074a71c0bf31626ed735d506e5118c92ac7f013f","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-06T21:36:16Z","title_canon_sha256":"da8b6b0aaf3eec6912e3051c07747942ad235c245d358c1e7dc6ca406be68ae2"},"schema_version":"1.0","source":{"id":"2011.03605","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.03605","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"arxiv_version","alias_value":"2011.03605v1","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.03605","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"pith_short_12","alias_value":"52D4K5ENNEQV","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"pith_short_16","alias_value":"52D4K5ENNEQVKV7G","created_at":"2026-07-05T01:49:57Z"},{"alias_kind":"pith_short_8","alias_value":"52D4K5EN","created_at":"2026-07-05T01:49:57Z"}],"graph_snapshots":[{"event_id":"sha256:8d4920f3358f2dfadcbe62b0e4ce5406a3c20a4409358a84531953fcafddadb0","target":"graph","created_at":"2026-07-05T01:49:57Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2011.03605/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data parallel ML models can take several days or weeks to train on several accelerators. The long duration of training relies on the cluster of resources to be available for the job to keep running for the entire duration. On a mesh network this is challenging because failures will create holes in the mesh. Packets must be routed around the failed chips for full connectivity. In this paper, we present techniques to route gradient summation allreduce traffic around failed chips on 2-D meshes. We evaluate performance of our fault tolerant allreduce techniques via the MLPerf-v0.7 ResNet-50 and BE","authors_text":"Norm Jouppi, Sameer Kumar","cross_cats":["cs.DC"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-06T21:36:16Z","title":"Highly Available Data Parallel ML training on Mesh Networks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.03605","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:f61da966ef9903ea19763e8e1a7f65e268be63a19212be0f40fe43585dfac1f2","target":"record","created_at":"2026-07-05T01:49:57Z","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":"909bc91809b04b7b7d1ad381074a71c0bf31626ed735d506e5118c92ac7f013f","cross_cats_sorted":["cs.DC"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-11-06T21:36:16Z","title_canon_sha256":"da8b6b0aaf3eec6912e3051c07747942ad235c245d358c1e7dc6ca406be68ae2"},"schema_version":"1.0","source":{"id":"2011.03605","kind":"arxiv","version":1}},"canonical_sha256":"ee87c5748d69215557e63586003ec91fa69f61fa492cefca273850b90bc27ab4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee87c5748d69215557e63586003ec91fa69f61fa492cefca273850b90bc27ab4","first_computed_at":"2026-07-05T01:49:57.700752Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:49:57.700752Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"k5ihWnTr5keE5VuffPc4bLeCLxs2/aJlI+ntY/p0SXJvA/8KieMP6BYyfIqADuJi9WM1AGOg/ku3uSoT52ffDw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:49:57.701203Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.03605","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f61da966ef9903ea19763e8e1a7f65e268be63a19212be0f40fe43585dfac1f2","sha256:8d4920f3358f2dfadcbe62b0e4ce5406a3c20a4409358a84531953fcafddadb0"],"state_sha256":"f65b6f006b8e7cb1fbb9b65aed9c2175879f9f65428a3f1f86b868d3b65fda28"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kLH+Y0CZIiFEdZUIcDAESLJon6pNuM1N/FrZDF5+nJ3QTV8Yq7c3AlQH807s+pIQDH2I5bkQrq/Pa6ZYg4eJAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:35:02.669010Z","bundle_sha256":"0871f4d5acfcb0b222d3b95786e960a62b45f185f72781e27859540bac278d7a"}}