{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:AUYAHH36JWWZUYW3HQ2ZNFWJKH","short_pith_number":"pith:AUYAHH36","canonical_record":{"source":{"id":"2304.11414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-04-22T14:09:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4260773c31a7b7bf7792b799dfec741a586e9be9bcd277d6ed9f848f4a7842c","abstract_canon_sha256":"f02c434f4c1f8cb0ab3d1678965c7895001a8505bb26c9f645b1afdba62fb37e"},"schema_version":"1.0"},"canonical_sha256":"0530039f7e4dad9a62db3c359696c951f4a8c5647db3cf368b329679eb9acd2a","source":{"kind":"arxiv","id":"2304.11414","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11414","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11414v1","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11414","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"AUYAHH36JWWZ","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"AUYAHH36JWWZUYW3","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"AUYAHH36","created_at":"2026-07-05T06:03:32Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:AUYAHH36JWWZUYW3HQ2ZNFWJKH","target":"record","payload":{"canonical_record":{"source":{"id":"2304.11414","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-04-22T14:09:14Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"a4260773c31a7b7bf7792b799dfec741a586e9be9bcd277d6ed9f848f4a7842c","abstract_canon_sha256":"f02c434f4c1f8cb0ab3d1678965c7895001a8505bb26c9f645b1afdba62fb37e"},"schema_version":"1.0"},"canonical_sha256":"0530039f7e4dad9a62db3c359696c951f4a8c5647db3cf368b329679eb9acd2a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:03:32.354165Z","signature_b64":"JxP94teVC5m8s0LcDeARCAYBQmMAWHRYMGvPPHzzr9zQxsSW3QwUUk3tP7NSYWcF2rpJ8p17u6eS0mSo5hXJDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0530039f7e4dad9a62db3c359696c951f4a8c5647db3cf368b329679eb9acd2a","last_reissued_at":"2026-07-05T06:03:32.353773Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:03:32.353773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.11414","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":"2026-07-05T06:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"02D6io8jsHNxSHsLFZIlggY4RTIwqhQirVh9e3teZ98AAclhCRNu47eog1F5HCj6DMWsXSkG/MfP8UYfiMc3Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:30:52.760239Z"},"content_sha256":"ae937f4b7fbe8db0af3f7470a4a008f540271902d6240c504a7f824bd062cc14","schema_version":"1.0","event_id":"sha256:ae937f4b7fbe8db0af3f7470a4a008f540271902d6240c504a7f824bd062cc14"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:AUYAHH36JWWZUYW3HQ2ZNFWJKH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Hengheng Zhang, Kaifeng Bi, Lingxi Xie, Qi Tian, Xiaotao Gu, Xin Chen","submitted_at":"2023-04-22T14:09:14Z","abstract_excerpt":"The Mixture of Experts (MoE) model becomes an important choice of large language models nowadays because of its scalability with sublinear computational complexity for training and inference. However, existing MoE models suffer from two critical drawbacks, 1) tremendous inner-node and inter-node communication overhead introduced by all-to-all dispatching and gathering, and 2) limited scalability for the backbone because of the bound data parallel and expert parallel to scale in the expert dimension. In this paper, we systematically analyze these drawbacks in terms of training efficiency in the"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11414","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/2304.11414/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":"2026-07-05T06:03:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VZymngsnYRQacdtSkzA9INVZ4XrQI3E2cO74iUjXWtG7c5lkD+kJ6d99UB1Ky+jGF2jQE3Zl/HxdVx/2OjPwAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T19:30:52.761184Z"},"content_sha256":"4a1ab337be09c636c2c3e5dedd37aab61556a4e15c2ab3f47be94720c91b3ecd","schema_version":"1.0","event_id":"sha256:4a1ab337be09c636c2c3e5dedd37aab61556a4e15c2ab3f47be94720c91b3ecd"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/AUYAHH36JWWZUYW3HQ2ZNFWJKH/bundle.json","state_url":"https://pith.science/pith/AUYAHH36JWWZUYW3HQ2ZNFWJKH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/AUYAHH36JWWZUYW3HQ2ZNFWJKH/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":"2026-08-09T19:30:52Z","links":{"resolver":"https://pith.science/pith/AUYAHH36JWWZUYW3HQ2ZNFWJKH","bundle":"https://pith.science/pith/AUYAHH36JWWZUYW3HQ2ZNFWJKH/bundle.json","state":"https://pith.science/pith/AUYAHH36JWWZUYW3HQ2ZNFWJKH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/AUYAHH36JWWZUYW3HQ2ZNFWJKH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:AUYAHH36JWWZUYW3HQ2ZNFWJKH","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":"f02c434f4c1f8cb0ab3d1678965c7895001a8505bb26c9f645b1afdba62fb37e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-04-22T14:09:14Z","title_canon_sha256":"a4260773c31a7b7bf7792b799dfec741a586e9be9bcd277d6ed9f848f4a7842c"},"schema_version":"1.0","source":{"id":"2304.11414","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.11414","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"arxiv_version","alias_value":"2304.11414v1","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.11414","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_12","alias_value":"AUYAHH36JWWZ","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_16","alias_value":"AUYAHH36JWWZUYW3","created_at":"2026-07-05T06:03:32Z"},{"alias_kind":"pith_short_8","alias_value":"AUYAHH36","created_at":"2026-07-05T06:03:32Z"}],"graph_snapshots":[{"event_id":"sha256:4a1ab337be09c636c2c3e5dedd37aab61556a4e15c2ab3f47be94720c91b3ecd","target":"graph","created_at":"2026-07-05T06:03:32Z","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/2304.11414/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Mixture of Experts (MoE) model becomes an important choice of large language models nowadays because of its scalability with sublinear computational complexity for training and inference. However, existing MoE models suffer from two critical drawbacks, 1) tremendous inner-node and inter-node communication overhead introduced by all-to-all dispatching and gathering, and 2) limited scalability for the backbone because of the bound data parallel and expert parallel to scale in the expert dimension. In this paper, we systematically analyze these drawbacks in terms of training efficiency in the","authors_text":"Hengheng Zhang, Kaifeng Bi, Lingxi Xie, Qi Tian, Xiaotao Gu, Xin Chen","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-04-22T14:09:14Z","title":"Pipeline MoE: A Flexible MoE Implementation with Pipeline Parallelism"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.11414","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:ae937f4b7fbe8db0af3f7470a4a008f540271902d6240c504a7f824bd062cc14","target":"record","created_at":"2026-07-05T06:03:32Z","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":"f02c434f4c1f8cb0ab3d1678965c7895001a8505bb26c9f645b1afdba62fb37e","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.DC","submitted_at":"2023-04-22T14:09:14Z","title_canon_sha256":"a4260773c31a7b7bf7792b799dfec741a586e9be9bcd277d6ed9f848f4a7842c"},"schema_version":"1.0","source":{"id":"2304.11414","kind":"arxiv","version":1}},"canonical_sha256":"0530039f7e4dad9a62db3c359696c951f4a8c5647db3cf368b329679eb9acd2a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0530039f7e4dad9a62db3c359696c951f4a8c5647db3cf368b329679eb9acd2a","first_computed_at":"2026-07-05T06:03:32.353773Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:03:32.353773Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"JxP94teVC5m8s0LcDeARCAYBQmMAWHRYMGvPPHzzr9zQxsSW3QwUUk3tP7NSYWcF2rpJ8p17u6eS0mSo5hXJDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T06:03:32.354165Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.11414","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ae937f4b7fbe8db0af3f7470a4a008f540271902d6240c504a7f824bd062cc14","sha256:4a1ab337be09c636c2c3e5dedd37aab61556a4e15c2ab3f47be94720c91b3ecd"],"state_sha256":"a6cfda7daa0d0cb3a30fdd644a38e5d171520c1b8d168830169db2ddf1dde479"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"r+tlSHOR1na5KU/DNvojdux/jBt8pisJEKCjOsLrC2lRuajnU0JerWBKCyVwQGcpVS6JA1aoY8K7FdRV+JUQAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T19:30:52.768171Z","bundle_sha256":"f9f5f6782e6c86497eb6065bc4d9d11c3f044a4a5a6d292445b296b2f6a01e9f"}}