{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:RJUYGM5PVQFFGRCBFF7VNQFDWJ","short_pith_number":"pith:RJUYGM5P","canonical_record":{"source":{"id":"2304.03946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-04-08T07:34:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"35e6a67e25b4cffd54e11fbfbe9b0612b2c929a9d3fc64cb61dfddd9807d85fd","abstract_canon_sha256":"654527888310c4992ce928d5232ef348402026e7157b3822ae334ab85ff48c9c"},"schema_version":"1.0"},"canonical_sha256":"8a698333afac0a534441297f56c0a3b2513beb504c177e6eb89f1f9908e39de1","source":{"kind":"arxiv","id":"2304.03946","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03946","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03946v1","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03946","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"RJUYGM5PVQFF","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"RJUYGM5PVQFFGRCB","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"RJUYGM5P","created_at":"2026-07-05T05:59:09Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:RJUYGM5PVQFFGRCBFF7VNQFDWJ","target":"record","payload":{"canonical_record":{"source":{"id":"2304.03946","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-04-08T07:34:26Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"35e6a67e25b4cffd54e11fbfbe9b0612b2c929a9d3fc64cb61dfddd9807d85fd","abstract_canon_sha256":"654527888310c4992ce928d5232ef348402026e7157b3822ae334ab85ff48c9c"},"schema_version":"1.0"},"canonical_sha256":"8a698333afac0a534441297f56c0a3b2513beb504c177e6eb89f1f9908e39de1","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:59:09.377174Z","signature_b64":"qQrc7OHviaZgknppSsf8S5RE8Nm5+EkkvNu1incqSxxOSMztvdL++GWBAvp9NxTWUPG+9gQuhe3Byti7LsNiDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8a698333afac0a534441297f56c0a3b2513beb504c177e6eb89f1f9908e39de1","last_reissued_at":"2026-07-05T05:59:09.376673Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:59:09.376673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2304.03946","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":"2026-07-05T05:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Z4tJr3FljkujNsjOxcKjLizJ4vPdp3Qy4+cM5UGlHPe/+ceFlSeD/SYs0TRj0AVZ55ZqGhpV2kfumPI7pEEGCA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:40:16.697953Z"},"content_sha256":"5ba9b3e2432bdf07d9590f0d4bf27eff3dd8a6e064890e535c1ab24c03ba57f6","schema_version":"1.0","event_id":"sha256:5ba9b3e2432bdf07d9590f0d4bf27eff3dd8a6e064890e535c1ab24c03ba57f6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:RJUYGM5PVQFFGRCBFF7VNQFDWJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.DC","authors_text":"Bin Cui, Gang Cao, Jilong Xue, Lingxiao Ma, Xiaonan Nie, Xupeng Miao, Zichao Yang, Zilong Wang","submitted_at":"2023-04-08T07:34:26Z","abstract_excerpt":"With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these models is composed of lots of dense algebras, requiring a huge amount of hardware resources. Recently, sparsely-gated Mixture-of-Experts (MoEs) are becoming more popular and have demonstrated impressive pretraining scalability in various downstream tasks. However, such a sparse conditional computation may not be effective as expected in practical systems due to the routing imbalance and fluctuation problems. Generall"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03946","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/2304.03946/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":"2026-07-05T05:59:09Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"kj0DIaW6YZr5JWZuI9xvb2J26KUzCBQqlH0e5HYxm6t4b318va2CdrAVf3RGXAAUSUWsJiwwVZtnUskJJj1XCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-21T21:40:16.698484Z"},"content_sha256":"01f50a316637102bdf3b66e252dc4be1383fb816550f8e625f037e775f8bec3b","schema_version":"1.0","event_id":"sha256:01f50a316637102bdf3b66e252dc4be1383fb816550f8e625f037e775f8bec3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RJUYGM5PVQFFGRCBFF7VNQFDWJ/bundle.json","state_url":"https://pith.science/pith/RJUYGM5PVQFFGRCBFF7VNQFDWJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RJUYGM5PVQFFGRCBFF7VNQFDWJ/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":"2026-08-21T21:40:16Z","links":{"resolver":"https://pith.science/pith/RJUYGM5PVQFFGRCBFF7VNQFDWJ","bundle":"https://pith.science/pith/RJUYGM5PVQFFGRCBFF7VNQFDWJ/bundle.json","state":"https://pith.science/pith/RJUYGM5PVQFFGRCBFF7VNQFDWJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RJUYGM5PVQFFGRCBFF7VNQFDWJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RJUYGM5PVQFFGRCBFF7VNQFDWJ","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":"654527888310c4992ce928d5232ef348402026e7157b3822ae334ab85ff48c9c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-04-08T07:34:26Z","title_canon_sha256":"35e6a67e25b4cffd54e11fbfbe9b0612b2c929a9d3fc64cb61dfddd9807d85fd"},"schema_version":"1.0","source":{"id":"2304.03946","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2304.03946","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"arxiv_version","alias_value":"2304.03946v1","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03946","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"pith_short_12","alias_value":"RJUYGM5PVQFF","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"pith_short_16","alias_value":"RJUYGM5PVQFFGRCB","created_at":"2026-07-05T05:59:09Z"},{"alias_kind":"pith_short_8","alias_value":"RJUYGM5P","created_at":"2026-07-05T05:59:09Z"}],"graph_snapshots":[{"event_id":"sha256:01f50a316637102bdf3b66e252dc4be1383fb816550f8e625f037e775f8bec3b","target":"graph","created_at":"2026-07-05T05:59:09Z","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/2304.03946/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the increasing data volume, there is a trend of using large-scale pre-trained models to store the knowledge into an enormous number of model parameters. The training of these models is composed of lots of dense algebras, requiring a huge amount of hardware resources. Recently, sparsely-gated Mixture-of-Experts (MoEs) are becoming more popular and have demonstrated impressive pretraining scalability in various downstream tasks. However, such a sparse conditional computation may not be effective as expected in practical systems due to the routing imbalance and fluctuation problems. Generall","authors_text":"Bin Cui, Gang Cao, Jilong Xue, Lingxiao Ma, Xiaonan Nie, Xupeng Miao, Zichao Yang, Zilong Wang","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-04-08T07:34:26Z","title":"FlexMoE: Scaling Large-scale Sparse Pre-trained Model Training via Dynamic Device Placement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03946","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":"sha256:5ba9b3e2432bdf07d9590f0d4bf27eff3dd8a6e064890e535c1ab24c03ba57f6","target":"record","created_at":"2026-07-05T05:59:09Z","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":"654527888310c4992ce928d5232ef348402026e7157b3822ae334ab85ff48c9c","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DC","submitted_at":"2023-04-08T07:34:26Z","title_canon_sha256":"35e6a67e25b4cffd54e11fbfbe9b0612b2c929a9d3fc64cb61dfddd9807d85fd"},"schema_version":"1.0","source":{"id":"2304.03946","kind":"arxiv","version":1}},"canonical_sha256":"8a698333afac0a534441297f56c0a3b2513beb504c177e6eb89f1f9908e39de1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8a698333afac0a534441297f56c0a3b2513beb504c177e6eb89f1f9908e39de1","first_computed_at":"2026-07-05T05:59:09.376673Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:59:09.376673Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qQrc7OHviaZgknppSsf8S5RE8Nm5+EkkvNu1incqSxxOSMztvdL++GWBAvp9NxTWUPG+9gQuhe3Byti7LsNiDA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:59:09.377174Z","signed_message":"canonical_sha256_bytes"},"source_id":"2304.03946","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5ba9b3e2432bdf07d9590f0d4bf27eff3dd8a6e064890e535c1ab24c03ba57f6","sha256:01f50a316637102bdf3b66e252dc4be1383fb816550f8e625f037e775f8bec3b"],"state_sha256":"f851b2655eddefcc674a336b63f969906f1cef3669f58419dff1c4de7c241a79"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lVuAGKn/IMcYRXYO3Bu8UmdIyEDAoweEzvpvFOCInQEJHhzcg5caazB+w8I9nbi7yCn/YR3stkTkyZjSz6KRDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-21T21:40:16.703450Z","bundle_sha256":"b70be72560cee9bf6d72a814c009bfdd4137ca5193cd95665f2d037b88dfc7f8"}}