{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:7JMLBJVXJYUXA4I3A7V6LYYDO4","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":"348c88402a7056e40a62a6904613b253696bf7cd078d7c407afa6b13ec30a1d0","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T22:43:57Z","title_canon_sha256":"b3ffa3720d07855412a7c0e2451ad7330123601aee5e11f982eb308547dd3d40"},"schema_version":"1.0","source":{"id":"2310.00811","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2310.00811","created_at":"2026-07-05T06:56:10Z"},{"alias_kind":"arxiv_version","alias_value":"2310.00811v1","created_at":"2026-07-05T06:56:10Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.00811","created_at":"2026-07-05T06:56:10Z"},{"alias_kind":"pith_short_12","alias_value":"7JMLBJVXJYUX","created_at":"2026-07-05T06:56:10Z"},{"alias_kind":"pith_short_16","alias_value":"7JMLBJVXJYUXA4I3","created_at":"2026-07-05T06:56:10Z"},{"alias_kind":"pith_short_8","alias_value":"7JMLBJVX","created_at":"2026-07-05T06:56:10Z"}],"graph_snapshots":[{"event_id":"sha256:1eef7bb57ff62eb1243e88f849fbce26fd93db084415a49db33a367c311d554f","target":"graph","created_at":"2026-07-05T06:56:10Z","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/2310.00811/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"One defining characteristic of Mixture-of-Expert (MoE) models is their capacity for conducting sparse computation via expert routing, leading to remarkable scalability. However, backpropagation, the cornerstone of deep learning, requires dense computation, thereby posting challenges in MoE gradient computations. Here, we introduce SparseMixer, a scalable gradient estimator that bridges the gap between backpropagation and sparse expert routing. Unlike typical MoE training which strategically neglects certain gradient terms for the sake of sparse computation and scalability, SparseMixer provides","authors_text":"Jianfeng Gao, Liyuan Liu, Weizhu Chen","cross_cats":["cs.AI","cs.CL","cs.CV"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T22:43:57Z","title":"Sparse Backpropagation for MoE Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.00811","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":"sha256:94edefb4144c449ea0e52e5b9e95562f325904e015f839bf9db73d0882615e51","target":"record","created_at":"2026-07-05T06:56:10Z","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":"348c88402a7056e40a62a6904613b253696bf7cd078d7c407afa6b13ec30a1d0","cross_cats_sorted":["cs.AI","cs.CL","cs.CV"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-10-01T22:43:57Z","title_canon_sha256":"b3ffa3720d07855412a7c0e2451ad7330123601aee5e11f982eb308547dd3d40"},"schema_version":"1.0","source":{"id":"2310.00811","kind":"arxiv","version":1}},"canonical_sha256":"fa58b0a6b74e2970711b07ebe5e303773518fdfce0e7ae1332a3105ecad49891","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fa58b0a6b74e2970711b07ebe5e303773518fdfce0e7ae1332a3105ecad49891","first_computed_at":"2026-07-05T06:56:10.881010Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:56:10.881010Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/A5LPNrVUW+bWIxKmmBOBHUW29WCyJHCj6FhNUr1Yy6YVfJeARhnaqBVCcarF1Ug5ol4sU6h9LSofBMwdfECBw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:56:10.881436Z","signed_message":"canonical_sha256_bytes"},"source_id":"2310.00811","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:94edefb4144c449ea0e52e5b9e95562f325904e015f839bf9db73d0882615e51","sha256:1eef7bb57ff62eb1243e88f849fbce26fd93db084415a49db33a367c311d554f"],"state_sha256":"65628e6ba67c3ce6f50ca9618d26def302b57e202bb4959fd269010b4b36e0a4"}