{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Y6GGFJG6WQLMWCPFVLSVUYYZSU","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":"b954f5c2666c720fd22c083bb6e8ebb37dae2cc06c0011a0460f12b3995c36de","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-08T14:39:49Z","title_canon_sha256":"7415a4d09c17beb6dfd5530307e3505136d079a9348236482a5f6be2a19c723f"},"schema_version":"1.0","source":{"id":"2404.05567","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05567","created_at":"2026-07-05T08:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05567v1","created_at":"2026-07-05T08:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05567","created_at":"2026-07-05T08:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"Y6GGFJG6WQLM","created_at":"2026-07-05T08:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"Y6GGFJG6WQLMWCPF","created_at":"2026-07-05T08:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"Y6GGFJG6","created_at":"2026-07-05T08:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:6ef2c28725e3f1faf5b4811f177aae5df5cb6d5ad5e13826c9ad18c73b931c47","target":"graph","created_at":"2026-07-05T08:05:42Z","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/2404.05567/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-Experts (MoE) language models can reduce computational costs by 2-4$\\times$ compared to dense models without sacrificing performance, making them more efficient in computation-bounded scenarios. However, MoE models generally require 2-4$\\times$ times more parameters to achieve comparable performance to a dense model, which incurs larger GPU memory requirements and makes MoE models less efficient in I/O-bounded scenarios like autoregressive generation. In this work, we propose a hybrid dense training and sparse inference framework for MoE models (DS-MoE) which achieves strong computa","authors_text":"Aude Oliva, Bowen Pan, Colin Raffel, Gaoyuan Zhang, Haokun Liu, Mayank Mishra, Rameswar Panda, Yikang Shen","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-08T14:39:49Z","title":"Dense Training, Sparse Inference: Rethinking Training of Mixture-of-Experts Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05567","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":"sha256:637e2568fae67f51dad20a48142d691dd3ed14c9a50f97ac44eaf5e7c8615c83","target":"record","created_at":"2026-07-05T08:05:42Z","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":"b954f5c2666c720fd22c083bb6e8ebb37dae2cc06c0011a0460f12b3995c36de","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-04-08T14:39:49Z","title_canon_sha256":"7415a4d09c17beb6dfd5530307e3505136d079a9348236482a5f6be2a19c723f"},"schema_version":"1.0","source":{"id":"2404.05567","kind":"arxiv","version":1}},"canonical_sha256":"c78c62a4deb416cb09e5aae55a63199508f30df67e280f22c918787efb17fd3f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c78c62a4deb416cb09e5aae55a63199508f30df67e280f22c918787efb17fd3f","first_computed_at":"2026-07-05T08:05:42.630036Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:05:42.630036Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"uH7WRaXvK9JiHc2IAIC/xc3Axn8XVBUDKhg+jCzgU1BY4z76ut4Xxl2jQCQpNuSA85f18oJCu6zWBNJmb1xBBg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:05:42.630535Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05567","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:637e2568fae67f51dad20a48142d691dd3ed14c9a50f97ac44eaf5e7c8615c83","sha256:6ef2c28725e3f1faf5b4811f177aae5df5cb6d5ad5e13826c9ad18c73b931c47"],"state_sha256":"5e35b2685b978bfb41e1cf0d6380c05af383cba0389b80a1724eccf2bd4e8a7c"}