{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:RRYTNBHYYRNXNFOCU6EJSEJBWM","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":"8c303c92a4d4841fb8b591d424b2dd77557a74b20f3494a31dcef568f86b5dfd","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-02T05:20:55Z","title_canon_sha256":"131502f3ef7beb573fa4ddf6c7a6512232a2a41c73f52cc5a476ebe92faf17b7"},"schema_version":"1.0","source":{"id":"2308.00951","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.00951","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"arxiv_version","alias_value":"2308.00951v2","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.00951","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"pith_short_12","alias_value":"RRYTNBHYYRNX","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"pith_short_16","alias_value":"RRYTNBHYYRNXNFOC","created_at":"2026-07-05T08:23:11Z"},{"alias_kind":"pith_short_8","alias_value":"RRYTNBHY","created_at":"2026-07-05T08:23:11Z"}],"graph_snapshots":[{"event_id":"sha256:04b7cf4cd7bef86df34261937152597d3ce4ad13cac5a4d3b5d17c5073c0f158","target":"graph","created_at":"2026-07-05T08:23:11Z","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/2308.00951/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Sparse mixture of expert architectures (MoEs) scale model capacity without significant increases in training or inference costs. Despite their success, MoEs suffer from a number of issues: training instability, token dropping, inability to scale the number of experts, or ineffective finetuning. In this work, we propose Soft MoE, a fully-differentiable sparse Transformer that addresses these challenges, while maintaining the benefits of MoEs. Soft MoE performs an implicit soft assignment by passing different weighted combinations of all input tokens to each expert. As in other MoEs, experts in ","authors_text":"Basil Mustafa, Carlos Riquelme, Joan Puigcerver, Neil Houlsby","cross_cats":["cs.AI","cs.CV"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-02T05:20:55Z","title":"From Sparse to Soft Mixtures of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.00951","kind":"arxiv","version":2},"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":"sha256:974113941b256775813a37d3ac2b1f36aad930c69a10b8935ba1fac4492cecee","target":"record","created_at":"2026-07-05T08:23:11Z","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":"8c303c92a4d4841fb8b591d424b2dd77557a74b20f3494a31dcef568f86b5dfd","cross_cats_sorted":["cs.AI","cs.CV"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-08-02T05:20:55Z","title_canon_sha256":"131502f3ef7beb573fa4ddf6c7a6512232a2a41c73f52cc5a476ebe92faf17b7"},"schema_version":"1.0","source":{"id":"2308.00951","kind":"arxiv","version":2}},"canonical_sha256":"8c713684f8c45b7695c2a788991121b30ed9d2009cefb6dc2fabeb2c8ee93d5b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8c713684f8c45b7695c2a788991121b30ed9d2009cefb6dc2fabeb2c8ee93d5b","first_computed_at":"2026-07-05T08:23:11.053304Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:23:11.053304Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2OjbroJqB/Zyqzo2vr0hsCivzTEiJm2QohtIxh8xKs/OaPaKOihoDVyd2tueYGBrL0DrbcG77wD9u/I2UfaMDg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:23:11.053824Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.00951","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:974113941b256775813a37d3ac2b1f36aad930c69a10b8935ba1fac4492cecee","sha256:04b7cf4cd7bef86df34261937152597d3ce4ad13cac5a4d3b5d17c5073c0f158"],"state_sha256":"c7dec0bbd820365fe1dbd24c3989d8d422286276f5a6148bd47b9cce0aeafbe2"}