{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZAHQOBA4FGOCB4WNCBIYSXKQCB","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":"e41bae5c17464582dbb87874fe09095f9dc0f1c5446935ea498e9bd2d3ae880b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T15:18:18Z","title_canon_sha256":"731a5004e1ed86e7ca7a3f49a23d373ed8eb6dbcc02bae568dbab7792b377e3d"},"schema_version":"1.0","source":{"id":"2305.02176","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.02176","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"arxiv_version","alias_value":"2305.02176v2","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.02176","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"pith_short_12","alias_value":"ZAHQOBA4FGOC","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"pith_short_16","alias_value":"ZAHQOBA4FGOCB4WN","created_at":"2026-07-05T07:03:23Z"},{"alias_kind":"pith_short_8","alias_value":"ZAHQOBA4","created_at":"2026-07-05T07:03:23Z"}],"graph_snapshots":[{"event_id":"sha256:9fe014a12e305391308e02b94f3dc82caa5d457be58b752cc4a391976f1268bf","target":"graph","created_at":"2026-07-05T07:03:23Z","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/2305.02176/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Mixture-of-experts (MoE) models that employ sparse activation have demonstrated effectiveness in significantly increasing the number of parameters while maintaining low computational requirements per token. However, recent studies have established that MoE models are inherently parameter-inefficient as the improvement in performance diminishes with an increasing number of experts. We hypothesize this parameter inefficiency is a result of all experts having equal capacity, which may not adequately meet the varying complexity requirements of different tokens or tasks. In light of this, we propos","authors_text":"Haoran Xu, Jean Maillard, Kenton Murray, Maha Elbayad, Vedanuj Goswami","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T15:18:18Z","title":"Towards Being Parameter-Efficient: A Stratified Sparsely Activated Transformer with Dynamic Capacity"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.02176","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":"sha256:2f4e393da3077fe1103d710f02dd55d47f9107263c08790dc0b49afb16560d85","target":"record","created_at":"2026-07-05T07:03:23Z","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":"e41bae5c17464582dbb87874fe09095f9dc0f1c5446935ea498e9bd2d3ae880b","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-05-03T15:18:18Z","title_canon_sha256":"731a5004e1ed86e7ca7a3f49a23d373ed8eb6dbcc02bae568dbab7792b377e3d"},"schema_version":"1.0","source":{"id":"2305.02176","kind":"arxiv","version":2}},"canonical_sha256":"c80f07041c299c20f2cd1051895d50105c6551be614bb002155b4405198437f2","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c80f07041c299c20f2cd1051895d50105c6551be614bb002155b4405198437f2","first_computed_at":"2026-07-05T07:03:23.815170Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:03:23.815170Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CM5sq3kyFv+QR0dZ7Poh4bZZ88MuDFZWAr71JznixzpElqWznd02ApcfCxM8PUe+5oCw8iE/DgeTi6MqwwxRDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:03:23.815643Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.02176","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2f4e393da3077fe1103d710f02dd55d47f9107263c08790dc0b49afb16560d85","sha256:9fe014a12e305391308e02b94f3dc82caa5d457be58b752cc4a391976f1268bf"],"state_sha256":"f619a61947c3d84ee39fece1f3b99a02f167f02fd51a75a712ce639f40c50ab1"}