{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:YTKFBTK4Y4IFJGKXBHQW4KAVJ6","short_pith_number":"pith:YTKFBTK4","schema_version":"1.0","canonical_sha256":"c4d450cd5cc71054995709e16e28154fa9dc54e9914bffe8ca677847a2312db7","source":{"kind":"arxiv","id":"2503.03213","version":1},"attestation_state":"computed","paper":{"title":"Convergence Rates for Softmax Gating Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Rinaldo, Huy Nguyen, Nhat Ho","submitted_at":"2025-03-05T06:11:24Z","abstract_excerpt":"Mixture of experts (MoE) has recently emerged as an effective framework to advance the efficiency and scalability of machine learning models by softly dividing complex tasks among multiple specialized sub-models termed experts. Central to the success of MoE is an adaptive softmax gating mechanism which takes responsibility for determining the relevance of each expert to a given input and then dynamically assigning experts their respective weights. Despite its widespread use in practice, a comprehensive study on the effects of the softmax gating on the MoE has been lacking in the literature. To"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2503.03213","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2025-03-05T06:11:24Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"71188370ff400970bbb3a965e9e1fcf6249a807e1cc56209f1efbeb4d96eae97","abstract_canon_sha256":"fcc09c2545f7ea4d046a590539ced445bb68892b854de6ce7f956976d6fb65b4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:24:41.412299Z","signature_b64":"wqtdOBNjTck8twGtYsM72Ow2KEs1kdz5BJQaBKfobbf+6bPb438U5Y6u9hL9ug7kxy6oPEznYJhdjUh5IW7WDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c4d450cd5cc71054995709e16e28154fa9dc54e9914bffe8ca677847a2312db7","last_reissued_at":"2026-07-05T10:24:41.411640Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:24:41.411640Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Convergence Rates for Softmax Gating Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Alessandro Rinaldo, Huy Nguyen, Nhat Ho","submitted_at":"2025-03-05T06:11:24Z","abstract_excerpt":"Mixture of experts (MoE) has recently emerged as an effective framework to advance the efficiency and scalability of machine learning models by softly dividing complex tasks among multiple specialized sub-models termed experts. Central to the success of MoE is an adaptive softmax gating mechanism which takes responsibility for determining the relevance of each expert to a given input and then dynamically assigning experts their respective weights. Despite its widespread use in practice, a comprehensive study on the effects of the softmax gating on the MoE has been lacking in the literature. To"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.03213","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/2503.03213/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2503.03213","created_at":"2026-07-05T10:24:41.411716+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.03213v1","created_at":"2026-07-05T10:24:41.411716+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.03213","created_at":"2026-07-05T10:24:41.411716+00:00"},{"alias_kind":"pith_short_12","alias_value":"YTKFBTK4Y4IF","created_at":"2026-07-05T10:24:41.411716+00:00"},{"alias_kind":"pith_short_16","alias_value":"YTKFBTK4Y4IFJGKX","created_at":"2026-07-05T10:24:41.411716+00:00"},{"alias_kind":"pith_short_8","alias_value":"YTKFBTK4","created_at":"2026-07-05T10:24:41.411716+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.06845","citing_title":"Convergence Rates for Latent Mixing Measures in Infinite Homoscedastic Location-Scale Mixture Models","ref_index":99,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6","json":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6.json","graph_json":"https://pith.science/api/pith-number/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/graph.json","events_json":"https://pith.science/api/pith-number/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/events.json","paper":"https://pith.science/paper/YTKFBTK4"},"agent_actions":{"view_html":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6","download_json":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6.json","view_paper":"https://pith.science/paper/YTKFBTK4","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.03213&json=true","fetch_graph":"https://pith.science/api/pith-number/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/graph.json","fetch_events":"https://pith.science/api/pith-number/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/action/storage_attestation","attest_author":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/action/author_attestation","sign_citation":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/action/citation_signature","submit_replication":"https://pith.science/pith/YTKFBTK4Y4IFJGKXBHQW4KAVJ6/action/replication_record"}},"created_at":"2026-07-05T10:24:41.411716+00:00","updated_at":"2026-07-05T10:24:41.411716+00:00"}