{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:7CU47J5KDR3MCZ3GW6DQELXQH4","short_pith_number":"pith:7CU47J5K","schema_version":"1.0","canonical_sha256":"f8a9cfa7aa1c76c16766b787022ef03f1c24feda2629ed641d0c530abbe11ad4","source":{"kind":"arxiv","id":"2310.14188","version":2},"attestation_state":"computed","paper":{"title":"A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Huy Nguyen, Nhat Ho, Pedram Akbarian, TrungTin Nguyen","submitted_at":"2023-10-22T05:32:19Z","abstract_excerpt":"Mixture-of-experts (MoE) model incorporates the power of multiple submodels via gating functions to achieve greater performance in numerous regression and classification applications. From a theoretical perspective, while there have been previous attempts to comprehend the behavior of that model under the regression settings through the convergence analysis of maximum likelihood estimation in the Gaussian MoE model, such analysis under the setting of a classification problem has remained missing in the literature. We close this gap by establishing the convergence rates of density estimation an"},"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":"2310.14188","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"stat.ML","submitted_at":"2023-10-22T05:32:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c640ff895e0e43b3f4b445c4ccf424033ec18343058a2644d1e5973d2003f835","abstract_canon_sha256":"fbcd2530d0ccbfef77d8e525554859524c7c434890b45c00b9ea2ae866ffc637"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:35:38.579223Z","signature_b64":"z9+pzqX1RvPQHDGTdncE6gT17HJZRgwcaPw1Utle+o5tNsfU3QdR7X67ZKeBx/CXN0z1K7bjHP1TMIRsiTHHAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f8a9cfa7aa1c76c16766b787022ef03f1c24feda2629ed641d0c530abbe11ad4","last_reissued_at":"2026-07-05T08:35:38.578795Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:35:38.578795Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A General Theory for Softmax Gating Multinomial Logistic Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"stat.ML","authors_text":"Huy Nguyen, Nhat Ho, Pedram Akbarian, TrungTin Nguyen","submitted_at":"2023-10-22T05:32:19Z","abstract_excerpt":"Mixture-of-experts (MoE) model incorporates the power of multiple submodels via gating functions to achieve greater performance in numerous regression and classification applications. From a theoretical perspective, while there have been previous attempts to comprehend the behavior of that model under the regression settings through the convergence analysis of maximum likelihood estimation in the Gaussian MoE model, such analysis under the setting of a classification problem has remained missing in the literature. We close this gap by establishing the convergence rates of density estimation an"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.14188","kind":"arxiv","version":2},"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/2310.14188/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":"2310.14188","created_at":"2026-07-05T08:35:38.578850+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.14188v2","created_at":"2026-07-05T08:35:38.578850+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.14188","created_at":"2026-07-05T08:35:38.578850+00:00"},{"alias_kind":"pith_short_12","alias_value":"7CU47J5KDR3M","created_at":"2026-07-05T08:35:38.578850+00:00"},{"alias_kind":"pith_short_16","alias_value":"7CU47J5KDR3MCZ3G","created_at":"2026-07-05T08:35:38.578850+00:00"},{"alias_kind":"pith_short_8","alias_value":"7CU47J5K","created_at":"2026-07-05T08:35:38.578850+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2602.03204","citing_title":"Sparsity is Combinatorial Depth: Quantifying MoE Expressivity via Tropical Geometry","ref_index":11,"is_internal_anchor":false},{"citing_arxiv_id":"2605.06845","citing_title":"Convergence Rates for Latent Mixing Measures in Infinite Homoscedastic Location-Scale Mixture Models","ref_index":109,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4","json":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4.json","graph_json":"https://pith.science/api/pith-number/7CU47J5KDR3MCZ3GW6DQELXQH4/graph.json","events_json":"https://pith.science/api/pith-number/7CU47J5KDR3MCZ3GW6DQELXQH4/events.json","paper":"https://pith.science/paper/7CU47J5K"},"agent_actions":{"view_html":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4","download_json":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4.json","view_paper":"https://pith.science/paper/7CU47J5K","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.14188&json=true","fetch_graph":"https://pith.science/api/pith-number/7CU47J5KDR3MCZ3GW6DQELXQH4/graph.json","fetch_events":"https://pith.science/api/pith-number/7CU47J5KDR3MCZ3GW6DQELXQH4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4/action/storage_attestation","attest_author":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4/action/author_attestation","sign_citation":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4/action/citation_signature","submit_replication":"https://pith.science/pith/7CU47J5KDR3MCZ3GW6DQELXQH4/action/replication_record"}},"created_at":"2026-07-05T08:35:38.578850+00:00","updated_at":"2026-07-05T08:35:38.578850+00:00"}