{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2013:PR242GRRPMROV4ICKSILG5WNFM","short_pith_number":"pith:PR242GRR","schema_version":"1.0","canonical_sha256":"7c75cd1a317b22eaf1025490b376cd2b055c389202f904db7b7130dc1d0921c0","source":{"kind":"arxiv","id":"1312.4314","version":3},"attestation_state":"computed","paper":{"title":"Learning Factored Representations in a Deep Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Eigen, Ilya Sutskever, Marc'Aurelio Ranzato","submitted_at":"2013-12-16T11:15:10Z","abstract_excerpt":"Mixtures of Experts combine the outputs of several \"expert\" networks, each of which specializes in a different part of the input space. This is achieved by training a \"gating\" network that maps each input to a distribution over the experts. Such models show promise for building larger networks that are still cheap to compute at test time, and more parallelizable at training time. In this this work, we extend the Mixture of Experts to a stacked model, the Deep Mixture of Experts, with multiple sets of gating and experts. This exponentially increases the number of effective experts by associatin"},"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":"1312.4314","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2013-12-16T11:15:10Z","cross_cats_sorted":[],"title_canon_sha256":"ee0a90c0ab6c07a06dbeeb9e3f2336f3aca4c3f7852a954ccdf33e9483028305","abstract_canon_sha256":"cadf900238aa68f9026c40de18030fb22803f253f8e978bae937417a08283563"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T02:56:51.570664Z","signature_b64":"jDufwlgLustATChbsqoU3IFfFFgY/LqLjIIZFANCIeGR6MGLYH0+WNKubWNmmivM/fcv8Cj8jZrszkaaYWyjAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7c75cd1a317b22eaf1025490b376cd2b055c389202f904db7b7130dc1d0921c0","last_reissued_at":"2026-05-18T02:56:51.570008Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T02:56:51.570008Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Learning Factored Representations in a Deep Mixture of Experts","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"David Eigen, Ilya Sutskever, Marc'Aurelio Ranzato","submitted_at":"2013-12-16T11:15:10Z","abstract_excerpt":"Mixtures of Experts combine the outputs of several \"expert\" networks, each of which specializes in a different part of the input space. This is achieved by training a \"gating\" network that maps each input to a distribution over the experts. Such models show promise for building larger networks that are still cheap to compute at test time, and more parallelizable at training time. In this this work, we extend the Mixture of Experts to a stacked model, the Deep Mixture of Experts, with multiple sets of gating and experts. This exponentially increases the number of effective experts by associatin"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1312.4314","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"1312.4314","created_at":"2026-05-18T02:56:51.570086+00:00"},{"alias_kind":"arxiv_version","alias_value":"1312.4314v3","created_at":"2026-05-18T02:56:51.570086+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1312.4314","created_at":"2026-05-18T02:56:51.570086+00:00"},{"alias_kind":"pith_short_12","alias_value":"PR242GRRPMRO","created_at":"2026-05-18T12:27:54.935989+00:00"},{"alias_kind":"pith_short_16","alias_value":"PR242GRRPMROV4IC","created_at":"2026-05-18T12:27:54.935989+00:00"},{"alias_kind":"pith_short_8","alias_value":"PR242GRR","created_at":"2026-05-18T12:27:54.935989+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":13,"internal_anchor_count":9,"sample":[{"citing_arxiv_id":"2501.14660","citing_title":"Mean-field limit from general mixtures of experts to quantum neural networks","ref_index":14,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20891","citing_title":"HDMoE: A Hierarchical Decoupling-Fusion Mixture-of-Experts Framework for Multimodal Cancer Survival Prediction","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.20908","citing_title":"SynCB: A Synergy Concept-Based Model with Dynamic Routing Between Concepts and Complementary Neural Branches","ref_index":2,"is_internal_anchor":true},{"citing_arxiv_id":"2502.05564","citing_title":"TabICL: A Tabular Foundation Model for In-Context Learning on Large Data","ref_index":139,"is_internal_anchor":true},{"citing_arxiv_id":"2605.17743","citing_title":"MoASE++: Mixture of Activation Sparsity Experts with Domain-Adaptive On-policy Distillation for Continual Test Time Adaptation","ref_index":49,"is_internal_anchor":true},{"citing_arxiv_id":"2403.12031","citing_title":"RouterBench: A Benchmark for Multi-LLM Routing System","ref_index":28,"is_internal_anchor":true},{"citing_arxiv_id":"2401.15947","citing_title":"MoE-LLaVA: Mixture of Experts for Large Vision-Language Models","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14200","citing_title":"How to Scale Mixture-of-Experts: From muP to the Maximally Scale-Stable Parameterization","ref_index":15,"is_internal_anchor":true},{"citing_arxiv_id":"2401.01335","citing_title":"Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2101.03961","citing_title":"Switch Transformers: Scaling to Trillion Parameter Models with Simple and Efficient Sparsity","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2202.08906","citing_title":"ST-MoE: Designing Stable and Transferable Sparse Expert Models","ref_index":145,"is_internal_anchor":false},{"citing_arxiv_id":"2604.13761","citing_title":"Design and Behavior of Sparse Mixture-of-Experts Layers in CNN-based Semantic Segmentation","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"1701.06538","citing_title":"Outrageously Large Neural Networks: The Sparsely-Gated Mixture-of-Experts Layer","ref_index":16,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM","json":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM.json","graph_json":"https://pith.science/api/pith-number/PR242GRRPMROV4ICKSILG5WNFM/graph.json","events_json":"https://pith.science/api/pith-number/PR242GRRPMROV4ICKSILG5WNFM/events.json","paper":"https://pith.science/paper/PR242GRR"},"agent_actions":{"view_html":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM","download_json":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM.json","view_paper":"https://pith.science/paper/PR242GRR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1312.4314&json=true","fetch_graph":"https://pith.science/api/pith-number/PR242GRRPMROV4ICKSILG5WNFM/graph.json","fetch_events":"https://pith.science/api/pith-number/PR242GRRPMROV4ICKSILG5WNFM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM/action/storage_attestation","attest_author":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM/action/author_attestation","sign_citation":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM/action/citation_signature","submit_replication":"https://pith.science/pith/PR242GRRPMROV4ICKSILG5WNFM/action/replication_record"}},"created_at":"2026-05-18T02:56:51.570086+00:00","updated_at":"2026-05-18T02:56:51.570086+00:00"}