{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:NFSBEUEJDE67NTYWE3GSX4NYME","short_pith_number":"pith:NFSBEUEJ","schema_version":"1.0","canonical_sha256":"6964125089193df6cf1626cd2bf1b8610a50a0e728e9a0f2e8f1def271767b25","source":{"kind":"arxiv","id":"2407.06204","version":3},"attestation_state":"computed","paper":{"title":"A Survey on Mixture of Experts in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Fan Wang, Jiayi Huang, Jing Tang, Juyong Jiang, Sunghun Kim, Weilin Cai","submitted_at":"2024-06-26T16:34:33Z","abstract_excerpt":"Large language models (LLMs) have garnered unprecedented advancements across diverse fields, ranging from natural language processing to computer vision and beyond. The prowess of LLMs is underpinned by their substantial model size, extensive and diverse datasets, and the vast computational power harnessed during training, all of which contribute to the emergent abilities of LLMs (e.g., in-context learning) that are not present in small models. Within this context, the mixture of experts (MoE) has emerged as an effective method for substantially scaling up model capacity with minimal computati"},"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":"2407.06204","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-06-26T16:34:33Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"5ec74651f55fa8da2e4cae45afd05c714a01882b14481dbb9556776110f1cc83","abstract_canon_sha256":"0c26507c701d046b93939a9d514421083923df35d025a10a7166fd5fa722196e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:46:37.658412Z","signature_b64":"O6dnscSSj1Hms6AS47stUgxjCYy/nmEQYeS941yjiC3tbvd0q2as27nIPmxsoz8KgV+m5B+A5R7xseder+YvAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6964125089193df6cf1626cd2bf1b8610a50a0e728e9a0f2e8f1def271767b25","last_reissued_at":"2026-07-05T10:46:37.657934Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:46:37.657934Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Survey on Mixture of Experts in Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Fan Wang, Jiayi Huang, Jing Tang, Juyong Jiang, Sunghun Kim, Weilin Cai","submitted_at":"2024-06-26T16:34:33Z","abstract_excerpt":"Large language models (LLMs) have garnered unprecedented advancements across diverse fields, ranging from natural language processing to computer vision and beyond. The prowess of LLMs is underpinned by their substantial model size, extensive and diverse datasets, and the vast computational power harnessed during training, all of which contribute to the emergent abilities of LLMs (e.g., in-context learning) that are not present in small models. Within this context, the mixture of experts (MoE) has emerged as an effective method for substantially scaling up model capacity with minimal computati"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.06204","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":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2407.06204/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":"2407.06204","created_at":"2026-07-05T10:46:37.657990+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.06204v3","created_at":"2026-07-05T10:46:37.657990+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.06204","created_at":"2026-07-05T10:46:37.657990+00:00"},{"alias_kind":"pith_short_12","alias_value":"NFSBEUEJDE67","created_at":"2026-07-05T10:46:37.657990+00:00"},{"alias_kind":"pith_short_16","alias_value":"NFSBEUEJDE67NTYW","created_at":"2026-07-05T10:46:37.657990+00:00"},{"alias_kind":"pith_short_8","alias_value":"NFSBEUEJ","created_at":"2026-07-05T10:46:37.657990+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":10,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.31397","citing_title":"Mixture-of-Control: State-Aware Fine-Tuning for Transformer-based Models","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.24399","citing_title":"ConceptM$^3$oE: Concept-Guided Multimodal Mixture of Experts for Interpretable Computational Pathology","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2509.15105","citing_title":"Super-Linear: A Lightweight Pretrained Mixture of Linear Experts for Time Series Forecasting","ref_index":5,"is_internal_anchor":false},{"citing_arxiv_id":"2503.05066","citing_title":"Capacity-Aware Inference: Mitigating the Straggler Effect in Mixture of Experts","ref_index":2,"is_internal_anchor":false},{"citing_arxiv_id":"2505.15325","citing_title":"SoftHGNN: Soft Hypergraph Neural Networks for General Visual Recognition","ref_index":47,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15104","citing_title":"From Text to Voice: A Reproducible and Verifiable Framework for Evaluating Tool Calling LLM Agents","ref_index":123,"is_internal_anchor":false},{"citing_arxiv_id":"2605.15484","citing_title":"When Does Sparse MoE Help in Vision? The Role of Backbone Compute Leverage in Sparse Routing","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2406.00515","citing_title":"A Survey on Large Language Models for Code Generation","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2501.06322","citing_title":"Multi-Agent Collaboration Mechanisms: A Survey of LLMs","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.09208","citing_title":"TSNN: A Non-parametric and Interpretable Framework for Traffic Time Series Forecasting","ref_index":71,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME","json":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME.json","graph_json":"https://pith.science/api/pith-number/NFSBEUEJDE67NTYWE3GSX4NYME/graph.json","events_json":"https://pith.science/api/pith-number/NFSBEUEJDE67NTYWE3GSX4NYME/events.json","paper":"https://pith.science/paper/NFSBEUEJ"},"agent_actions":{"view_html":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME","download_json":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME.json","view_paper":"https://pith.science/paper/NFSBEUEJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.06204&json=true","fetch_graph":"https://pith.science/api/pith-number/NFSBEUEJDE67NTYWE3GSX4NYME/graph.json","fetch_events":"https://pith.science/api/pith-number/NFSBEUEJDE67NTYWE3GSX4NYME/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME/action/storage_attestation","attest_author":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME/action/author_attestation","sign_citation":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME/action/citation_signature","submit_replication":"https://pith.science/pith/NFSBEUEJDE67NTYWE3GSX4NYME/action/replication_record"}},"created_at":"2026-07-05T10:46:37.657990+00:00","updated_at":"2026-07-05T10:46:37.657990+00:00"}