{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:KYZF5XUTT7KBMRMOVGCL6XGGBE","short_pith_number":"pith:KYZF5XUT","schema_version":"1.0","canonical_sha256":"56325ede939fd416458ea984bf5cc609181b70cd543a9facec4f51c5bbd77575","source":{"kind":"arxiv","id":"2505.20225","version":1},"attestation_state":"computed","paper":{"title":"FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenyan Xiong, Hao Kang, Zichun Yu","submitted_at":"2025-05-26T17:06:25Z","abstract_excerpt":"Recent large language models such as Gemini-1.5, DeepSeek-V3, and Llama-4 increasingly adopt Mixture-of-Experts (MoE) architectures, which offer strong efficiency-performance trade-offs by activating only a fraction of the model per token. Yet academic researchers still lack a fully open, end-to-end MoE platform for investigating scaling, routing, and expert behavior. We release FLAME-MoE, a completely open-source research suite composed of seven decoder-only models, ranging from 38M to 1.7B active parameters, whose architecture--64 experts with top-8 gating and 2 shared experts--closely refle"},"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":"2505.20225","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-26T17:06:25Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"dc1cc9a0aec5efae75184d4ff751973d1b620b139a9b04b758bfa716131130f3","abstract_canon_sha256":"ad5e7b5c8ac39731c7c285af8c66f897577063145c650196832923439b46a068"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:54.485107Z","signature_b64":"wPcmXqhatElfVf/3mVIFqu8GwBnxrj9jNGmGEVIUt3j3rnbc+ZIR8CHZOgF/Y1xlJIIhTkVUx4qS/cumjNjpCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"56325ede939fd416458ea984bf5cc609181b70cd543a9facec4f51c5bbd77575","last_reissued_at":"2026-07-05T11:09:54.484634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:54.484634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"FLAME-MoE: A Transparent End-to-End Research Platform for Mixture-of-Experts Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenyan Xiong, Hao Kang, Zichun Yu","submitted_at":"2025-05-26T17:06:25Z","abstract_excerpt":"Recent large language models such as Gemini-1.5, DeepSeek-V3, and Llama-4 increasingly adopt Mixture-of-Experts (MoE) architectures, which offer strong efficiency-performance trade-offs by activating only a fraction of the model per token. Yet academic researchers still lack a fully open, end-to-end MoE platform for investigating scaling, routing, and expert behavior. We release FLAME-MoE, a completely open-source research suite composed of seven decoder-only models, ranging from 38M to 1.7B active parameters, whose architecture--64 experts with top-8 gating and 2 shared experts--closely refle"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.20225","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/2505.20225/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":"2505.20225","created_at":"2026-07-05T11:09:54.484689+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.20225v1","created_at":"2026-07-05T11:09:54.484689+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.20225","created_at":"2026-07-05T11:09:54.484689+00:00"},{"alias_kind":"pith_short_12","alias_value":"KYZF5XUTT7KB","created_at":"2026-07-05T11:09:54.484689+00:00"},{"alias_kind":"pith_short_16","alias_value":"KYZF5XUTT7KBMRMO","created_at":"2026-07-05T11:09:54.484689+00:00"},{"alias_kind":"pith_short_8","alias_value":"KYZF5XUT","created_at":"2026-07-05T11:09:54.484689+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE","json":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE.json","graph_json":"https://pith.science/api/pith-number/KYZF5XUTT7KBMRMOVGCL6XGGBE/graph.json","events_json":"https://pith.science/api/pith-number/KYZF5XUTT7KBMRMOVGCL6XGGBE/events.json","paper":"https://pith.science/paper/KYZF5XUT"},"agent_actions":{"view_html":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE","download_json":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE.json","view_paper":"https://pith.science/paper/KYZF5XUT","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.20225&json=true","fetch_graph":"https://pith.science/api/pith-number/KYZF5XUTT7KBMRMOVGCL6XGGBE/graph.json","fetch_events":"https://pith.science/api/pith-number/KYZF5XUTT7KBMRMOVGCL6XGGBE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE/action/storage_attestation","attest_author":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE/action/author_attestation","sign_citation":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE/action/citation_signature","submit_replication":"https://pith.science/pith/KYZF5XUTT7KBMRMOVGCL6XGGBE/action/replication_record"}},"created_at":"2026-07-05T11:09:54.484689+00:00","updated_at":"2026-07-05T11:09:54.484689+00:00"}