{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7Z7JURQPLRDOMMFIMRVXYKFHDS","short_pith_number":"pith:7Z7JURQP","schema_version":"1.0","canonical_sha256":"fe7e9a460f5c46e630a8646b7c28a71cb48b9cfec5572b90e01a66762cde8c27","source":{"kind":"arxiv","id":"2411.00918","version":5},"attestation_state":"computed","paper":{"title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Luong Tran, Nam V. Nguyen, Quang Pham, Thong T. Doan, Van Nguyen","submitted_at":"2024-11-01T14:04:36Z","abstract_excerpt":"Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains severely constrained by the prohibitive computational costs of training and evaluation, restricting large-scale studies accessible to most researchers. We introduce LibMoE, a unified framework for reproducible, efficient, and extensible MoE research that supports both pretraining and sparse-upcycling regimes. Beyond unified implementations, the framework provides t"},"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":"2411.00918","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-11-01T14:04:36Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cc0868633d105998004a105a8e41b5e0a9fddc09436088ca656edda4be7cd6fc","abstract_canon_sha256":"177d7e56c935363c3e759da1b25d52cf311aaadddfcc21f4419546ce6af1dea2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-28T01:22:18.521210Z","signature_b64":"xSVwSSF+cxr+1yNb8Vi62tSRXe6bkuZBYxwlJj/EwDfhAbVYY7EZLQOG1/cgqdctdAmXhCLyh7JSC9rPOHYFAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe7e9a460f5c46e630a8646b7c28a71cb48b9cfec5572b90e01a66762cde8c27","last_reissued_at":"2026-07-28T01:22:18.520187Z","signature_status":"signed_v1","first_computed_at":"2026-07-28T01:22:18.520187Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"LIBMoE: A Library for comprehensive benchmarking Mixture of Experts in Large Language Models","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Luong Tran, Nam V. Nguyen, Quang Pham, Thong T. Doan, Van Nguyen","submitted_at":"2024-11-01T14:04:36Z","abstract_excerpt":"Mixture of experts (MoE) architectures have become a cornerstone for scaling up and are a key component in most large language models such as GPT-OSS, DeepSeek-V3, Llama-4, and Gemini-2.5. However, systematic research on MoE remains severely constrained by the prohibitive computational costs of training and evaluation, restricting large-scale studies accessible to most researchers. We introduce LibMoE, a unified framework for reproducible, efficient, and extensible MoE research that supports both pretraining and sparse-upcycling regimes. Beyond unified implementations, the framework provides t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.00918","kind":"arxiv","version":5},"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/2411.00918/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":"2411.00918","created_at":"2026-07-28T01:22:18.520646+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.00918v5","created_at":"2026-07-28T01:22:18.520646+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.00918","created_at":"2026-07-28T01:22:18.520646+00:00"},{"alias_kind":"pith_short_12","alias_value":"7Z7JURQPLRDO","created_at":"2026-07-28T01:22:18.520646+00:00"},{"alias_kind":"pith_short_16","alias_value":"7Z7JURQPLRDOMMFI","created_at":"2026-07-28T01:22:18.520646+00:00"},{"alias_kind":"pith_short_8","alias_value":"7Z7JURQP","created_at":"2026-07-28T01:22:18.520646+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/7Z7JURQPLRDOMMFIMRVXYKFHDS","json":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS.json","graph_json":"https://pith.science/api/pith-number/7Z7JURQPLRDOMMFIMRVXYKFHDS/graph.json","events_json":"https://pith.science/api/pith-number/7Z7JURQPLRDOMMFIMRVXYKFHDS/events.json","paper":"https://pith.science/paper/7Z7JURQP"},"agent_actions":{"view_html":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS","download_json":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS.json","view_paper":"https://pith.science/paper/7Z7JURQP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.00918&json=true","fetch_graph":"https://pith.science/api/pith-number/7Z7JURQPLRDOMMFIMRVXYKFHDS/graph.json","fetch_events":"https://pith.science/api/pith-number/7Z7JURQPLRDOMMFIMRVXYKFHDS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS/action/storage_attestation","attest_author":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS/action/author_attestation","sign_citation":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS/action/citation_signature","submit_replication":"https://pith.science/pith/7Z7JURQPLRDOMMFIMRVXYKFHDS/action/replication_record"}},"created_at":"2026-07-28T01:22:18.520646+00:00","updated_at":"2026-07-28T01:22:18.520646+00:00"}