{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OBQALUT5KG6CPKHQFYARYL2LY7","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"e00c03214dcc48194bc6c3b89ebd9272d87226c4ef9c611998430a92e2a2b7d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T17:19:12Z","title_canon_sha256":"a82aa25f830ad0eb4fe219ef61213f182e0624b3b6e5c2bfbfb52476b0c2c03e"},"schema_version":"1.0","source":{"id":"2408.08274","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2408.08274","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"arxiv_version","alias_value":"2408.08274v2","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2408.08274","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"pith_short_12","alias_value":"OBQALUT5KG6C","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"pith_short_16","alias_value":"OBQALUT5KG6CPKHQ","created_at":"2026-07-05T08:56:24Z"},{"alias_kind":"pith_short_8","alias_value":"OBQALUT5","created_at":"2026-07-05T08:56:24Z"}],"graph_snapshots":[{"event_id":"sha256:6805b725b649d833440c42b47368bcabd547fe3dc7b18e9dc0cf23da9274dc41","target":"graph","created_at":"2026-07-05T08:56:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2408.08274/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The Mixture of Experts (MoE) framework has become a popular architecture for large language models due to its superior performance over dense models. However, training MoEs from scratch in a large-scale regime is prohibitively expensive. Existing methods mitigate this by pre-training multiple dense expert models independently and using them to initialize an MoE. This is done by using experts' feed-forward network (FFN) to initialize the MoE's experts while merging other parameters. However, this method limits the reuse of dense model parameters to only the FFN layers, thereby constraining the ","authors_text":"Acyr Locatelli, Ahmet Ustun, Bharat Venkitesh, David Cairuz, Dwaraknath Gnaneshwar, Jakob Foerster, Nikolas Gritsch, Phil Blunsom, Qizhen Zhang, Sebastian Ruder, Simon Guo","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T17:19:12Z","title":"BAM! Just Like That: Simple and Efficient Parameter Upcycling for Mixture of Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2408.08274","kind":"arxiv","version":2},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e5dfd63fb4be868e3516b6f5086b6868d85c892f4fe0be0c8d0ebba58db62787","target":"record","created_at":"2026-07-05T08:56:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"e00c03214dcc48194bc6c3b89ebd9272d87226c4ef9c611998430a92e2a2b7d0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-08-15T17:19:12Z","title_canon_sha256":"a82aa25f830ad0eb4fe219ef61213f182e0624b3b6e5c2bfbfb52476b0c2c03e"},"schema_version":"1.0","source":{"id":"2408.08274","kind":"arxiv","version":2}},"canonical_sha256":"706005d27d51bc27a8f02e011c2f4bc7f9ea2cd8547501245ccc1318a1a57d9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"706005d27d51bc27a8f02e011c2f4bc7f9ea2cd8547501245ccc1318a1a57d9f","first_computed_at":"2026-07-05T08:56:24.741806Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:56:24.741806Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"gyzWLuK4/LF5gMsSChWCxNq8LyW4FVW9tsPSMVrr7ZAzoznVgvi/BQJvsJPmUdubQHXRx6vPjuvcCSNTGSD0DQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:56:24.742312Z","signed_message":"canonical_sha256_bytes"},"source_id":"2408.08274","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e5dfd63fb4be868e3516b6f5086b6868d85c892f4fe0be0c8d0ebba58db62787","sha256:6805b725b649d833440c42b47368bcabd547fe3dc7b18e9dc0cf23da9274dc41"],"state_sha256":"e377060edb6b8e455b23409a4ae755506bc5cbc08bfe9f1a02c2aa10f7261fb4"}