{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7QLHQ4WXEW3GBJV3ZYA6Z5XR3H","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":"652511d4648e3519d85445484d3c8e629788cb53590303e7f48a7fd1866630d3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T16:54:58Z","title_canon_sha256":"33ccc20270f6c267683e11f26f635ffb2b5d6686e604de6951266405492a58cc"},"schema_version":"1.0","source":{"id":"2403.07816","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2403.07816","created_at":"2026-07-05T07:55:15Z"},{"alias_kind":"arxiv_version","alias_value":"2403.07816v1","created_at":"2026-07-05T07:55:15Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2403.07816","created_at":"2026-07-05T07:55:15Z"},{"alias_kind":"pith_short_12","alias_value":"7QLHQ4WXEW3G","created_at":"2026-07-05T07:55:15Z"},{"alias_kind":"pith_short_16","alias_value":"7QLHQ4WXEW3GBJV3","created_at":"2026-07-05T07:55:15Z"},{"alias_kind":"pith_short_8","alias_value":"7QLHQ4WX","created_at":"2026-07-05T07:55:15Z"}],"graph_snapshots":[{"event_id":"sha256:7d4c96c2ed6396f21d6ac5e8759806c22785e79647bbdd076a5c538fee1ff43c","target":"graph","created_at":"2026-07-05T07:55:15Z","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/2403.07816/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We investigate efficient methods for training Large Language Models (LLMs) to possess capabilities in multiple specialized domains, such as coding, math reasoning and world knowledge. Our method, named Branch-Train-MiX (BTX), starts from a seed model, which is branched to train experts in embarrassingly parallel fashion with high throughput and reduced communication cost. After individual experts are asynchronously trained, BTX brings together their feedforward parameters as experts in Mixture-of-Expert (MoE) layers and averages the remaining parameters, followed by an MoE-finetuning stage to ","authors_text":"Baptiste Rozi\\`ere, Daniel Li, Hu Xu, Jacob Kahn, Jason Weston, Olga Golovneva, Sainbayar Sukhbaatar, Vasu Sharma, Wen-tau Yih, Xian Li, Xi Victoria Lin","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T16:54:58Z","title":"Branch-Train-MiX: Mixing Expert LLMs into a Mixture-of-Experts LLM"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2403.07816","kind":"arxiv","version":1},"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":"sha256:7f07f0351ecf2f689cd6ca2282a554c1126e860628b8d576dc739c6bff41c44a","target":"record","created_at":"2026-07-05T07:55:15Z","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":"652511d4648e3519d85445484d3c8e629788cb53590303e7f48a7fd1866630d3","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-03-12T16:54:58Z","title_canon_sha256":"33ccc20270f6c267683e11f26f635ffb2b5d6686e604de6951266405492a58cc"},"schema_version":"1.0","source":{"id":"2403.07816","kind":"arxiv","version":1}},"canonical_sha256":"fc167872d725b660a6bbce01ecf6f1d9f2e24be26209d76bbd992b22a73f5960","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fc167872d725b660a6bbce01ecf6f1d9f2e24be26209d76bbd992b22a73f5960","first_computed_at":"2026-07-05T07:55:15.924753Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:55:15.924753Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ZGCCqJ9lVQDpRLTby3VK/8g0Ac9bEwxaA0QNFkgKn6OSk6Iz6rP+qHGyMAlQfPb7kvZo16oCzreQCIJwfAtoDg==","signature_status":"signed_v1","signed_at":"2026-07-05T07:55:15.925242Z","signed_message":"canonical_sha256_bytes"},"source_id":"2403.07816","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7f07f0351ecf2f689cd6ca2282a554c1126e860628b8d576dc739c6bff41c44a","sha256:7d4c96c2ed6396f21d6ac5e8759806c22785e79647bbdd076a5c538fee1ff43c"],"state_sha256":"5eb74e8a14a3da72c9c897af35c7c448a19f807b0f3da7ca2fd1d774c8bd0a3f"}