{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:Q3HYWGW2TG7DI3OGACW2TUKGFL","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":"bc929dc5a4afc6a8193e6fb7896df3f3d91b7aa8a1cafa457dd9b01851ed4f74","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T08:00:00Z","title_canon_sha256":"0b3de4882233cbaee5d4f4d4eca95f6b237dcccbab412bf983ff2a841e02648f"},"schema_version":"1.0","source":{"id":"2405.15319","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2405.15319","created_at":"2026-07-05T09:23:50Z"},{"alias_kind":"arxiv_version","alias_value":"2405.15319v2","created_at":"2026-07-05T09:23:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15319","created_at":"2026-07-05T09:23:50Z"},{"alias_kind":"pith_short_12","alias_value":"Q3HYWGW2TG7D","created_at":"2026-07-05T09:23:50Z"},{"alias_kind":"pith_short_16","alias_value":"Q3HYWGW2TG7DI3OG","created_at":"2026-07-05T09:23:50Z"},{"alias_kind":"pith_short_8","alias_value":"Q3HYWGW2","created_at":"2026-07-05T09:23:50Z"}],"graph_snapshots":[{"event_id":"sha256:1bf4070c81060d3c44a9e6091117e87c9cb9d0ce17eee329c35ea5c9ab4dbfea","target":"graph","created_at":"2026-07-05T09:23:50Z","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/2405.15319/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLMs are computationally expensive to pre-train due to their large scale. Model growth emerges as a promising approach by leveraging smaller models to accelerate the training of larger ones. However, the viability of these model growth methods in efficient LLM pre-training remains underexplored. This work identifies three critical $\\underline{\\textit{O}}$bstacles: ($\\textit{O}$1) lack of comprehensive evaluation, ($\\textit{O}$2) untested viability for scaling, and ($\\textit{O}$3) lack of empirical guidelines. To tackle $\\textit{O}$1, we summarize existing approaches into four atomic growth ope","authors_text":"Jie Fu, Reynold Cheng, Tongxu Luo, Wenyu Du, Yikang Shen, Yike Guo, Zeyu Huang, Zihan Qiu","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T08:00:00Z","title":"Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15319","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":"sha256:7ca689b6bbe78ee065f345934f049a10b96465ee997b36c08b9a3dccee45b6fb","target":"record","created_at":"2026-07-05T09:23:50Z","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":"bc929dc5a4afc6a8193e6fb7896df3f3d91b7aa8a1cafa457dd9b01851ed4f74","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T08:00:00Z","title_canon_sha256":"0b3de4882233cbaee5d4f4d4eca95f6b237dcccbab412bf983ff2a841e02648f"},"schema_version":"1.0","source":{"id":"2405.15319","kind":"arxiv","version":2}},"canonical_sha256":"86cf8b1ada99be346dc600ada9d1462afea573394649743a2dd9126f3ec441e8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"86cf8b1ada99be346dc600ada9d1462afea573394649743a2dd9126f3ec441e8","first_computed_at":"2026-07-05T09:23:50.759658Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:23:50.759658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"hF1IazfQONLyPieHRWrg2nq0e/uPIBj0k24yj1s8n9/v0dDbh2sUbwexlD6VTagrYCCduyoUGEfDTLzTTyNeCg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:23:50.760134Z","signed_message":"canonical_sha256_bytes"},"source_id":"2405.15319","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ca689b6bbe78ee065f345934f049a10b96465ee997b36c08b9a3dccee45b6fb","sha256:1bf4070c81060d3c44a9e6091117e87c9cb9d0ce17eee329c35ea5c9ab4dbfea"],"state_sha256":"fea436e95624864627fc8f655d40c4cf2559542b8f2ce1208c43f723e394a565"}