{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:Q3HYWGW2TG7DI3OGACW2TUKGFL","short_pith_number":"pith:Q3HYWGW2","schema_version":"1.0","canonical_sha256":"86cf8b1ada99be346dc600ada9d1462afea573394649743a2dd9126f3ec441e8","source":{"kind":"arxiv","id":"2405.15319","version":2},"attestation_state":"computed","paper":{"title":"Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jie Fu, Reynold Cheng, Tongxu Luo, Wenyu Du, Yikang Shen, Yike Guo, Zeyu Huang, Zihan Qiu","submitted_at":"2024-05-24T08:00:00Z","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"},"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":"2405.15319","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-05-24T08:00:00Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"0b3de4882233cbaee5d4f4d4eca95f6b237dcccbab412bf983ff2a841e02648f","abstract_canon_sha256":"bc929dc5a4afc6a8193e6fb7896df3f3d91b7aa8a1cafa457dd9b01851ed4f74"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:23:50.760134Z","signature_b64":"hF1IazfQONLyPieHRWrg2nq0e/uPIBj0k24yj1s8n9/v0dDbh2sUbwexlD6VTagrYCCduyoUGEfDTLzTTyNeCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"86cf8b1ada99be346dc600ada9d1462afea573394649743a2dd9126f3ec441e8","last_reissued_at":"2026-07-05T09:23:50.759658Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:23:50.759658Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Stacking Your Transformers: A Closer Look at Model Growth for Efficient LLM Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Jie Fu, Reynold Cheng, Tongxu Luo, Wenyu Du, Yikang Shen, Yike Guo, Zeyu Huang, Zihan Qiu","submitted_at":"2024-05-24T08:00:00Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.15319","kind":"arxiv","version":2},"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/2405.15319/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":"2405.15319","created_at":"2026-07-05T09:23:50.759723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.15319v2","created_at":"2026-07-05T09:23:50.759723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.15319","created_at":"2026-07-05T09:23:50.759723+00:00"},{"alias_kind":"pith_short_12","alias_value":"Q3HYWGW2TG7D","created_at":"2026-07-05T09:23:50.759723+00:00"},{"alias_kind":"pith_short_16","alias_value":"Q3HYWGW2TG7DI3OG","created_at":"2026-07-05T09:23:50.759723+00:00"},{"alias_kind":"pith_short_8","alias_value":"Q3HYWGW2","created_at":"2026-07-05T09:23:50.759723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.06518","citing_title":"Crown, Frame, Reverse: Layer-Wise Scaling Variants for LLM Pre-Training","ref_index":8,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL","json":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL.json","graph_json":"https://pith.science/api/pith-number/Q3HYWGW2TG7DI3OGACW2TUKGFL/graph.json","events_json":"https://pith.science/api/pith-number/Q3HYWGW2TG7DI3OGACW2TUKGFL/events.json","paper":"https://pith.science/paper/Q3HYWGW2"},"agent_actions":{"view_html":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL","download_json":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL.json","view_paper":"https://pith.science/paper/Q3HYWGW2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.15319&json=true","fetch_graph":"https://pith.science/api/pith-number/Q3HYWGW2TG7DI3OGACW2TUKGFL/graph.json","fetch_events":"https://pith.science/api/pith-number/Q3HYWGW2TG7DI3OGACW2TUKGFL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL/action/storage_attestation","attest_author":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL/action/author_attestation","sign_citation":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL/action/citation_signature","submit_replication":"https://pith.science/pith/Q3HYWGW2TG7DI3OGACW2TUKGFL/action/replication_record"}},"created_at":"2026-07-05T09:23:50.759723+00:00","updated_at":"2026-07-05T09:23:50.759723+00:00"}