{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:ST3TMZGLGI7YNDZEQYYMXQ3MPQ","short_pith_number":"pith:ST3TMZGL","schema_version":"1.0","canonical_sha256":"94f73664cb323f868f248630cbc36c7c0b46c705fd315f015ec325cc572d084f","source":{"kind":"arxiv","id":"2411.18700","version":1},"attestation_state":"computed","paper":{"title":"On the Effectiveness of Incremental Training of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin C. M. Fung, Miles Q. Li, Shih-Chia Huang","submitted_at":"2024-11-27T19:11:49Z","abstract_excerpt":"Training large language models is a computationally intensive process that often requires substantial resources to achieve state-of-the-art results. Incremental layer-wise training has been proposed as a potential strategy to optimize the training process by progressively introducing layers, with the expectation that this approach would lead to faster convergence and more efficient use of computational resources. In this paper, we investigate the effectiveness of incremental training for LLMs, dividing the training process into multiple stages where layers are added progressively. Our experime"},"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":"2411.18700","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-11-27T19:11:49Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"2d29eda79b412d577b759468fe305738a0739bdc5e94b6deaac6f4f94da87493","abstract_canon_sha256":"e78750d0fbc3d4bf1ce7f1ab4970dcfb824cf8df32d0e0e2b5687f04b330dd16"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:41:49.885420Z","signature_b64":"39TjRlMnbKr0X9tD8FXOAwVU6LCgO2z8Ss2jmGdC1MpcpFiegXUA1i3jI2/YFojPBQoNzwvVhj2HTaBGZBlaAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"94f73664cb323f868f248630cbc36c7c0b46c705fd315f015ec325cc572d084f","last_reissued_at":"2026-07-05T09:41:49.884933Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:41:49.884933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"On the Effectiveness of Incremental Training of Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Benjamin C. M. Fung, Miles Q. Li, Shih-Chia Huang","submitted_at":"2024-11-27T19:11:49Z","abstract_excerpt":"Training large language models is a computationally intensive process that often requires substantial resources to achieve state-of-the-art results. Incremental layer-wise training has been proposed as a potential strategy to optimize the training process by progressively introducing layers, with the expectation that this approach would lead to faster convergence and more efficient use of computational resources. In this paper, we investigate the effectiveness of incremental training for LLMs, dividing the training process into multiple stages where layers are added progressively. Our experime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.18700","kind":"arxiv","version":1},"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/2411.18700/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":"2411.18700","created_at":"2026-07-05T09:41:49.884991+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.18700v1","created_at":"2026-07-05T09:41:49.884991+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.18700","created_at":"2026-07-05T09:41:49.884991+00:00"},{"alias_kind":"pith_short_12","alias_value":"ST3TMZGLGI7Y","created_at":"2026-07-05T09:41:49.884991+00:00"},{"alias_kind":"pith_short_16","alias_value":"ST3TMZGLGI7YNDZE","created_at":"2026-07-05T09:41:49.884991+00:00"},{"alias_kind":"pith_short_8","alias_value":"ST3TMZGL","created_at":"2026-07-05T09:41:49.884991+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/ST3TMZGLGI7YNDZEQYYMXQ3MPQ","json":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ.json","graph_json":"https://pith.science/api/pith-number/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/graph.json","events_json":"https://pith.science/api/pith-number/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/events.json","paper":"https://pith.science/paper/ST3TMZGL"},"agent_actions":{"view_html":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ","download_json":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ.json","view_paper":"https://pith.science/paper/ST3TMZGL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.18700&json=true","fetch_graph":"https://pith.science/api/pith-number/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/graph.json","fetch_events":"https://pith.science/api/pith-number/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/action/storage_attestation","attest_author":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/action/author_attestation","sign_citation":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/action/citation_signature","submit_replication":"https://pith.science/pith/ST3TMZGLGI7YNDZEQYYMXQ3MPQ/action/replication_record"}},"created_at":"2026-07-05T09:41:49.884991+00:00","updated_at":"2026-07-05T09:41:49.884991+00:00"}