{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:I4DNGOGGWFY3HAIV7PBWHE3AX6","short_pith_number":"pith:I4DNGOGG","schema_version":"1.0","canonical_sha256":"4706d338c6b171b38115fbc3639360bf8e66d3999a03cf63358cb561319a3356","source":{"kind":"arxiv","id":"2011.13635","version":1},"attestation_state":"computed","paper":{"title":"Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Yang, Cheng Yang, Jingqiao Zhang, Ru He, Shengnan Wang, Yuechuan Li","submitted_at":"2020-11-27T10:00:22Z","abstract_excerpt":"Pre-trained language models, such as BERT, have achieved significant accuracy gain in many natural language processing tasks. Despite its effectiveness, the huge number of parameters makes training a BERT model computationally very challenging. In this paper, we propose an efficient multi-stage layerwise training (MSLT) approach to reduce the training time of BERT. We decompose the whole training process into several stages. The training is started from a small model with only a few encoder layers and we gradually increase the depth of the model by adding new encoder layers. At each stage, we "},"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":"2011.13635","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-27T10:00:22Z","cross_cats_sorted":[],"title_canon_sha256":"f73447bed4c8a184d82d19d6a9a1dbc754b87b678013eb32a142348c793835fb","abstract_canon_sha256":"32526b6af27a32edac37d351ba77829dc45c5a52e4ad41613b98bc4e666a951c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:54:56.622829Z","signature_b64":"TlwnL7MDzQ08z7s4dDEdu1DvkdIeFDG9stHHLO+rF7XULJfa1geT+9WUfbLFMxiv1NPmD0Zgwyi0W3sHQXbYAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4706d338c6b171b38115fbc3639360bf8e66d3999a03cf63358cb561319a3356","last_reissued_at":"2026-07-05T01:54:56.622290Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:54:56.622290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Yang, Cheng Yang, Jingqiao Zhang, Ru He, Shengnan Wang, Yuechuan Li","submitted_at":"2020-11-27T10:00:22Z","abstract_excerpt":"Pre-trained language models, such as BERT, have achieved significant accuracy gain in many natural language processing tasks. Despite its effectiveness, the huge number of parameters makes training a BERT model computationally very challenging. In this paper, we propose an efficient multi-stage layerwise training (MSLT) approach to reduce the training time of BERT. We decompose the whole training process into several stages. The training is started from a small model with only a few encoder layers and we gradually increase the depth of the model by adding new encoder layers. At each stage, we "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13635","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/2011.13635/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":"2011.13635","created_at":"2026-07-05T01:54:56.622365+00:00"},{"alias_kind":"arxiv_version","alias_value":"2011.13635v1","created_at":"2026-07-05T01:54:56.622365+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13635","created_at":"2026-07-05T01:54:56.622365+00:00"},{"alias_kind":"pith_short_12","alias_value":"I4DNGOGGWFY3","created_at":"2026-07-05T01:54:56.622365+00:00"},{"alias_kind":"pith_short_16","alias_value":"I4DNGOGGWFY3HAIV","created_at":"2026-07-05T01:54:56.622365+00:00"},{"alias_kind":"pith_short_8","alias_value":"I4DNGOGG","created_at":"2026-07-05T01:54:56.622365+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2512.13751","citing_title":"MIDUS: Memory-Infused Depth Up-Scaling","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6","json":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6.json","graph_json":"https://pith.science/api/pith-number/I4DNGOGGWFY3HAIV7PBWHE3AX6/graph.json","events_json":"https://pith.science/api/pith-number/I4DNGOGGWFY3HAIV7PBWHE3AX6/events.json","paper":"https://pith.science/paper/I4DNGOGG"},"agent_actions":{"view_html":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6","download_json":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6.json","view_paper":"https://pith.science/paper/I4DNGOGG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2011.13635&json=true","fetch_graph":"https://pith.science/api/pith-number/I4DNGOGGWFY3HAIV7PBWHE3AX6/graph.json","fetch_events":"https://pith.science/api/pith-number/I4DNGOGGWFY3HAIV7PBWHE3AX6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6/action/storage_attestation","attest_author":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6/action/author_attestation","sign_citation":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6/action/citation_signature","submit_replication":"https://pith.science/pith/I4DNGOGGWFY3HAIV7PBWHE3AX6/action/replication_record"}},"created_at":"2026-07-05T01:54:56.622365+00:00","updated_at":"2026-07-05T01:54:56.622365+00:00"}