{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:I4DNGOGGWFY3HAIV7PBWHE3AX6","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":"32526b6af27a32edac37d351ba77829dc45c5a52e4ad41613b98bc4e666a951c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-27T10:00:22Z","title_canon_sha256":"f73447bed4c8a184d82d19d6a9a1dbc754b87b678013eb32a142348c793835fb"},"schema_version":"1.0","source":{"id":"2011.13635","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2011.13635","created_at":"2026-07-05T01:54:56Z"},{"alias_kind":"arxiv_version","alias_value":"2011.13635v1","created_at":"2026-07-05T01:54:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2011.13635","created_at":"2026-07-05T01:54:56Z"},{"alias_kind":"pith_short_12","alias_value":"I4DNGOGGWFY3","created_at":"2026-07-05T01:54:56Z"},{"alias_kind":"pith_short_16","alias_value":"I4DNGOGGWFY3HAIV","created_at":"2026-07-05T01:54:56Z"},{"alias_kind":"pith_short_8","alias_value":"I4DNGOGG","created_at":"2026-07-05T01:54:56Z"}],"graph_snapshots":[{"event_id":"sha256:6630c99d629c8cfc69494870553248929cc701a9825aca6a5f6bec1c950ac553","target":"graph","created_at":"2026-07-05T01:54:56Z","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/2011.13635/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Chao Yang, Cheng Yang, Jingqiao Zhang, Ru He, Shengnan Wang, Yuechuan Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-27T10:00:22Z","title":"Progressively Stacking 2.0: A Multi-stage Layerwise Training Method for BERT Training Speedup"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2011.13635","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:bc3cec73f5f5eeaf71a1cb30736567fa675b896c3c40ee93652b7f7c12515377","target":"record","created_at":"2026-07-05T01:54:56Z","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":"32526b6af27a32edac37d351ba77829dc45c5a52e4ad41613b98bc4e666a951c","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2020-11-27T10:00:22Z","title_canon_sha256":"f73447bed4c8a184d82d19d6a9a1dbc754b87b678013eb32a142348c793835fb"},"schema_version":"1.0","source":{"id":"2011.13635","kind":"arxiv","version":1}},"canonical_sha256":"4706d338c6b171b38115fbc3639360bf8e66d3999a03cf63358cb561319a3356","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4706d338c6b171b38115fbc3639360bf8e66d3999a03cf63358cb561319a3356","first_computed_at":"2026-07-05T01:54:56.622290Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:54:56.622290Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TlwnL7MDzQ08z7s4dDEdu1DvkdIeFDG9stHHLO+rF7XULJfa1geT+9WUfbLFMxiv1NPmD0Zgwyi0W3sHQXbYAg==","signature_status":"signed_v1","signed_at":"2026-07-05T01:54:56.622829Z","signed_message":"canonical_sha256_bytes"},"source_id":"2011.13635","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bc3cec73f5f5eeaf71a1cb30736567fa675b896c3c40ee93652b7f7c12515377","sha256:6630c99d629c8cfc69494870553248929cc701a9825aca6a5f6bec1c950ac553"],"state_sha256":"2ffd23405033e1fe575e3a22b718b764f17900e567cf37b7bde986925a1ca971"}