{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:4OYOAVSFGG5O7C7LMVVHFNXRE3","short_pith_number":"pith:4OYOAVSF","canonical_record":{"source":{"id":"2010.13369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T06:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"30ffca25a6805203e68c8d708c382c79eb8b4867c3e768142ad3b5e1a46acf3a","abstract_canon_sha256":"e22e2a6be24fe95c3a4cc5af4729680421350f8d33df60b4619b789d6dc79c0e"},"schema_version":"1.0"},"canonical_sha256":"e3b0e0564531baef8beb656a72b6f126f6d53ec125aead414a7aa9aaf5024266","source":{"kind":"arxiv","id":"2010.13369","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13369","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13369v1","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13369","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"4OYOAVSFGG5O","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"4OYOAVSFGG5O7C7L","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"4OYOAVSF","created_at":"2026-07-05T01:46:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:4OYOAVSFGG5O7C7LMVVHFNXRE3","target":"record","payload":{"canonical_record":{"source":{"id":"2010.13369","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T06:50:07Z","cross_cats_sorted":[],"title_canon_sha256":"30ffca25a6805203e68c8d708c382c79eb8b4867c3e768142ad3b5e1a46acf3a","abstract_canon_sha256":"e22e2a6be24fe95c3a4cc5af4729680421350f8d33df60b4619b789d6dc79c0e"},"schema_version":"1.0"},"canonical_sha256":"e3b0e0564531baef8beb656a72b6f126f6d53ec125aead414a7aa9aaf5024266","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:46:05.492878Z","signature_b64":"aURSng2v2BtgUgPjKQobHVmTTSmyGc1A9fOLeZf2oAMLNejKbpqU2ylRQEr/d7gI+gvDDyjaXCDucYhEqyaaBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e3b0e0564531baef8beb656a72b6f126f6d53ec125aead414a7aa9aaf5024266","last_reissued_at":"2026-07-05T01:46:05.492335Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:46:05.492335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.13369","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"z19jvctkYV4Dym7mdLR4IIxtows3jFFZap75C2f1pAgPseIxldoRsjza8+Oe1xn1gsiZ4+LxnhZmjencz3CiAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:13:44.928565Z"},"content_sha256":"a26d92d0f0ec09fd173f95f643af9f6e897d2fb960fb55d3a82e5dc97b8807cd","schema_version":"1.0","event_id":"sha256:a26d92d0f0ec09fd173f95f643af9f6e897d2fb960fb55d3a82e5dc97b8807cd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:4OYOAVSFGG5O7C7LMVVHFNXRE3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Minjia Zhang, Yuxiong He","submitted_at":"2020-10-26T06:50:07Z","abstract_excerpt":"Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current methods for accelerating the pre-training either rely on massive parallelism with advanced hardware or are not applicable to language modeling. In this work, we propose a method based on progressive layer dropping that speeds the training of Transformer-based language models, not at the cost of excessive hardware resources but from model architecture change and tr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13369","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/2010.13369/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:46:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fC5qKFUY9YJxf57PUY7qIW4NQ7ZnnS2LCNhlBvtB2CHTfHbgigIxyWWdtqIk/1xxDC9nlUrsZHPFT2jrU9BcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T05:13:44.929061Z"},"content_sha256":"f76db17b1ebfade47dae28cfc5c0b1f84d8f2698e09f5591f618842e93b862a4","schema_version":"1.0","event_id":"sha256:f76db17b1ebfade47dae28cfc5c0b1f84d8f2698e09f5591f618842e93b862a4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/4OYOAVSFGG5O7C7LMVVHFNXRE3/bundle.json","state_url":"https://pith.science/pith/4OYOAVSFGG5O7C7LMVVHFNXRE3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/4OYOAVSFGG5O7C7LMVVHFNXRE3/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-08T05:13:44Z","links":{"resolver":"https://pith.science/pith/4OYOAVSFGG5O7C7LMVVHFNXRE3","bundle":"https://pith.science/pith/4OYOAVSFGG5O7C7LMVVHFNXRE3/bundle.json","state":"https://pith.science/pith/4OYOAVSFGG5O7C7LMVVHFNXRE3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/4OYOAVSFGG5O7C7LMVVHFNXRE3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:4OYOAVSFGG5O7C7LMVVHFNXRE3","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":"e22e2a6be24fe95c3a4cc5af4729680421350f8d33df60b4619b789d6dc79c0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T06:50:07Z","title_canon_sha256":"30ffca25a6805203e68c8d708c382c79eb8b4867c3e768142ad3b5e1a46acf3a"},"schema_version":"1.0","source":{"id":"2010.13369","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.13369","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"arxiv_version","alias_value":"2010.13369v1","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.13369","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"pith_short_12","alias_value":"4OYOAVSFGG5O","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"pith_short_16","alias_value":"4OYOAVSFGG5O7C7L","created_at":"2026-07-05T01:46:05Z"},{"alias_kind":"pith_short_8","alias_value":"4OYOAVSF","created_at":"2026-07-05T01:46:05Z"}],"graph_snapshots":[{"event_id":"sha256:f76db17b1ebfade47dae28cfc5c0b1f84d8f2698e09f5591f618842e93b862a4","target":"graph","created_at":"2026-07-05T01:46:05Z","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/2010.13369/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recently, Transformer-based language models have demonstrated remarkable performance across many NLP domains. However, the unsupervised pre-training step of these models suffers from unbearable overall computational expenses. Current methods for accelerating the pre-training either rely on massive parallelism with advanced hardware or are not applicable to language modeling. In this work, we propose a method based on progressive layer dropping that speeds the training of Transformer-based language models, not at the cost of excessive hardware resources but from model architecture change and tr","authors_text":"Minjia Zhang, Yuxiong He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T06:50:07Z","title":"Accelerating Training of Transformer-Based Language Models with Progressive Layer Dropping"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.13369","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:a26d92d0f0ec09fd173f95f643af9f6e897d2fb960fb55d3a82e5dc97b8807cd","target":"record","created_at":"2026-07-05T01:46:05Z","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":"e22e2a6be24fe95c3a4cc5af4729680421350f8d33df60b4619b789d6dc79c0e","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2020-10-26T06:50:07Z","title_canon_sha256":"30ffca25a6805203e68c8d708c382c79eb8b4867c3e768142ad3b5e1a46acf3a"},"schema_version":"1.0","source":{"id":"2010.13369","kind":"arxiv","version":1}},"canonical_sha256":"e3b0e0564531baef8beb656a72b6f126f6d53ec125aead414a7aa9aaf5024266","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3b0e0564531baef8beb656a72b6f126f6d53ec125aead414a7aa9aaf5024266","first_computed_at":"2026-07-05T01:46:05.492335Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:46:05.492335Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"aURSng2v2BtgUgPjKQobHVmTTSmyGc1A9fOLeZf2oAMLNejKbpqU2ylRQEr/d7gI+gvDDyjaXCDucYhEqyaaBA==","signature_status":"signed_v1","signed_at":"2026-07-05T01:46:05.492878Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.13369","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a26d92d0f0ec09fd173f95f643af9f6e897d2fb960fb55d3a82e5dc97b8807cd","sha256:f76db17b1ebfade47dae28cfc5c0b1f84d8f2698e09f5591f618842e93b862a4"],"state_sha256":"80700e55b825906d26067470c0496e9fca42cea8f0d641d8d37c1f003a1bba24"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0f2jfpyAevXZnpnOL4AJY/5jNyLF1ik3AQteCW9NPvclp1pbQhbCBWErDmCgBL8yO2XDn0+hQmVeT0GsEfkACg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T05:13:44.934026Z","bundle_sha256":"d71f6c5422764721dc65c75ecd03b960e3715ef6823126d16f8903867e5bdc05"}}