{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:YRXLVXGI6EECCAFTMBTOB74SDR","short_pith_number":"pith:YRXLVXGI","canonical_record":{"source":{"id":"2110.03848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T01:23:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d26bb73519538806e51bc08ea4505ca60a2de777731680fdccf5090e480e4567","abstract_canon_sha256":"c1708d12fb663e27a47e240643ba1e2876809e8e6326d607f804917c98f30c25"},"schema_version":"1.0"},"canonical_sha256":"c46ebadcc8f1082100b36066e0ff921c432c9932e4460d09b401a3013f218c67","source":{"kind":"arxiv","id":"2110.03848","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03848","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03848v1","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03848","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"YRXLVXGI6EEC","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"pith_short_16","alias_value":"YRXLVXGI6EECCAFT","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"pith_short_8","alias_value":"YRXLVXGI","created_at":"2026-07-05T03:20:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:YRXLVXGI6EECCAFTMBTOB74SDR","target":"record","payload":{"canonical_record":{"source":{"id":"2110.03848","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T01:23:34Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"d26bb73519538806e51bc08ea4505ca60a2de777731680fdccf5090e480e4567","abstract_canon_sha256":"c1708d12fb663e27a47e240643ba1e2876809e8e6326d607f804917c98f30c25"},"schema_version":"1.0"},"canonical_sha256":"c46ebadcc8f1082100b36066e0ff921c432c9932e4460d09b401a3013f218c67","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:20:47.881149Z","signature_b64":"Aoo/byxNDWqrQM5h1Dyl36m/5FGLZioiFoBcq5vJHxp4/c+wcdp7G12RnrRHck5n88SF7Wnm8j1BzBolplrPBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c46ebadcc8f1082100b36066e0ff921c432c9932e4460d09b401a3013f218c67","last_reissued_at":"2026-07-05T03:20:47.880757Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:20:47.880757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.03848","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":"2026-07-05T03:20:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/R+90eKRuAmVYkBTmbliv6TnVtnRGj0h9zcgfMajQPZruZBCopXLXOZnvZa4VQgFIlAd6DHiGHOON1rtHx/OBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T09:56:38.295104Z"},"content_sha256":"fccd95780735fa9c06d7ef18cc701ac149c10658a980a8609d5e968349723d9d","schema_version":"1.0","event_id":"sha256:fccd95780735fa9c06d7ef18cc701ac149c10658a980a8609d5e968349723d9d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:YRXLVXGI6EECCAFTMBTOB74SDR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Speeding up Deep Model Training by Sharing Weights and Then Unsharing","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Denny Zhou, Le Hou, Qiang Liu, Shuo Yang, Xiaodan Song","submitted_at":"2021-10-08T01:23:34Z","abstract_excerpt":"We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transformer encoders). Our proposed approach first trains BERT with the weights shared across all the repeated modules till some point. This is for learning the commonly shared component of weights across all repeated layers. We then stop weight sharing and continue training until convergence. We present theoretic insights for training by sharing weights then unsharing with analysis for simplified models. Empirical experime"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03848","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/2110.03848/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":"2026-07-05T03:20:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yPYYD2hyL7cQW9u83IBkxEaHdxzkH+AYrZ3K+R7BjHYRu7Byd1BBrOUit3t3HNNSMKEOax0PZBJtKvS2JLamDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-16T09:56:38.295510Z"},"content_sha256":"f4eb6a222b0069acb0f04b155a360eaa32632341952a3c2237475997902ef2b4","schema_version":"1.0","event_id":"sha256:f4eb6a222b0069acb0f04b155a360eaa32632341952a3c2237475997902ef2b4"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/YRXLVXGI6EECCAFTMBTOB74SDR/bundle.json","state_url":"https://pith.science/pith/YRXLVXGI6EECCAFTMBTOB74SDR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/YRXLVXGI6EECCAFTMBTOB74SDR/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":"2026-07-16T09:56:38Z","links":{"resolver":"https://pith.science/pith/YRXLVXGI6EECCAFTMBTOB74SDR","bundle":"https://pith.science/pith/YRXLVXGI6EECCAFTMBTOB74SDR/bundle.json","state":"https://pith.science/pith/YRXLVXGI6EECCAFTMBTOB74SDR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/YRXLVXGI6EECCAFTMBTOB74SDR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:YRXLVXGI6EECCAFTMBTOB74SDR","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":"c1708d12fb663e27a47e240643ba1e2876809e8e6326d607f804917c98f30c25","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T01:23:34Z","title_canon_sha256":"d26bb73519538806e51bc08ea4505ca60a2de777731680fdccf5090e480e4567"},"schema_version":"1.0","source":{"id":"2110.03848","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.03848","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"arxiv_version","alias_value":"2110.03848v1","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.03848","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"pith_short_12","alias_value":"YRXLVXGI6EEC","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"pith_short_16","alias_value":"YRXLVXGI6EECCAFT","created_at":"2026-07-05T03:20:47Z"},{"alias_kind":"pith_short_8","alias_value":"YRXLVXGI","created_at":"2026-07-05T03:20:47Z"}],"graph_snapshots":[{"event_id":"sha256:f4eb6a222b0069acb0f04b155a360eaa32632341952a3c2237475997902ef2b4","target":"graph","created_at":"2026-07-05T03:20:47Z","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/2110.03848/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We propose a simple and efficient approach for training the BERT model. Our approach exploits the special structure of BERT that contains a stack of repeated modules (i.e., transformer encoders). Our proposed approach first trains BERT with the weights shared across all the repeated modules till some point. This is for learning the commonly shared component of weights across all repeated layers. We then stop weight sharing and continue training until convergence. We present theoretic insights for training by sharing weights then unsharing with analysis for simplified models. Empirical experime","authors_text":"Denny Zhou, Le Hou, Qiang Liu, Shuo Yang, Xiaodan Song","cross_cats":["cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T01:23:34Z","title":"Speeding up Deep Model Training by Sharing Weights and Then Unsharing"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.03848","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:fccd95780735fa9c06d7ef18cc701ac149c10658a980a8609d5e968349723d9d","target":"record","created_at":"2026-07-05T03:20:47Z","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":"c1708d12fb663e27a47e240643ba1e2876809e8e6326d607f804917c98f30c25","cross_cats_sorted":["cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2021-10-08T01:23:34Z","title_canon_sha256":"d26bb73519538806e51bc08ea4505ca60a2de777731680fdccf5090e480e4567"},"schema_version":"1.0","source":{"id":"2110.03848","kind":"arxiv","version":1}},"canonical_sha256":"c46ebadcc8f1082100b36066e0ff921c432c9932e4460d09b401a3013f218c67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c46ebadcc8f1082100b36066e0ff921c432c9932e4460d09b401a3013f218c67","first_computed_at":"2026-07-05T03:20:47.880757Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:20:47.880757Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Aoo/byxNDWqrQM5h1Dyl36m/5FGLZioiFoBcq5vJHxp4/c+wcdp7G12RnrRHck5n88SF7Wnm8j1BzBolplrPBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:20:47.881149Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.03848","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:fccd95780735fa9c06d7ef18cc701ac149c10658a980a8609d5e968349723d9d","sha256:f4eb6a222b0069acb0f04b155a360eaa32632341952a3c2237475997902ef2b4"],"state_sha256":"0c44ca618c1ed2e311077527cedb868b6ffc7447cdbad0552550118013b5e8bd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ZVTYVtRC2hf/HZpA1b2As018dKpsUCEIXJPrrxBSDGhwnqoAjlkHks1/CTycR2xOmqRr23iPHJGBeYCSyw0TBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-16T09:56:38.298118Z","bundle_sha256":"895daa98757e800693f81c36ca1b47a5634de865416e2463d17545729c87f966"}}