{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:OOCVV3S2RKWJOSSBQKNAQTU5M7","short_pith_number":"pith:OOCVV3S2","canonical_record":{"source":{"id":"2010.12562","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:44:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"905b0faf1dd2cc68ee3ff0ff94cc1e169f0f34db8fc9e9dcee2db7ec100ed694","abstract_canon_sha256":"26268fc6d5bce128f54bf9121aef69c3bb190816229a0d3988f812b7b224e71b"},"schema_version":"1.0"},"canonical_sha256":"73855aee5a8aac974a41829a084e9d67ec93c3d10c975f722b96aa54c88a1d9f","source":{"kind":"arxiv","id":"2010.12562","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12562","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12562v3","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12562","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"pith_short_12","alias_value":"OOCVV3S2RKWJ","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"pith_short_16","alias_value":"OOCVV3S2RKWJOSSB","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"pith_short_8","alias_value":"OOCVV3S2","created_at":"2026-07-05T02:56:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:OOCVV3S2RKWJOSSBQKNAQTU5M7","target":"record","payload":{"canonical_record":{"source":{"id":"2010.12562","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:44:59Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"905b0faf1dd2cc68ee3ff0ff94cc1e169f0f34db8fc9e9dcee2db7ec100ed694","abstract_canon_sha256":"26268fc6d5bce128f54bf9121aef69c3bb190816229a0d3988f812b7b224e71b"},"schema_version":"1.0"},"canonical_sha256":"73855aee5a8aac974a41829a084e9d67ec93c3d10c975f722b96aa54c88a1d9f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:56:37.204658Z","signature_b64":"nbTZzVQxCvU6g+JQnSxy7cnkaYbL7v5HOuDFgWWVQfXTU6ISq9CY70YfkaShEQlV8myaSMFtKOl6xBcI+IwNCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"73855aee5a8aac974a41829a084e9d67ec93c3d10c975f722b96aa54c88a1d9f","last_reissued_at":"2026-07-05T02:56:37.204243Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:56:37.204243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2010.12562","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:56:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CK0oH5NsLcF/7Jce3+Q3NW2dS8+CsxvGiZZwqxtN2TgfQ3UYUrecnLwL8wIooeWq+pZjHfYg3U/Un4hDzyB0BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:42:27.626730Z"},"content_sha256":"cd6de11fa4fb6c423743242e0f8425b91d237d243e658ec75defed183f8f7333","schema_version":"1.0","event_id":"sha256:cd6de11fa4fb6c423743242e0f8425b91d237d243e658ec75defed183f8f7333"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:OOCVV3S2RKWJOSSBQKNAQTU5M7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"On the Transformer Growth for Progressive BERT Training","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Chen Chen, Hongkun Yu, Jiawei Han, Jing Li, Liyuan Liu, Xiaotao Gu","submitted_at":"2020-10-23T17:44:59Z","abstract_excerpt":"Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational complexity. Our objective is to advance the understanding of Transformer growth and discover principles that guide progressive training. First, we find that similar to network architecture search, Transformer growth also favors compound scaling. Specifically, while existing methods only conduct network growth in a single dimension, we observe that it is benefi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12562","kind":"arxiv","version":3},"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/2010.12562/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":"2026-07-05T02:56:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Tf7mGwx7BDAoyoY2QAwjrGRRlYPkQorIsKyPe3pxxJ0zdwc+UM6vJk4M7bVgwjdE9VGItefY0bchdXe3eIG3AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T13:42:27.627299Z"},"content_sha256":"3b4527443ba985ba8358e2d29ef6aabaf421cf00a54e89b68e425300a0be9837","schema_version":"1.0","event_id":"sha256:3b4527443ba985ba8358e2d29ef6aabaf421cf00a54e89b68e425300a0be9837"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OOCVV3S2RKWJOSSBQKNAQTU5M7/bundle.json","state_url":"https://pith.science/pith/OOCVV3S2RKWJOSSBQKNAQTU5M7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OOCVV3S2RKWJOSSBQKNAQTU5M7/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":"2026-08-04T13:42:27Z","links":{"resolver":"https://pith.science/pith/OOCVV3S2RKWJOSSBQKNAQTU5M7","bundle":"https://pith.science/pith/OOCVV3S2RKWJOSSBQKNAQTU5M7/bundle.json","state":"https://pith.science/pith/OOCVV3S2RKWJOSSBQKNAQTU5M7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OOCVV3S2RKWJOSSBQKNAQTU5M7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OOCVV3S2RKWJOSSBQKNAQTU5M7","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":"26268fc6d5bce128f54bf9121aef69c3bb190816229a0d3988f812b7b224e71b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:44:59Z","title_canon_sha256":"905b0faf1dd2cc68ee3ff0ff94cc1e169f0f34db8fc9e9dcee2db7ec100ed694"},"schema_version":"1.0","source":{"id":"2010.12562","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12562","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12562v3","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12562","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"pith_short_12","alias_value":"OOCVV3S2RKWJ","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"pith_short_16","alias_value":"OOCVV3S2RKWJOSSB","created_at":"2026-07-05T02:56:37Z"},{"alias_kind":"pith_short_8","alias_value":"OOCVV3S2","created_at":"2026-07-05T02:56:37Z"}],"graph_snapshots":[{"event_id":"sha256:3b4527443ba985ba8358e2d29ef6aabaf421cf00a54e89b68e425300a0be9837","target":"graph","created_at":"2026-07-05T02:56:37Z","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/2010.12562/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Due to the excessive cost of large-scale language model pre-training, considerable efforts have been made to train BERT progressively -- start from an inferior but low-cost model and gradually grow the model to increase the computational complexity. Our objective is to advance the understanding of Transformer growth and discover principles that guide progressive training. First, we find that similar to network architecture search, Transformer growth also favors compound scaling. Specifically, while existing methods only conduct network growth in a single dimension, we observe that it is benefi","authors_text":"Chen Chen, Hongkun Yu, Jiawei Han, Jing Li, Liyuan Liu, Xiaotao Gu","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:44:59Z","title":"On the Transformer Growth for Progressive BERT Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12562","kind":"arxiv","version":3},"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:cd6de11fa4fb6c423743242e0f8425b91d237d243e658ec75defed183f8f7333","target":"record","created_at":"2026-07-05T02:56:37Z","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":"26268fc6d5bce128f54bf9121aef69c3bb190816229a0d3988f812b7b224e71b","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-23T17:44:59Z","title_canon_sha256":"905b0faf1dd2cc68ee3ff0ff94cc1e169f0f34db8fc9e9dcee2db7ec100ed694"},"schema_version":"1.0","source":{"id":"2010.12562","kind":"arxiv","version":3}},"canonical_sha256":"73855aee5a8aac974a41829a084e9d67ec93c3d10c975f722b96aa54c88a1d9f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"73855aee5a8aac974a41829a084e9d67ec93c3d10c975f722b96aa54c88a1d9f","first_computed_at":"2026-07-05T02:56:37.204243Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:56:37.204243Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nbTZzVQxCvU6g+JQnSxy7cnkaYbL7v5HOuDFgWWVQfXTU6ISq9CY70YfkaShEQlV8myaSMFtKOl6xBcI+IwNCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:56:37.204658Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12562","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cd6de11fa4fb6c423743242e0f8425b91d237d243e658ec75defed183f8f7333","sha256:3b4527443ba985ba8358e2d29ef6aabaf421cf00a54e89b68e425300a0be9837"],"state_sha256":"00b8b278db5825fef25dc07035b537f05f5a32da37474f985eb5584f56754f18"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjMkE/tb17lahlbdZxGZBue7qSJek+9eUmB57WDhY072pT7s9AKWDaLBbqyVVDa8IQbMuSr12T5h8T3BQQH7CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T13:42:27.632549Z","bundle_sha256":"e36d86553f32760b66dfe4f176ee660f1be5ae54fc720e3335d0afbfbc14717f"}}