{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:6WUJY762Y3DH24H7I4AIZ64PUQ","short_pith_number":"pith:6WUJY762","canonical_record":{"source":{"id":"2106.10715","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-20T15:43:54Z","cross_cats_sorted":[],"title_canon_sha256":"d1b611ef2cb5189b3d38d18be254d5e98ecb4a160d9f4a77aaaf0ba6e907acb9","abstract_canon_sha256":"8b3b6fd8bb0ddba6e7887b8eba63d340a49fe41c83cb82b58ab50e39ec184d68"},"schema_version":"1.0"},"canonical_sha256":"f5a89c7fdac6c67d70ff47008cfb8fa4028c15c9d49565d122444452ef05814f","source":{"kind":"arxiv","id":"2106.10715","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10715","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10715v3","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10715","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"pith_short_12","alias_value":"6WUJY762Y3DH","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"pith_short_16","alias_value":"6WUJY762Y3DH24H7","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"pith_short_8","alias_value":"6WUJY762","created_at":"2026-07-05T02:52:03Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:6WUJY762Y3DH24H7I4AIZ64PUQ","target":"record","payload":{"canonical_record":{"source":{"id":"2106.10715","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-20T15:43:54Z","cross_cats_sorted":[],"title_canon_sha256":"d1b611ef2cb5189b3d38d18be254d5e98ecb4a160d9f4a77aaaf0ba6e907acb9","abstract_canon_sha256":"8b3b6fd8bb0ddba6e7887b8eba63d340a49fe41c83cb82b58ab50e39ec184d68"},"schema_version":"1.0"},"canonical_sha256":"f5a89c7fdac6c67d70ff47008cfb8fa4028c15c9d49565d122444452ef05814f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:52:03.513194Z","signature_b64":"cRjmRt8mj8JOZT1C1tqfwRkdQsLfnT7hAZkxC4Zog/x3WoZMNou8lApGWK5ik7eAmPeK7DpHDKwXCu99MMWQCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f5a89c7fdac6c67d70ff47008cfb8fa4028c15c9d49565d122444452ef05814f","last_reissued_at":"2026-07-05T02:52:03.512720Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:52:03.512720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2106.10715","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":"2026-07-05T02:52:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uUbPLjgHFAbeCMbKBpDgw+fCoHY34IBrr/G/8qEyHnQGnhH6Da5J2iv98G7pkjyrwrAUNBXDeWqJgNfLjv61AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:02:39.612224Z"},"content_sha256":"d5ba0841a52f257dad97c0d766910bd33b8bc78a6d8bc13754602aca6b9144b0","schema_version":"1.0","event_id":"sha256:d5ba0841a52f257dad97c0d766910bd33b8bc78a6d8bc13754602aca6b9144b0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:6WUJY762Y3DH24H7I4AIZ64PUQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chaojun Xiao, Fanchao Qi, Guoyang Zeng, Jian Guan, Maosong Sun, Minlie Huang, Pei Ke, Shengqi Chen, Wentao Han, Xiaoyan Zhu, Xu Han, Yang Liu, Yanzheng Cai, Yuan Yao, Yuxian Gu, Zhenbo Sun, Zhengyan Zhang, Zhixing Tan, Zhiyuan Liu","submitted_at":"2021-06-20T15:43:54Z","abstract_excerpt":"In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference. (1) We introduce knowledge inheritance to accelerate the pre-training process by exploiting existing PLMs instead of training models from scratch. (2) We explore the best practice of prompt tuning with large-scale PLMs. Compared with conventional fine-tun"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10715","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/2106.10715/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":"2026-07-05T02:52:03Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"uv+BsIlPtxKZCjapQoxd0WN+AtTHxQKspQUA2yE8XRPETOYykZCwY9dJOaBdhahwY/CwTfmh10L0eVdgYBmyAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T18:02:39.612774Z"},"content_sha256":"b59bc29aba34f6ed6cf89f7b6e62577ddf0923612bd7bcb22f88ef67a3d24dd5","schema_version":"1.0","event_id":"sha256:b59bc29aba34f6ed6cf89f7b6e62577ddf0923612bd7bcb22f88ef67a3d24dd5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6WUJY762Y3DH24H7I4AIZ64PUQ/bundle.json","state_url":"https://pith.science/pith/6WUJY762Y3DH24H7I4AIZ64PUQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6WUJY762Y3DH24H7I4AIZ64PUQ/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":"2026-08-18T18:02:39Z","links":{"resolver":"https://pith.science/pith/6WUJY762Y3DH24H7I4AIZ64PUQ","bundle":"https://pith.science/pith/6WUJY762Y3DH24H7I4AIZ64PUQ/bundle.json","state":"https://pith.science/pith/6WUJY762Y3DH24H7I4AIZ64PUQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6WUJY762Y3DH24H7I4AIZ64PUQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:6WUJY762Y3DH24H7I4AIZ64PUQ","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":"8b3b6fd8bb0ddba6e7887b8eba63d340a49fe41c83cb82b58ab50e39ec184d68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-20T15:43:54Z","title_canon_sha256":"d1b611ef2cb5189b3d38d18be254d5e98ecb4a160d9f4a77aaaf0ba6e907acb9"},"schema_version":"1.0","source":{"id":"2106.10715","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2106.10715","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"arxiv_version","alias_value":"2106.10715v3","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.10715","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"pith_short_12","alias_value":"6WUJY762Y3DH","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"pith_short_16","alias_value":"6WUJY762Y3DH24H7","created_at":"2026-07-05T02:52:03Z"},{"alias_kind":"pith_short_8","alias_value":"6WUJY762","created_at":"2026-07-05T02:52:03Z"}],"graph_snapshots":[{"event_id":"sha256:b59bc29aba34f6ed6cf89f7b6e62577ddf0923612bd7bcb22f88ef67a3d24dd5","target":"graph","created_at":"2026-07-05T02:52:03Z","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/2106.10715/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In recent years, the size of pre-trained language models (PLMs) has grown by leaps and bounds. However, efficiency issues of these large-scale PLMs limit their utilization in real-world scenarios. We present a suite of cost-effective techniques for the use of PLMs to deal with the efficiency issues of pre-training, fine-tuning, and inference. (1) We introduce knowledge inheritance to accelerate the pre-training process by exploiting existing PLMs instead of training models from scratch. (2) We explore the best practice of prompt tuning with large-scale PLMs. Compared with conventional fine-tun","authors_text":"Chaojun Xiao, Fanchao Qi, Guoyang Zeng, Jian Guan, Maosong Sun, Minlie Huang, Pei Ke, Shengqi Chen, Wentao Han, Xiaoyan Zhu, Xu Han, Yang Liu, Yanzheng Cai, Yuan Yao, Yuxian Gu, Zhenbo Sun, Zhengyan Zhang, Zhixing Tan, Zhiyuan Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-20T15:43:54Z","title":"CPM-2: Large-scale Cost-effective Pre-trained Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.10715","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:d5ba0841a52f257dad97c0d766910bd33b8bc78a6d8bc13754602aca6b9144b0","target":"record","created_at":"2026-07-05T02:52:03Z","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":"8b3b6fd8bb0ddba6e7887b8eba63d340a49fe41c83cb82b58ab50e39ec184d68","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-06-20T15:43:54Z","title_canon_sha256":"d1b611ef2cb5189b3d38d18be254d5e98ecb4a160d9f4a77aaaf0ba6e907acb9"},"schema_version":"1.0","source":{"id":"2106.10715","kind":"arxiv","version":3}},"canonical_sha256":"f5a89c7fdac6c67d70ff47008cfb8fa4028c15c9d49565d122444452ef05814f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f5a89c7fdac6c67d70ff47008cfb8fa4028c15c9d49565d122444452ef05814f","first_computed_at":"2026-07-05T02:52:03.512720Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:52:03.512720Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"cRjmRt8mj8JOZT1C1tqfwRkdQsLfnT7hAZkxC4Zog/x3WoZMNou8lApGWK5ik7eAmPeK7DpHDKwXCu99MMWQCA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:52:03.513194Z","signed_message":"canonical_sha256_bytes"},"source_id":"2106.10715","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d5ba0841a52f257dad97c0d766910bd33b8bc78a6d8bc13754602aca6b9144b0","sha256:b59bc29aba34f6ed6cf89f7b6e62577ddf0923612bd7bcb22f88ef67a3d24dd5"],"state_sha256":"db6a1bc9983d290d0086e31552009c722467289ce57f484a682487c2d0da1830"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"K5h0/mE5JUGUhcFGfmySHPIkv0Mj7KilL2VsH3qLTJt8cNe3MDst56HnK+2oquwXk16sorCZvosYCB6lAyZmBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T18:02:39.617010Z","bundle_sha256":"6c0d87d2e58faff645ebc0994e4ba1aa665b6d1ce15cdf6419bf27f399e4d0d7"}}