{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:RG4FNJ5UJ5OBRYH52Y2JH7XWBQ","short_pith_number":"pith:RG4FNJ5U","schema_version":"1.0","canonical_sha256":"89b856a7b44f5c18e0fdd63493fef60c2c1e63ae788729cf7a3839fe6f027e66","source":{"kind":"arxiv","id":"2110.04725","version":2},"attestation_state":"computed","paper":{"title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chong Shen, Feng Li, Hongli Liu, Hong Zhu, Jiangang Luo, Liang Xu, Rongguo Zhang, Shaohua Wu, Tong Yu, Xuanwei Zhang, Xudong Zhao","submitted_at":"2021-10-10T07:40:22Z","abstract_excerpt":"Recent work like GPT-3 has demonstrated excellent performance of Zero-Shot and Few-Shot learning on many natural language processing (NLP) tasks by scaling up model size, dataset size and the amount of computation. However, training a model like GPT-3 requires huge amount of computational resources which makes it challengeable to researchers. In this work, we propose a method that incorporates large-scale distributed training performance into model architecture design. With this method, Yuan 1.0, the current largest singleton language model with 245B parameters, achieves excellent performance "},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2110.04725","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-10T07:40:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"e59afad2edd682dd0e8d2df53014f7495a43909b49aca08821bb2c68b85af62d","abstract_canon_sha256":"fd16de02047ec7f85489e9e0bdf1e40fe81db8d6b94f70984fd1bb8551c6b96d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:03.168159Z","signature_b64":"jZkXtPJl7Z0YC7NIpUHMSOQ793Z0jyA9SP7tSilHd3GV4b9TYzz0vRayZXuxzxn8i8dgoBpkyhj9yzgO1JnWDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"89b856a7b44f5c18e0fdd63493fef60c2c1e63ae788729cf7a3839fe6f027e66","last_reissued_at":"2026-07-05T03:22:03.167666Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:03.167666Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Yuan 1.0: Large-Scale Pre-trained Language Model in Zero-Shot and Few-Shot Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chong Shen, Feng Li, Hongli Liu, Hong Zhu, Jiangang Luo, Liang Xu, Rongguo Zhang, Shaohua Wu, Tong Yu, Xuanwei Zhang, Xudong Zhao","submitted_at":"2021-10-10T07:40:22Z","abstract_excerpt":"Recent work like GPT-3 has demonstrated excellent performance of Zero-Shot and Few-Shot learning on many natural language processing (NLP) tasks by scaling up model size, dataset size and the amount of computation. However, training a model like GPT-3 requires huge amount of computational resources which makes it challengeable to researchers. In this work, we propose a method that incorporates large-scale distributed training performance into model architecture design. With this method, Yuan 1.0, the current largest singleton language model with 245B parameters, achieves excellent performance "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.04725","kind":"arxiv","version":2},"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/2110.04725/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2110.04725","created_at":"2026-07-05T03:22:03.167732+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.04725v2","created_at":"2026-07-05T03:22:03.167732+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.04725","created_at":"2026-07-05T03:22:03.167732+00:00"},{"alias_kind":"pith_short_12","alias_value":"RG4FNJ5UJ5OB","created_at":"2026-07-05T03:22:03.167732+00:00"},{"alias_kind":"pith_short_16","alias_value":"RG4FNJ5UJ5OBRYH5","created_at":"2026-07-05T03:22:03.167732+00:00"},{"alias_kind":"pith_short_8","alias_value":"RG4FNJ5U","created_at":"2026-07-05T03:22:03.167732+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":5,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2201.11990","citing_title":"Using DeepSpeed and Megatron to Train Megatron-Turing NLG 530B, A Large-Scale Generative Language Model","ref_index":74,"is_internal_anchor":false},{"citing_arxiv_id":"2307.06435","citing_title":"A Comprehensive Overview of Large Language Models","ref_index":115,"is_internal_anchor":false},{"citing_arxiv_id":"2301.12652","citing_title":"REPLUG: Retrieval-Augmented Black-Box Language Models","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2311.16867","citing_title":"The Falcon Series of Open Language Models","ref_index":80,"is_internal_anchor":false},{"citing_arxiv_id":"2303.18223","citing_title":"A Survey of Large Language Models","ref_index":111,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ","json":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ.json","graph_json":"https://pith.science/api/pith-number/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/graph.json","events_json":"https://pith.science/api/pith-number/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/events.json","paper":"https://pith.science/paper/RG4FNJ5U"},"agent_actions":{"view_html":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ","download_json":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ.json","view_paper":"https://pith.science/paper/RG4FNJ5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.04725&json=true","fetch_graph":"https://pith.science/api/pith-number/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/graph.json","fetch_events":"https://pith.science/api/pith-number/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/action/storage_attestation","attest_author":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/action/author_attestation","sign_citation":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/action/citation_signature","submit_replication":"https://pith.science/pith/RG4FNJ5UJ5OBRYH52Y2JH7XWBQ/action/replication_record"}},"created_at":"2026-07-05T03:22:03.167732+00:00","updated_at":"2026-07-05T03:22:03.167732+00:00"}