{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:GNOMYXPV5F4BCI34VOFBH33BQZ","short_pith_number":"pith:GNOMYXPV","schema_version":"1.0","canonical_sha256":"335ccc5df5e97811237cab8a13ef61866c92d89df95351e037442fb0b8d31e89","source":{"kind":"arxiv","id":"2209.10372","version":5},"attestation_state":"computed","paper":{"title":"WeLM: A Well-Read Pre-trained Language Model for Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Houjin Yu, Hui Su, Jie Zhou, Xiaoyu Shen, Xiao Zhou, Yang Yu, Yuwen Chen, Zilin Zhu","submitted_at":"2022-09-21T14:05:30Z","abstract_excerpt":"Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks. In this work, we present WeLM: a well-read pre-trained language model for Chinese that is able to seamlessly perform different types of tasks with zero or few-shot demonstrations. WeLM is trained with 10B parameters by \"reading\" a curated high-quality corpus covering a wide range of topics. We show that WeLM is equipped with broad knowledge on various domains and languages. On 18 monolingual (Chinese) tasks, WeLM can significantly outpe"},"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":"2209.10372","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-09-21T14:05:30Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"97f1851e7913ba513297681ab532cf563599238aa0e0e3226637d24c3d05b1b0","abstract_canon_sha256":"8d9235411abb9ce786cb8995c25aea0e22b06d9cf49088a00b01897dc86f6b04"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:10:19.707781Z","signature_b64":"2v/b7c7zs982SmOMuCtx+0kSpZpKnCptN9cgEAikADoYXAhOCP8FsH699LyqwSS78orebmS9DQrP3s3VNjGPBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"335ccc5df5e97811237cab8a13ef61866c92d89df95351e037442fb0b8d31e89","last_reissued_at":"2026-07-05T06:10:19.707293Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:10:19.707293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"WeLM: A Well-Read Pre-trained Language Model for Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Houjin Yu, Hui Su, Jie Zhou, Xiaoyu Shen, Xiao Zhou, Yang Yu, Yuwen Chen, Zilin Zhu","submitted_at":"2022-09-21T14:05:30Z","abstract_excerpt":"Large Language Models pre-trained with self-supervised learning have demonstrated impressive zero-shot generalization capabilities on a wide spectrum of tasks. In this work, we present WeLM: a well-read pre-trained language model for Chinese that is able to seamlessly perform different types of tasks with zero or few-shot demonstrations. WeLM is trained with 10B parameters by \"reading\" a curated high-quality corpus covering a wide range of topics. We show that WeLM is equipped with broad knowledge on various domains and languages. On 18 monolingual (Chinese) tasks, WeLM can significantly outpe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2209.10372","kind":"arxiv","version":5},"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/2209.10372/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":"2209.10372","created_at":"2026-07-05T06:10:19.707363+00:00"},{"alias_kind":"arxiv_version","alias_value":"2209.10372v5","created_at":"2026-07-05T06:10:19.707363+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2209.10372","created_at":"2026-07-05T06:10:19.707363+00:00"},{"alias_kind":"pith_short_12","alias_value":"GNOMYXPV5F4B","created_at":"2026-07-05T06:10:19.707363+00:00"},{"alias_kind":"pith_short_16","alias_value":"GNOMYXPV5F4BCI34","created_at":"2026-07-05T06:10:19.707363+00:00"},{"alias_kind":"pith_short_8","alias_value":"GNOMYXPV","created_at":"2026-07-05T06:10:19.707363+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2305.16264","citing_title":"Scaling Data-Constrained Language Models","ref_index":111,"is_internal_anchor":false},{"citing_arxiv_id":"2303.18223","citing_title":"A Survey of Large Language Models","ref_index":119,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ","json":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ.json","graph_json":"https://pith.science/api/pith-number/GNOMYXPV5F4BCI34VOFBH33BQZ/graph.json","events_json":"https://pith.science/api/pith-number/GNOMYXPV5F4BCI34VOFBH33BQZ/events.json","paper":"https://pith.science/paper/GNOMYXPV"},"agent_actions":{"view_html":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ","download_json":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ.json","view_paper":"https://pith.science/paper/GNOMYXPV","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2209.10372&json=true","fetch_graph":"https://pith.science/api/pith-number/GNOMYXPV5F4BCI34VOFBH33BQZ/graph.json","fetch_events":"https://pith.science/api/pith-number/GNOMYXPV5F4BCI34VOFBH33BQZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ/action/storage_attestation","attest_author":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ/action/author_attestation","sign_citation":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ/action/citation_signature","submit_replication":"https://pith.science/pith/GNOMYXPV5F4BCI34VOFBH33BQZ/action/replication_record"}},"created_at":"2026-07-05T06:10:19.707363+00:00","updated_at":"2026-07-05T06:10:19.707363+00:00"}