{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:MRFNKZDLFCGVS34QPYAKSWONKJ","short_pith_number":"pith:MRFNKZDL","schema_version":"1.0","canonical_sha256":"644ad5646b288d596f907e00a959cd52625362fbcba8db390900ca6a6796acf0","source":{"kind":"arxiv","id":"2110.06696","version":2},"attestation_state":"computed","paper":{"title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanqing Zhang, Jingyun Hua, Keming Chen, Ming Zhou, Yuhang Guo, Yulong Wang, Zhuosheng Zhang","submitted_at":"2021-10-13T13:14:32Z","abstract_excerpt":"Although pre-trained models (PLMs) have achieved remarkable improvements in a wide range of NLP tasks, they are expensive in terms of time and resources. This calls for the study of training more efficient models with less computation but still ensures impressive performance. Instead of pursuing a larger scale, we are committed to developing lightweight yet more powerful models trained with equal or less computation and friendly to rapid deployment. This technical report releases our pre-trained model called Mengzi, which stands for a family of discriminative, generative, domain-specific, and "},"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":"2110.06696","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-10-13T13:14:32Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d7e665a913462017d69584e070b49c347350aaf6f82759f8f7c230495e1fc14d","abstract_canon_sha256":"89d28b7514b2b356e2b49caa50bd5c6ada709013fe8e99dcf3ff28aa9282ba79"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:22:37.722691Z","signature_b64":"spCw/WIFfb0cALxCkvfG/OYj6Oj7JqdWskp1gZgoJiBDQ2qIFYUvFhL5e2SM0D+qHuh7ECMuXLXGXC+PmsEaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"644ad5646b288d596f907e00a959cd52625362fbcba8db390900ca6a6796acf0","last_reissued_at":"2026-07-05T03:22:37.722190Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:22:37.722190Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Mengzi: Towards Lightweight yet Ingenious Pre-trained Models for Chinese","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Hanqing Zhang, Jingyun Hua, Keming Chen, Ming Zhou, Yuhang Guo, Yulong Wang, Zhuosheng Zhang","submitted_at":"2021-10-13T13:14:32Z","abstract_excerpt":"Although pre-trained models (PLMs) have achieved remarkable improvements in a wide range of NLP tasks, they are expensive in terms of time and resources. This calls for the study of training more efficient models with less computation but still ensures impressive performance. Instead of pursuing a larger scale, we are committed to developing lightweight yet more powerful models trained with equal or less computation and friendly to rapid deployment. This technical report releases our pre-trained model called Mengzi, which stands for a family of discriminative, generative, domain-specific, and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.06696","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/2110.06696/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":"2110.06696","created_at":"2026-07-05T03:22:37.722251+00:00"},{"alias_kind":"arxiv_version","alias_value":"2110.06696v2","created_at":"2026-07-05T03:22:37.722251+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.06696","created_at":"2026-07-05T03:22:37.722251+00:00"},{"alias_kind":"pith_short_12","alias_value":"MRFNKZDLFCGV","created_at":"2026-07-05T03:22:37.722251+00:00"},{"alias_kind":"pith_short_16","alias_value":"MRFNKZDLFCGVS34Q","created_at":"2026-07-05T03:22:37.722251+00:00"},{"alias_kind":"pith_short_8","alias_value":"MRFNKZDL","created_at":"2026-07-05T03:22:37.722251+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2406.12009","citing_title":"FinTruthQA: A Benchmark for AI-Driven Financial Disclosure Quality Assessment in Investor -- Firm Interactions","ref_index":37,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ","json":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ.json","graph_json":"https://pith.science/api/pith-number/MRFNKZDLFCGVS34QPYAKSWONKJ/graph.json","events_json":"https://pith.science/api/pith-number/MRFNKZDLFCGVS34QPYAKSWONKJ/events.json","paper":"https://pith.science/paper/MRFNKZDL"},"agent_actions":{"view_html":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ","download_json":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ.json","view_paper":"https://pith.science/paper/MRFNKZDL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2110.06696&json=true","fetch_graph":"https://pith.science/api/pith-number/MRFNKZDLFCGVS34QPYAKSWONKJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MRFNKZDLFCGVS34QPYAKSWONKJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ/action/storage_attestation","attest_author":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ/action/author_attestation","sign_citation":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ/action/citation_signature","submit_replication":"https://pith.science/pith/MRFNKZDLFCGVS34QPYAKSWONKJ/action/replication_record"}},"created_at":"2026-07-05T03:22:37.722251+00:00","updated_at":"2026-07-05T03:22:37.722251+00:00"}