{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:XTTYRYNFHUY72RHSJEUX2WU7A4","short_pith_number":"pith:XTTYRYNF","schema_version":"1.0","canonical_sha256":"bce788e1a53d31fd44f249297d5a9f070ca13ffed0e9d48b3d45ac68c1608ecf","source":{"kind":"arxiv","id":"2310.07488","version":2},"attestation_state":"computed","paper":{"title":"KwaiYiiMath: Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Chen, Chao Liao, Chengru Song, Di Zhang, Fuzheng Zhang, Jiayi Fu, Junchen Wan, Kun Gai, Lei Lin, Pengli Liu, Shengnan Zhang, Xiaoyang Gao, Xucheng Ye, Xue Zheng, Yan Li, Yiqiao Liao, Yuliang Liu, Zhengzong Chen, Zhirui Yang, Zhongyuan Wang, Zijia Lin","submitted_at":"2023-10-11T13:35:05Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have demonstrated remarkable abilities in handling a variety of natural language processing (NLP) downstream tasks, even on mathematical tasks requiring multi-step reasoning. In this report, we introduce the KwaiYiiMath which enhances the mathematical reasoning abilities of KwaiYiiBase1, by applying Supervised Fine-Tuning (SFT) and Reinforced Learning from Human Feedback (RLHF), including on both English and Chinese mathematical tasks. Meanwhile, we also constructed a small-scale Chinese primary school mathematics test set (named KMath), cons"},"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":"2310.07488","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-10-11T13:35:05Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"36337735768fc896a2939057644e1f6c9dcc9d8076a500a60a8cc3611e2bac8a","abstract_canon_sha256":"22aba974b3cd4fbfbbbf24af89ea5130a12d1164904f3d9992ebe8cd03ff28bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:02:33.323918Z","signature_b64":"kDTXSUWw3XSM4DhPyIg3dMokTZji43og+ri7jdkPgK0W9+vS50srpCnzp8g0N1+uKAfa/PsTGtPljVxrNd8LDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bce788e1a53d31fd44f249297d5a9f070ca13ffed0e9d48b3d45ac68c1608ecf","last_reissued_at":"2026-07-05T07:02:33.323484Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:02:33.323484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KwaiYiiMath: Technical Report","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bin Chen, Chao Liao, Chengru Song, Di Zhang, Fuzheng Zhang, Jiayi Fu, Junchen Wan, Kun Gai, Lei Lin, Pengli Liu, Shengnan Zhang, Xiaoyang Gao, Xucheng Ye, Xue Zheng, Yan Li, Yiqiao Liao, Yuliang Liu, Zhengzong Chen, Zhirui Yang, Zhongyuan Wang, Zijia Lin","submitted_at":"2023-10-11T13:35:05Z","abstract_excerpt":"Recent advancements in large language models (LLMs) have demonstrated remarkable abilities in handling a variety of natural language processing (NLP) downstream tasks, even on mathematical tasks requiring multi-step reasoning. In this report, we introduce the KwaiYiiMath which enhances the mathematical reasoning abilities of KwaiYiiBase1, by applying Supervised Fine-Tuning (SFT) and Reinforced Learning from Human Feedback (RLHF), including on both English and Chinese mathematical tasks. Meanwhile, we also constructed a small-scale Chinese primary school mathematics test set (named KMath), cons"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2310.07488","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/2310.07488/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":"2310.07488","created_at":"2026-07-05T07:02:33.323552+00:00"},{"alias_kind":"arxiv_version","alias_value":"2310.07488v2","created_at":"2026-07-05T07:02:33.323552+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2310.07488","created_at":"2026-07-05T07:02:33.323552+00:00"},{"alias_kind":"pith_short_12","alias_value":"XTTYRYNFHUY7","created_at":"2026-07-05T07:02:33.323552+00:00"},{"alias_kind":"pith_short_16","alias_value":"XTTYRYNFHUY72RHS","created_at":"2026-07-05T07:02:33.323552+00:00"},{"alias_kind":"pith_short_8","alias_value":"XTTYRYNF","created_at":"2026-07-05T07:02:33.323552+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":47,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4","json":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4.json","graph_json":"https://pith.science/api/pith-number/XTTYRYNFHUY72RHSJEUX2WU7A4/graph.json","events_json":"https://pith.science/api/pith-number/XTTYRYNFHUY72RHSJEUX2WU7A4/events.json","paper":"https://pith.science/paper/XTTYRYNF"},"agent_actions":{"view_html":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4","download_json":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4.json","view_paper":"https://pith.science/paper/XTTYRYNF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2310.07488&json=true","fetch_graph":"https://pith.science/api/pith-number/XTTYRYNFHUY72RHSJEUX2WU7A4/graph.json","fetch_events":"https://pith.science/api/pith-number/XTTYRYNFHUY72RHSJEUX2WU7A4/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4/action/storage_attestation","attest_author":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4/action/author_attestation","sign_citation":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4/action/citation_signature","submit_replication":"https://pith.science/pith/XTTYRYNFHUY72RHSJEUX2WU7A4/action/replication_record"}},"created_at":"2026-07-05T07:02:33.323552+00:00","updated_at":"2026-07-05T07:02:33.323552+00:00"}