{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6BZJIS5CDI6NOJCA23AGAX7YAJ","short_pith_number":"pith:6BZJIS5C","schema_version":"1.0","canonical_sha256":"f072944ba21a3cd72440d6c0605ff80254bae0ae22152302b05229535442f649","source":{"kind":"arxiv","id":"2404.02893","version":1},"attestation_state":"computed","paper":{"title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aohan Zeng, Jie Tang, Wenyi Zhao, Xiaohan Zhang, Xiao Liu, Xinghan Liu, Yifan Xu, Yueyan Li, Yuxiao Dong, Zhengxiao Du, Zhenyu Hou, Zihan Wang","submitted_at":"2024-04-03T17:51:18Z","abstract_excerpt":"Large language models (LLMs) have shown excellent mastering of human language, but still struggle in real-world applications that require mathematical problem-solving. While many strategies and datasets to enhance LLMs' mathematics are developed, it remains a challenge to simultaneously maintain and improve both language and mathematical capabilities in deployed LLM systems.In this work, we tailor the Self-Critique pipeline, which addresses the challenge in the feedback learning stage of LLM alignment. We first train a general Math-Critique model from the LLM itself to provide feedback signals"},"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":"2404.02893","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T17:51:18Z","cross_cats_sorted":[],"title_canon_sha256":"73d4f46cc1701a0179e337d34fe7884e32a4d9334d92494de989835fff330660","abstract_canon_sha256":"b099df05626889333bcefaf58967e7039c23075ff125a66f14f1a102af973081"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:04:02.484181Z","signature_b64":"z0sumlY/wyWVOLPsse7/ERoZGqT71cPb/pEY7JAsX9MpfBPlbSRANpnJ0qvykiX4Ier51gkrcfZz7NUXSuW0Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f072944ba21a3cd72440d6c0605ff80254bae0ae22152302b05229535442f649","last_reissued_at":"2026-07-05T08:04:02.483759Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:04:02.483759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Aohan Zeng, Jie Tang, Wenyi Zhao, Xiaohan Zhang, Xiao Liu, Xinghan Liu, Yifan Xu, Yueyan Li, Yuxiao Dong, Zhengxiao Du, Zhenyu Hou, Zihan Wang","submitted_at":"2024-04-03T17:51:18Z","abstract_excerpt":"Large language models (LLMs) have shown excellent mastering of human language, but still struggle in real-world applications that require mathematical problem-solving. While many strategies and datasets to enhance LLMs' mathematics are developed, it remains a challenge to simultaneously maintain and improve both language and mathematical capabilities in deployed LLM systems.In this work, we tailor the Self-Critique pipeline, which addresses the challenge in the feedback learning stage of LLM alignment. We first train a general Math-Critique model from the LLM itself to provide feedback signals"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02893","kind":"arxiv","version":1},"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/2404.02893/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":"2404.02893","created_at":"2026-07-05T08:04:02.483814+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.02893v1","created_at":"2026-07-05T08:04:02.483814+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02893","created_at":"2026-07-05T08:04:02.483814+00:00"},{"alias_kind":"pith_short_12","alias_value":"6BZJIS5CDI6N","created_at":"2026-07-05T08:04:02.483814+00:00"},{"alias_kind":"pith_short_16","alias_value":"6BZJIS5CDI6NOJCA","created_at":"2026-07-05T08:04:02.483814+00:00"},{"alias_kind":"pith_short_8","alias_value":"6BZJIS5C","created_at":"2026-07-05T08:04:02.483814+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2502.02871","citing_title":"Position: Multimodal Large Language Models Can Significantly Advance Scientific Reasoning","ref_index":219,"is_internal_anchor":false},{"citing_arxiv_id":"2406.18629","citing_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","ref_index":29,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ","json":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ.json","graph_json":"https://pith.science/api/pith-number/6BZJIS5CDI6NOJCA23AGAX7YAJ/graph.json","events_json":"https://pith.science/api/pith-number/6BZJIS5CDI6NOJCA23AGAX7YAJ/events.json","paper":"https://pith.science/paper/6BZJIS5C"},"agent_actions":{"view_html":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ","download_json":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ.json","view_paper":"https://pith.science/paper/6BZJIS5C","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.02893&json=true","fetch_graph":"https://pith.science/api/pith-number/6BZJIS5CDI6NOJCA23AGAX7YAJ/graph.json","fetch_events":"https://pith.science/api/pith-number/6BZJIS5CDI6NOJCA23AGAX7YAJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ/action/storage_attestation","attest_author":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ/action/author_attestation","sign_citation":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ/action/citation_signature","submit_replication":"https://pith.science/pith/6BZJIS5CDI6NOJCA23AGAX7YAJ/action/replication_record"}},"created_at":"2026-07-05T08:04:02.483814+00:00","updated_at":"2026-07-05T08:04:02.483814+00:00"}