{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:6BZJIS5CDI6NOJCA23AGAX7YAJ","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"b099df05626889333bcefaf58967e7039c23075ff125a66f14f1a102af973081","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T17:51:18Z","title_canon_sha256":"73d4f46cc1701a0179e337d34fe7884e32a4d9334d92494de989835fff330660"},"schema_version":"1.0","source":{"id":"2404.02893","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.02893","created_at":"2026-07-05T08:04:02Z"},{"alias_kind":"arxiv_version","alias_value":"2404.02893v1","created_at":"2026-07-05T08:04:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.02893","created_at":"2026-07-05T08:04:02Z"},{"alias_kind":"pith_short_12","alias_value":"6BZJIS5CDI6N","created_at":"2026-07-05T08:04:02Z"},{"alias_kind":"pith_short_16","alias_value":"6BZJIS5CDI6NOJCA","created_at":"2026-07-05T08:04:02Z"},{"alias_kind":"pith_short_8","alias_value":"6BZJIS5C","created_at":"2026-07-05T08:04:02Z"}],"graph_snapshots":[{"event_id":"sha256:7932bb9cb2a2d4b4094dff217e9f1245d78100ee7a2ffed8cf56e58940e14d43","target":"graph","created_at":"2026-07-05T08:04:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2404.02893/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","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","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T17:51:18Z","title":"ChatGLM-Math: Improving Math Problem-Solving in Large Language Models with a Self-Critique Pipeline"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.02893","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:2d1d5386c4fa9298da298491ebde8367ff30e36bf7d8c8a2d83938ce1aefdd4c","target":"record","created_at":"2026-07-05T08:04:02Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"b099df05626889333bcefaf58967e7039c23075ff125a66f14f1a102af973081","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-03T17:51:18Z","title_canon_sha256":"73d4f46cc1701a0179e337d34fe7884e32a4d9334d92494de989835fff330660"},"schema_version":"1.0","source":{"id":"2404.02893","kind":"arxiv","version":1}},"canonical_sha256":"f072944ba21a3cd72440d6c0605ff80254bae0ae22152302b05229535442f649","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f072944ba21a3cd72440d6c0605ff80254bae0ae22152302b05229535442f649","first_computed_at":"2026-07-05T08:04:02.483759Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:04:02.483759Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"z0sumlY/wyWVOLPsse7/ERoZGqT71cPb/pEY7JAsX9MpfBPlbSRANpnJ0qvykiX4Ier51gkrcfZz7NUXSuW0Bg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:04:02.484181Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.02893","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2d1d5386c4fa9298da298491ebde8367ff30e36bf7d8c8a2d83938ce1aefdd4c","sha256:7932bb9cb2a2d4b4094dff217e9f1245d78100ee7a2ffed8cf56e58940e14d43"],"state_sha256":"a74bfdfa8adc8d3683d81ed3976242432001eb13d824a0524055c6900da0c81e"}