{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:DFSMVLQW4WXDKQAMFKROIVHC35","short_pith_number":"pith:DFSMVLQW","schema_version":"1.0","canonical_sha256":"1964caae16e5ae35400c2aa2e454e2df59d158795016766fa1048c3a296d7cf3","source":{"kind":"arxiv","id":"2412.04857","version":1},"attestation_state":"computed","paper":{"title":"Neuro-Symbolic Data Generation for Math Reasoning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chun Cao, Fan Yang, Xian Zhang, Xiaoxing Ma, Yuan Yao, Yu-Feng Li, Zenan Li, Zhi Zhou","submitted_at":"2024-12-06T08:49:49Z","abstract_excerpt":"A critical question about Large Language Models (LLMs) is whether their apparent deficiency in mathematical reasoning is inherent, or merely a result of insufficient exposure to high-quality mathematical data. To explore this, we developed an automated method for generating high-quality, supervised mathematical datasets. The method carefully mutates existing math problems, ensuring both diversity and validity of the newly generated problems. This is achieved by a neuro-symbolic data generation framework combining the intuitive informalization strengths of LLMs, and the precise symbolic reasoni"},"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":"2412.04857","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.AI","submitted_at":"2024-12-06T08:49:49Z","cross_cats_sorted":[],"title_canon_sha256":"d8b238b6705bd1b0ac755cf1f2cc1a8fda797b18dda09d7e085bf65773c7acfa","abstract_canon_sha256":"08ba1315530eb4871da49fbbfb22ea96ba3a163713107b04a81db5f8637e20b6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:45:24.904495Z","signature_b64":"FQX4pgD9MNyKuNO3VkafyQEmt44LglHv2HOQUy9xnuBreqhlWWcvWDnCcsbhNiijzX1zZ1aAUzHXdPceh6FzDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1964caae16e5ae35400c2aa2e454e2df59d158795016766fa1048c3a296d7cf3","last_reissued_at":"2026-07-05T09:45:24.904012Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:45:24.904012Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Neuro-Symbolic Data Generation for Math Reasoning","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chun Cao, Fan Yang, Xian Zhang, Xiaoxing Ma, Yuan Yao, Yu-Feng Li, Zenan Li, Zhi Zhou","submitted_at":"2024-12-06T08:49:49Z","abstract_excerpt":"A critical question about Large Language Models (LLMs) is whether their apparent deficiency in mathematical reasoning is inherent, or merely a result of insufficient exposure to high-quality mathematical data. To explore this, we developed an automated method for generating high-quality, supervised mathematical datasets. The method carefully mutates existing math problems, ensuring both diversity and validity of the newly generated problems. This is achieved by a neuro-symbolic data generation framework combining the intuitive informalization strengths of LLMs, and the precise symbolic reasoni"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.04857","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/2412.04857/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":"2412.04857","created_at":"2026-07-05T09:45:24.904077+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.04857v1","created_at":"2026-07-05T09:45:24.904077+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.04857","created_at":"2026-07-05T09:45:24.904077+00:00"},{"alias_kind":"pith_short_12","alias_value":"DFSMVLQW4WXD","created_at":"2026-07-05T09:45:24.904077+00:00"},{"alias_kind":"pith_short_16","alias_value":"DFSMVLQW4WXDKQAM","created_at":"2026-07-05T09:45:24.904077+00:00"},{"alias_kind":"pith_short_8","alias_value":"DFSMVLQW","created_at":"2026-07-05T09:45:24.904077+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09712","citing_title":"LAST: Leveraging Tools as Hints to Enhance Spatial Reasoning for Multimodal Large Language Models","ref_index":21,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35","json":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35.json","graph_json":"https://pith.science/api/pith-number/DFSMVLQW4WXDKQAMFKROIVHC35/graph.json","events_json":"https://pith.science/api/pith-number/DFSMVLQW4WXDKQAMFKROIVHC35/events.json","paper":"https://pith.science/paper/DFSMVLQW"},"agent_actions":{"view_html":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35","download_json":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35.json","view_paper":"https://pith.science/paper/DFSMVLQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.04857&json=true","fetch_graph":"https://pith.science/api/pith-number/DFSMVLQW4WXDKQAMFKROIVHC35/graph.json","fetch_events":"https://pith.science/api/pith-number/DFSMVLQW4WXDKQAMFKROIVHC35/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35/action/timestamp_anchor","attest_storage":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35/action/storage_attestation","attest_author":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35/action/author_attestation","sign_citation":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35/action/citation_signature","submit_replication":"https://pith.science/pith/DFSMVLQW4WXDKQAMFKROIVHC35/action/replication_record"}},"created_at":"2026-07-05T09:45:24.904077+00:00","updated_at":"2026-07-05T09:45:24.904077+00:00"}