{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:25UWFI7SIXSC2WNMSUQHNAD4HU","short_pith_number":"pith:25UWFI7S","schema_version":"1.0","canonical_sha256":"d76962a3f245e42d59ac952076807c3d1528836c5aaa0d85d8d88ee101c98c0a","source":{"kind":"arxiv","id":"2309.05653","version":3},"attestation_state":"computed","paper":{"title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Huan Sun, Wenhao Huang, Wenhu Chen, Xiang Yue, Xingwei Qu, Yao Fu, Yu Su","submitted_at":"2023-09-11T17:47:22Z","abstract_excerpt":"We introduce MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on MathInstruct, our meticulously curated instruction tuning dataset. MathInstruct is compiled from 13 math datasets with intermediate rationales, six of which have rationales newly curated by us. It presents a unique hybrid of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and also ensures extensive coverage of diverse fields in math. The hybrid of CoT and PoT not only unleashes the potential of tool use but also all"},"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":"2309.05653","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-09-11T17:47:22Z","cross_cats_sorted":[],"title_canon_sha256":"b32e8f4f7b8751a5c73576a835ae479aa4832f672253ab36013026f08e1f4dc8","abstract_canon_sha256":"a46dfaf6e07cb1b7d13e6fd313c3e45c3d69c74b047b592aada6be8f6be08237"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:42:11.991567Z","signature_b64":"aCjS/+tmyRupsJ2PMeyY/U9GmxJvvR9foPu+gbMyEZLBeg/BCXbV+vWFrSEY7uA2cGPYkDB8Kzk4XqDEeBT9Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d76962a3f245e42d59ac952076807c3d1528836c5aaa0d85d8d88ee101c98c0a","last_reissued_at":"2026-05-17T23:42:11.991038Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:42:11.991038Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAmmoTH: Building Math Generalist Models through Hybrid Instruction Tuning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ge Zhang, Huan Sun, Wenhao Huang, Wenhu Chen, Xiang Yue, Xingwei Qu, Yao Fu, Yu Su","submitted_at":"2023-09-11T17:47:22Z","abstract_excerpt":"We introduce MAmmoTH, a series of open-source large language models (LLMs) specifically tailored for general math problem-solving. The MAmmoTH models are trained on MathInstruct, our meticulously curated instruction tuning dataset. MathInstruct is compiled from 13 math datasets with intermediate rationales, six of which have rationales newly curated by us. It presents a unique hybrid of chain-of-thought (CoT) and program-of-thought (PoT) rationales, and also ensures extensive coverage of diverse fields in math. The hybrid of CoT and PoT not only unleashes the potential of tool use but also all"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2309.05653","kind":"arxiv","version":3},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"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":"2309.05653","created_at":"2026-05-17T23:42:11.991116+00:00"},{"alias_kind":"arxiv_version","alias_value":"2309.05653v3","created_at":"2026-05-17T23:42:11.991116+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2309.05653","created_at":"2026-05-17T23:42:11.991116+00:00"},{"alias_kind":"pith_short_12","alias_value":"25UWFI7SIXSC","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_16","alias_value":"25UWFI7SIXSC2WNM","created_at":"2026-05-18T12:33:33.725879+00:00"},{"alias_kind":"pith_short_8","alias_value":"25UWFI7S","created_at":"2026-05-18T12:33:33.725879+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":21,"internal_anchor_count":21,"sample":[{"citing_arxiv_id":"2406.18629","citing_title":"Step-DPO: Step-wise Preference Optimization for Long-chain Reasoning of LLMs","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2510.06965","citing_title":"EDUMATH: Generating Standards-aligned Educational Math Word Problems","ref_index":8,"is_internal_anchor":true},{"citing_arxiv_id":"2512.20856","citing_title":"NVIDIA Nemotron 3: Efficient and Open Intelligence","ref_index":173,"is_internal_anchor":true},{"citing_arxiv_id":"2402.13116","citing_title":"A Survey on Knowledge Distillation of Large Language Models","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2403.14624","citing_title":"MathVerse: Does Your Multi-modal LLM Truly See the Diagrams in Visual Math Problems?","ref_index":64,"is_internal_anchor":true},{"citing_arxiv_id":"2602.04476","citing_title":"Vision-aligned Latent Reasoning for Multi-modal Large Language Model","ref_index":34,"is_internal_anchor":true},{"citing_arxiv_id":"2406.08464","citing_title":"Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing","ref_index":159,"is_internal_anchor":true},{"citing_arxiv_id":"2602.22911","citing_title":"CeRA: Overcoming the Linear Ceiling of Low-Rank Adaptation via Capacity Expansion","ref_index":6,"is_internal_anchor":true},{"citing_arxiv_id":"2605.14075","citing_title":"Rethinking Layer Relevance in Large Language Models Beyond Cosine Similarity","ref_index":58,"is_internal_anchor":true},{"citing_arxiv_id":"2312.08935","citing_title":"Math-Shepherd: Verify and Reinforce LLMs Step-by-step without Human Annotations","ref_index":93,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06651","citing_title":"AI co-mathematician: Accelerating mathematicians with agentic AI","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2504.05299","citing_title":"SmolVLM: Redefining small and efficient multimodal models","ref_index":37,"is_internal_anchor":true},{"citing_arxiv_id":"2502.02737","citing_title":"SmolLM2: When Smol Goes Big -- Data-Centric Training of a Small Language Model","ref_index":120,"is_internal_anchor":true},{"citing_arxiv_id":"2605.08221","citing_title":"NoisyCoconut: Counterfactual Consensus via Latent Space Reasoning","ref_index":31,"is_internal_anchor":true},{"citing_arxiv_id":"2502.16982","citing_title":"Muon is Scalable for LLM Training","ref_index":55,"is_internal_anchor":true},{"citing_arxiv_id":"2502.01456","citing_title":"Process Reinforcement through Implicit Rewards","ref_index":144,"is_internal_anchor":true},{"citing_arxiv_id":"2605.06651","citing_title":"AI co-mathematician: Accelerating mathematicians with agentic AI","ref_index":7,"is_internal_anchor":true},{"citing_arxiv_id":"2604.10079","citing_title":"Why Supervised Fine-Tuning Fails to Learn: A Systematic Study of Incomplete Learning in Large Language Models","ref_index":13,"is_internal_anchor":true},{"citing_arxiv_id":"2604.07655","citing_title":"Guardian-as-an-Advisor: Advancing Next-Generation Guardian Models for Trustworthy LLMs","ref_index":88,"is_internal_anchor":true},{"citing_arxiv_id":"2401.02954","citing_title":"DeepSeek LLM: Scaling Open-Source Language Models with Longtermism","ref_index":86,"is_internal_anchor":true},{"citing_arxiv_id":"2405.04434","citing_title":"DeepSeek-V2: A Strong, Economical, and Efficient Mixture-of-Experts Language Model","ref_index":75,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU","json":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU.json","graph_json":"https://pith.science/api/pith-number/25UWFI7SIXSC2WNMSUQHNAD4HU/graph.json","events_json":"https://pith.science/api/pith-number/25UWFI7SIXSC2WNMSUQHNAD4HU/events.json","paper":"https://pith.science/paper/25UWFI7S"},"agent_actions":{"view_html":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU","download_json":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU.json","view_paper":"https://pith.science/paper/25UWFI7S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2309.05653&json=true","fetch_graph":"https://pith.science/api/pith-number/25UWFI7SIXSC2WNMSUQHNAD4HU/graph.json","fetch_events":"https://pith.science/api/pith-number/25UWFI7SIXSC2WNMSUQHNAD4HU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU/action/storage_attestation","attest_author":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU/action/author_attestation","sign_citation":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU/action/citation_signature","submit_replication":"https://pith.science/pith/25UWFI7SIXSC2WNMSUQHNAD4HU/action/replication_record"}},"created_at":"2026-05-17T23:42:11.991116+00:00","updated_at":"2026-05-17T23:42:11.991116+00:00"}