{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:P3WUEFY345QDQYT6YZDIA2X2VN","short_pith_number":"pith:P3WUEFY3","schema_version":"1.0","canonical_sha256":"7eed42171be76038627ec646806afaab594e8b50debe6fbb66045ba058b10200","source":{"kind":"arxiv","id":"2409.00147","version":1},"attestation_state":"computed","paper":{"title":"MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Fu, Hongguang Fu, Liangcai Gao, Shuai Peng, Xiuqin Zhong, Zhi Tang","submitted_at":"2024-08-30T07:37:38Z","abstract_excerpt":"The rapid development of large language models (LLMs) has spurred extensive research into their domain-specific capabilities, particularly mathematical reasoning. However, most open-source LLMs focus solely on mathematical reasoning, neglecting the integration with visual injection, despite the fact that many mathematical tasks rely on visual inputs such as geometric diagrams, charts, and function plots. To fill this gap, we introduce \\textbf{MultiMath-7B}, a multimodal large language model that bridges the gap between math and vision. \\textbf{MultiMath-7B} is trained through a four-stage proc"},"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":"2409.00147","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-08-30T07:37:38Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f220d3ac23c60065505a303450d303d1ea07d7537c1a60b7ffdbf959e02d9eb","abstract_canon_sha256":"5917e1a63653773c1749ad0dd79883f79b3db4aee8d1e97c5cf08a9e41ae632b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:01:41.605052Z","signature_b64":"pe8qCfMr45r6uwUeDKoeTY4Mqs+GW/8/TrWtUEK82PtewOmv1SU+jz1JPI/IXpZtcxSmxL2q8u97WR6uexxBBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7eed42171be76038627ec646806afaab594e8b50debe6fbb66045ba058b10200","last_reissued_at":"2026-07-05T09:01:41.604571Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:01:41.604571Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MultiMath: Bridging Visual and Mathematical Reasoning for Large Language Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Di Fu, Hongguang Fu, Liangcai Gao, Shuai Peng, Xiuqin Zhong, Zhi Tang","submitted_at":"2024-08-30T07:37:38Z","abstract_excerpt":"The rapid development of large language models (LLMs) has spurred extensive research into their domain-specific capabilities, particularly mathematical reasoning. However, most open-source LLMs focus solely on mathematical reasoning, neglecting the integration with visual injection, despite the fact that many mathematical tasks rely on visual inputs such as geometric diagrams, charts, and function plots. To fill this gap, we introduce \\textbf{MultiMath-7B}, a multimodal large language model that bridges the gap between math and vision. \\textbf{MultiMath-7B} is trained through a four-stage proc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.00147","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/2409.00147/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":"2409.00147","created_at":"2026-07-05T09:01:41.604626+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.00147v1","created_at":"2026-07-05T09:01:41.604626+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.00147","created_at":"2026-07-05T09:01:41.604626+00:00"},{"alias_kind":"pith_short_12","alias_value":"P3WUEFY345QD","created_at":"2026-07-05T09:01:41.604626+00:00"},{"alias_kind":"pith_short_16","alias_value":"P3WUEFY345QDQYT6","created_at":"2026-07-05T09:01:41.604626+00:00"},{"alias_kind":"pith_short_8","alias_value":"P3WUEFY3","created_at":"2026-07-05T09:01:41.604626+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":9,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2607.02089","citing_title":"ESC: Emotional Self-Correction for Reliable Vision-Language Models","ref_index":65,"is_internal_anchor":false},{"citing_arxiv_id":"2606.17888","citing_title":"MathVis-Fine: Aligning Visual Supervision with Necessity via Progressive Dependency-Guided Training for Multimodal Mathematical Reasoning","ref_index":35,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":216,"is_internal_anchor":false},{"citing_arxiv_id":"2606.01145","citing_title":"Reasoning4Sciences: Bridging Reasoning Language Models to All Scientific Branches","ref_index":231,"is_internal_anchor":false},{"citing_arxiv_id":"2410.04509","citing_title":"ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2503.16549","citing_title":"MathFlow: Enhancing the Perceptual Flow of MLLMs for Visual Mathematical Problems","ref_index":48,"is_internal_anchor":false},{"citing_arxiv_id":"2511.01831","citing_title":"Routing-Based Continual Learning for Multimodal Large Language Models","ref_index":51,"is_internal_anchor":false},{"citing_arxiv_id":"2603.09677","citing_title":"Logics-Parsing-Omni Technical Report","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2603.18472","citing_title":"Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding","ref_index":118,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN","json":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN.json","graph_json":"https://pith.science/api/pith-number/P3WUEFY345QDQYT6YZDIA2X2VN/graph.json","events_json":"https://pith.science/api/pith-number/P3WUEFY345QDQYT6YZDIA2X2VN/events.json","paper":"https://pith.science/paper/P3WUEFY3"},"agent_actions":{"view_html":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN","download_json":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN.json","view_paper":"https://pith.science/paper/P3WUEFY3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.00147&json=true","fetch_graph":"https://pith.science/api/pith-number/P3WUEFY345QDQYT6YZDIA2X2VN/graph.json","fetch_events":"https://pith.science/api/pith-number/P3WUEFY345QDQYT6YZDIA2X2VN/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN/action/timestamp_anchor","attest_storage":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN/action/storage_attestation","attest_author":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN/action/author_attestation","sign_citation":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN/action/citation_signature","submit_replication":"https://pith.science/pith/P3WUEFY345QDQYT6YZDIA2X2VN/action/replication_record"}},"created_at":"2026-07-05T09:01:41.604626+00:00","updated_at":"2026-07-05T09:01:41.604626+00:00"}