{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:C5JEH547MLU6RUDSNMOJXR4P6J","short_pith_number":"pith:C5JEH547","schema_version":"1.0","canonical_sha256":"175243f79f62e9e8d0726b1c9bc78ff253c85b2241d0250c5f2fbf69c9af71ed","source":{"kind":"arxiv","id":"2412.05237","version":2},"attestation_state":"computed","paper":{"title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Li, Graham Neubig, Jarvis Guo, King Zhu, Tuney Zheng, Wenhu Chen, Xiang Yue, Yizhi Li, Yubo Wang, Yuelin Bai","submitted_at":"2024-12-06T18:14:24Z","abstract_excerpt":"Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were predominately repurposed from academic datasets such as VQA, AI2D, and ChartQA. These datasets target simplistic tasks, and only provide phrase-level answers without any intermediate rationales. To address these challenges, we introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate ratio"},"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":"2412.05237","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-12-06T18:14:24Z","cross_cats_sorted":["cs.CV"],"title_canon_sha256":"775f88a39a0ba7add683b823586b925fc2cc2cdd23b47ba6a62b242a44943d18","abstract_canon_sha256":"a52dd15252321ce96f96d0ea89e589cb228bdec90af84c7089e42e08f496e254"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:15:41.029461Z","signature_b64":"gOFrxAdBK1PDleP+towAFSH9vdX3VHAYC+dSkvEHvdcXnq9A57jglkknIyjnwUDQwxgljMOD9GtK6AvNK7u0Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"175243f79f62e9e8d0726b1c9bc78ff253c85b2241d0250c5f2fbf69c9af71ed","last_reissued_at":"2026-07-05T11:15:41.028896Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:15:41.028896Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MAmmoTH-VL: Eliciting Multimodal Reasoning with Instruction Tuning at Scale","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV"],"primary_cat":"cs.CL","authors_text":"Bo Li, Graham Neubig, Jarvis Guo, King Zhu, Tuney Zheng, Wenhu Chen, Xiang Yue, Yizhi Li, Yubo Wang, Yuelin Bai","submitted_at":"2024-12-06T18:14:24Z","abstract_excerpt":"Open-source multimodal large language models (MLLMs) have shown significant potential in a broad range of multimodal tasks. However, their reasoning capabilities remain constrained by existing instruction-tuning datasets, which were predominately repurposed from academic datasets such as VQA, AI2D, and ChartQA. These datasets target simplistic tasks, and only provide phrase-level answers without any intermediate rationales. To address these challenges, we introduce a scalable and cost-effective method to construct a large-scale multimodal instruction-tuning dataset with rich intermediate ratio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05237","kind":"arxiv","version":2},"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/2412.05237/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":"2412.05237","created_at":"2026-07-05T11:15:41.028957+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05237v2","created_at":"2026-07-05T11:15:41.028957+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05237","created_at":"2026-07-05T11:15:41.028957+00:00"},{"alias_kind":"pith_short_12","alias_value":"C5JEH547MLU6","created_at":"2026-07-05T11:15:41.028957+00:00"},{"alias_kind":"pith_short_16","alias_value":"C5JEH547MLU6RUDS","created_at":"2026-07-05T11:15:41.028957+00:00"},{"alias_kind":"pith_short_8","alias_value":"C5JEH547","created_at":"2026-07-05T11:15:41.028957+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":20,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.25432","citing_title":"Brevity is the Soul of Inference Efficiency: Inducing Concision in VLMs via Data Curation","ref_index":42,"is_internal_anchor":false},{"citing_arxiv_id":"2606.13289","citing_title":"HYDRA-X: Native Unified Multimodal Models with Holistic Visual Tokenizers","ref_index":165,"is_internal_anchor":false},{"citing_arxiv_id":"2606.00390","citing_title":"Zamba2-VL Technical Report","ref_index":117,"is_internal_anchor":false},{"citing_arxiv_id":"2606.25432","citing_title":"Brevity is the Soul of Inference Efficiency: Inducing Concision in VLMs via Data Curation","ref_index":41,"is_internal_anchor":false},{"citing_arxiv_id":"2502.13923","citing_title":"Qwen2.5-VL Technical Report","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16416","citing_title":"Circle-RoPE: Cone-like Decoupled Rotary Positional Embedding for Large Vision-Language Models","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2605.17283","citing_title":"OProver: A Unified Framework for Agentic Formal Theorem Proving","ref_index":70,"is_internal_anchor":false},{"citing_arxiv_id":"2503.17352","citing_title":"OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles","ref_index":21,"is_internal_anchor":false},{"citing_arxiv_id":"2511.22663","citing_title":"AIA: Rethinking Architecture Decoupling Strategy In Unified Multimodal Model","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2505.16933","citing_title":"LLaDA-V: Large Language Diffusion Models with Visual Instruction Tuning","ref_index":55,"is_internal_anchor":false},{"citing_arxiv_id":"2503.10615","citing_title":"R1-Onevision: Advancing Generalized Multimodal Reasoning through Cross-Modal Formalization","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2503.12605","citing_title":"Multimodal Chain-of-Thought Reasoning: A Comprehensive Survey","ref_index":256,"is_internal_anchor":false},{"citing_arxiv_id":"2603.27259","citing_title":"Seeing the Scene Matters: Revealing Forgetting in Video Understanding Models with a Scene-Aware Long-Video Benchmark","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11405","citing_title":"20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2504.05299","citing_title":"SmolVLM: Redefining small and efficient multimodal models","ref_index":15,"is_internal_anchor":false},{"citing_arxiv_id":"2605.11405","citing_title":"20/20 Vision Language Models: A Prescription for Better VLMs through Data Curation Alone","ref_index":17,"is_internal_anchor":false},{"citing_arxiv_id":"2605.08560","citing_title":"ZAYA1-VL-8B Technical Report","ref_index":150,"is_internal_anchor":false},{"citing_arxiv_id":"2604.24625","citing_title":"Meta-CoT: Enhancing Granularity and Generalization in Image Editing","ref_index":13,"is_internal_anchor":false},{"citing_arxiv_id":"2604.11490","citing_title":"Anthropogenic Regional Adaptation in Multimodal Vision-Language Model","ref_index":25,"is_internal_anchor":false},{"citing_arxiv_id":"2505.14683","citing_title":"Emerging Properties in Unified Multimodal Pretraining","ref_index":27,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J","json":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J.json","graph_json":"https://pith.science/api/pith-number/C5JEH547MLU6RUDSNMOJXR4P6J/graph.json","events_json":"https://pith.science/api/pith-number/C5JEH547MLU6RUDSNMOJXR4P6J/events.json","paper":"https://pith.science/paper/C5JEH547"},"agent_actions":{"view_html":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J","download_json":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J.json","view_paper":"https://pith.science/paper/C5JEH547","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05237&json=true","fetch_graph":"https://pith.science/api/pith-number/C5JEH547MLU6RUDSNMOJXR4P6J/graph.json","fetch_events":"https://pith.science/api/pith-number/C5JEH547MLU6RUDSNMOJXR4P6J/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J/action/timestamp_anchor","attest_storage":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J/action/storage_attestation","attest_author":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J/action/author_attestation","sign_citation":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J/action/citation_signature","submit_replication":"https://pith.science/pith/C5JEH547MLU6RUDSNMOJXR4P6J/action/replication_record"}},"created_at":"2026-07-05T11:15:41.028957+00:00","updated_at":"2026-07-05T11:15:41.028957+00:00"}