{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:Y3SJI3VKXMCWSLXCYTCZENDFZQ","short_pith_number":"pith:Y3SJI3VK","schema_version":"1.0","canonical_sha256":"c6e4946eaabb05692ee2c4c5923465cc1e8a36b40806338e20078fbee8c078df","source":{"kind":"arxiv","id":"2508.10433","version":1},"attestation_state":"computed","paper":{"title":"We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chen Li, Chong Sun, Enhui Wan, Guanting Dong, Honggang Zhang, Jie Wang, Peiqing Yang, Qiuna Tan, Runqi Qiao, Sitong Zhou, Xiaowan Wang, Yanzi Wang, Yida Xu, Yuchen Zeng","submitted_at":"2025-08-14T08:15:41Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to comprehensively enhance"},"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":"2508.10433","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-08-14T08:15:41Z","cross_cats_sorted":["cs.CV","cs.LG"],"title_canon_sha256":"51e7b1fb60c7dea7ac2fcec157b39c5072129a8b8a6f52f3e23fd64561d39194","abstract_canon_sha256":"8757a804771df652b2890b9e8073e103b7d04c9b9cba004f5c7e021039f64541"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:53:56.224732Z","signature_b64":"4HgvgZJzwoebFbbb5FhA59yGvo+GOLT4Fqb71WmjfN6pI/ja8v4tjS9cg8AZrYiL/ZxDboX7BFIc+lton13GAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c6e4946eaabb05692ee2c4c5923465cc1e8a36b40806338e20078fbee8c078df","last_reissued_at":"2026-07-05T11:53:56.224149Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:53:56.224149Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"We-Math 2.0: A Versatile MathBook System for Incentivizing Visual Mathematical Reasoning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CV","cs.LG"],"primary_cat":"cs.AI","authors_text":"Chen Li, Chong Sun, Enhui Wan, Guanting Dong, Honggang Zhang, Jie Wang, Peiqing Yang, Qiuna Tan, Runqi Qiao, Sitong Zhou, Xiaowan Wang, Yanzi Wang, Yida Xu, Yuchen Zeng","submitted_at":"2025-08-14T08:15:41Z","abstract_excerpt":"Multimodal Large Language Models (MLLMs) have demonstrated impressive capabilities across various tasks, but still struggle with complex mathematical reasoning. Existing research primarily focuses on dataset construction and method optimization, often overlooking two critical aspects: comprehensive knowledge-driven design and model-centric data space modeling. In this paper, we introduce We-Math 2.0, a unified system that integrates a structured mathematical knowledge system, model-centric data space modeling, and a reinforcement learning (RL)-based training paradigm to comprehensively enhance"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.10433","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/2508.10433/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":"2508.10433","created_at":"2026-07-05T11:53:56.224218+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.10433v1","created_at":"2026-07-05T11:53:56.224218+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.10433","created_at":"2026-07-05T11:53:56.224218+00:00"},{"alias_kind":"pith_short_12","alias_value":"Y3SJI3VKXMCW","created_at":"2026-07-05T11:53:56.224218+00:00"},{"alias_kind":"pith_short_16","alias_value":"Y3SJI3VKXMCWSLXC","created_at":"2026-07-05T11:53:56.224218+00:00"},{"alias_kind":"pith_short_8","alias_value":"Y3SJI3VK","created_at":"2026-07-05T11:53:56.224218+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.23543","citing_title":"VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct","ref_index":46,"is_internal_anchor":false},{"citing_arxiv_id":"2605.25571","citing_title":"AnE: Pushing the Reasoning Frontier of Multimodal LLMs via Anchor Evolution","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.26781","citing_title":"LiveK12Bench: Have Large Multimodal Models Truly Conquered High School-level Examinations?","ref_index":9,"is_internal_anchor":false},{"citing_arxiv_id":"2511.20785","citing_title":"LongVT: Incentivizing \"Thinking with Long Videos\" via Native Tool Calling","ref_index":33,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00814","citing_title":"Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs","ref_index":59,"is_internal_anchor":false},{"citing_arxiv_id":"2604.18292","citing_title":"Agent-World: Scaling Real-World Environment Synthesis for Evolving General Agent Intelligence","ref_index":79,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ","json":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ.json","graph_json":"https://pith.science/api/pith-number/Y3SJI3VKXMCWSLXCYTCZENDFZQ/graph.json","events_json":"https://pith.science/api/pith-number/Y3SJI3VKXMCWSLXCYTCZENDFZQ/events.json","paper":"https://pith.science/paper/Y3SJI3VK"},"agent_actions":{"view_html":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ","download_json":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ.json","view_paper":"https://pith.science/paper/Y3SJI3VK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.10433&json=true","fetch_graph":"https://pith.science/api/pith-number/Y3SJI3VKXMCWSLXCYTCZENDFZQ/graph.json","fetch_events":"https://pith.science/api/pith-number/Y3SJI3VKXMCWSLXCYTCZENDFZQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ/action/storage_attestation","attest_author":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ/action/author_attestation","sign_citation":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ/action/citation_signature","submit_replication":"https://pith.science/pith/Y3SJI3VKXMCWSLXCYTCZENDFZQ/action/replication_record"}},"created_at":"2026-07-05T11:53:56.224218+00:00","updated_at":"2026-07-05T11:53:56.224218+00:00"}