{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:TKCRMJTIX33XH4SB6K5AHAMCWA","short_pith_number":"pith:TKCRMJTI","schema_version":"1.0","canonical_sha256":"9a85162668bef773f241f2ba038182b0303f610c342fe41085bcf40a84810cbd","source":{"kind":"arxiv","id":"2502.11102","version":2},"attestation_state":"computed","paper":{"title":"OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Can Ren, Hongliang Lu, Yaoyu Wu, Yuxuan Chen, Zaiwen Wen, Zhonglin Xie","submitted_at":"2025-02-16T12:38:37Z","abstract_excerpt":"Despite the rapid development of large language models (LLMs), a fundamental challenge persists: the lack of high-quality optimization modeling datasets hampers LLMs' robust modeling of practical optimization problems from natural language descriptions (NL). This data scarcity also contributes to the generalization difficulties experienced by learning-based methods. To address these challenges, we propose a scalable framework for synthesizing a high-quality dataset, named OptMATH. Starting from curated seed data with mathematical formulations (MF), this framework automatically generates proble"},"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":"2502.11102","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2025-02-16T12:38:37Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"c781663485bba6017f18c96134763ceb1f1caefc2dde315f17a9a06c8a688b6e","abstract_canon_sha256":"a341677c641d92859207e007a1017d045a45179735ccefbf98d821ce49187467"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:17:54.409819Z","signature_b64":"I9PBQx6g1YXh6GEHlLClyDbZJNJ9jLBkgWHODqTBSH8fatOXMTZiQP9dT/BNpzm0rRXNSMspYihsNZpk3An4CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9a85162668bef773f241f2ba038182b0303f610c342fe41085bcf40a84810cbd","last_reissued_at":"2026-07-05T10:17:54.409331Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:17:54.409331Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OptMATH: A Scalable Bidirectional Data Synthesis Framework for Optimization Modeling","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.AI","authors_text":"Can Ren, Hongliang Lu, Yaoyu Wu, Yuxuan Chen, Zaiwen Wen, Zhonglin Xie","submitted_at":"2025-02-16T12:38:37Z","abstract_excerpt":"Despite the rapid development of large language models (LLMs), a fundamental challenge persists: the lack of high-quality optimization modeling datasets hampers LLMs' robust modeling of practical optimization problems from natural language descriptions (NL). This data scarcity also contributes to the generalization difficulties experienced by learning-based methods. To address these challenges, we propose a scalable framework for synthesizing a high-quality dataset, named OptMATH. Starting from curated seed data with mathematical formulations (MF), this framework automatically generates proble"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.11102","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/2502.11102/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":"2502.11102","created_at":"2026-07-05T10:17:54.409391+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.11102v2","created_at":"2026-07-05T10:17:54.409391+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.11102","created_at":"2026-07-05T10:17:54.409391+00:00"},{"alias_kind":"pith_short_12","alias_value":"TKCRMJTIX33X","created_at":"2026-07-05T10:17:54.409391+00:00"},{"alias_kind":"pith_short_16","alias_value":"TKCRMJTIX33XH4SB","created_at":"2026-07-05T10:17:54.409391+00:00"},{"alias_kind":"pith_short_8","alias_value":"TKCRMJTI","created_at":"2026-07-05T10:17:54.409391+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":7,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.25246","citing_title":"FrontierOR: Benchmarking LLMs' Capacity for Efficient Algorithm Design in Large-Scale Optimization","ref_index":14,"is_internal_anchor":false},{"citing_arxiv_id":"2605.28158","citing_title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","ref_index":28,"is_internal_anchor":false},{"citing_arxiv_id":"2601.19924","citing_title":"OPT-Engine: Benchmarking the Limits of LLMs in Optimization Modeling via Complexity Scaling","ref_index":8,"is_internal_anchor":false},{"citing_arxiv_id":"2604.25847","citing_title":"From Soliloquy to Agora: Memory-Enhanced LLM Agents with Decentralized Debate for Optimization Modeling","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2604.17708","citing_title":"Co-evolving Agent Architectures and Interpretable Reasoning for Automated Optimization","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16804","citing_title":"AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems","ref_index":36,"is_internal_anchor":false},{"citing_arxiv_id":"2605.02728","citing_title":"ORPilot: A Production-Oriented Agentic LLM-for-OR Tool for Optimization Modeling","ref_index":12,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA","json":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA.json","graph_json":"https://pith.science/api/pith-number/TKCRMJTIX33XH4SB6K5AHAMCWA/graph.json","events_json":"https://pith.science/api/pith-number/TKCRMJTIX33XH4SB6K5AHAMCWA/events.json","paper":"https://pith.science/paper/TKCRMJTI"},"agent_actions":{"view_html":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA","download_json":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA.json","view_paper":"https://pith.science/paper/TKCRMJTI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.11102&json=true","fetch_graph":"https://pith.science/api/pith-number/TKCRMJTIX33XH4SB6K5AHAMCWA/graph.json","fetch_events":"https://pith.science/api/pith-number/TKCRMJTIX33XH4SB6K5AHAMCWA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA/action/storage_attestation","attest_author":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA/action/author_attestation","sign_citation":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA/action/citation_signature","submit_replication":"https://pith.science/pith/TKCRMJTIX33XH4SB6K5AHAMCWA/action/replication_record"}},"created_at":"2026-07-05T10:17:54.409391+00:00","updated_at":"2026-07-05T10:17:54.409391+00:00"}