{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:I6SYE4MELFFYAITQYEVPCXBMQJ","short_pith_number":"pith:I6SYE4ME","schema_version":"1.0","canonical_sha256":"47a5827184594b802270c12af15c2c827857c00133214b2aa81180e5888132f6","source":{"kind":"arxiv","id":"2411.01679","version":2},"attestation_state":"computed","paper":{"title":"Autoformulation of Mathematical Optimization Models Using LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mihaela van der Schaar, Nicol\\'as Astorga, Tennison Liu, Yuanzhang Xiao","submitted_at":"2024-11-03T20:41:38Z","abstract_excerpt":"Mathematical optimization is fundamental to decision-making across diverse domains, from operations research to healthcare. Yet, translating real-world problems into optimization models remains a difficult task, often demanding specialized expertise. This paper approaches the problem of $\\textit{autoformulation}$: the automated creation of solver-ready optimization models from natural language problem descriptions. We identify three core challenges of autoformulation: $\\textit{(1)}$ the vast, problem-dependent hypothesis space, $\\textit{(2)}$ efficient and diverse exploration of this space und"},"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":"2411.01679","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-11-03T20:41:38Z","cross_cats_sorted":[],"title_canon_sha256":"b6badf48ef7ba6e4c9211f74d1e9c96773220c2a7c16960031a7c0ae46c7e8fc","abstract_canon_sha256":"b7d9b60e6c722ca4aa01a7d171a6f840573735162dc7e3a6af6801a10ba3d77c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:16:30.425963Z","signature_b64":"6+5P93NUVIfF0eZ8Bf/L22OOeL93S9zpUSWZJYZ48uGG7DCCcbek8YBqNna4mB2Hj8790SaJHH/zXrL67nR0DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"47a5827184594b802270c12af15c2c827857c00133214b2aa81180e5888132f6","last_reissued_at":"2026-07-05T11:16:30.425391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:16:30.425391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Autoformulation of Mathematical Optimization Models Using LLMs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Mihaela van der Schaar, Nicol\\'as Astorga, Tennison Liu, Yuanzhang Xiao","submitted_at":"2024-11-03T20:41:38Z","abstract_excerpt":"Mathematical optimization is fundamental to decision-making across diverse domains, from operations research to healthcare. Yet, translating real-world problems into optimization models remains a difficult task, often demanding specialized expertise. This paper approaches the problem of $\\textit{autoformulation}$: the automated creation of solver-ready optimization models from natural language problem descriptions. We identify three core challenges of autoformulation: $\\textit{(1)}$ the vast, problem-dependent hypothesis space, $\\textit{(2)}$ efficient and diverse exploration of this space und"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.01679","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/2411.01679/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":"2411.01679","created_at":"2026-07-05T11:16:30.425457+00:00"},{"alias_kind":"arxiv_version","alias_value":"2411.01679v2","created_at":"2026-07-05T11:16:30.425457+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.01679","created_at":"2026-07-05T11:16:30.425457+00:00"},{"alias_kind":"pith_short_12","alias_value":"I6SYE4MELFFY","created_at":"2026-07-05T11:16:30.425457+00:00"},{"alias_kind":"pith_short_16","alias_value":"I6SYE4MELFFYAITQ","created_at":"2026-07-05T11:16:30.425457+00:00"},{"alias_kind":"pith_short_8","alias_value":"I6SYE4ME","created_at":"2026-07-05T11:16:30.425457+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.27013","citing_title":"Generating Robust Portfolios of Optimization Models using Large Language Models","ref_index":1,"is_internal_anchor":false},{"citing_arxiv_id":"2605.10598","citing_title":"Budget-Efficient Automatic Algorithm Design via Code Graph","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2604.16804","citing_title":"AutoOR: Scalably Post-training LLMs to Autoformalize Operations Research Problems","ref_index":1,"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":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ","json":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ.json","graph_json":"https://pith.science/api/pith-number/I6SYE4MELFFYAITQYEVPCXBMQJ/graph.json","events_json":"https://pith.science/api/pith-number/I6SYE4MELFFYAITQYEVPCXBMQJ/events.json","paper":"https://pith.science/paper/I6SYE4ME"},"agent_actions":{"view_html":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ","download_json":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ.json","view_paper":"https://pith.science/paper/I6SYE4ME","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2411.01679&json=true","fetch_graph":"https://pith.science/api/pith-number/I6SYE4MELFFYAITQYEVPCXBMQJ/graph.json","fetch_events":"https://pith.science/api/pith-number/I6SYE4MELFFYAITQYEVPCXBMQJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ/action/storage_attestation","attest_author":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ/action/author_attestation","sign_citation":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ/action/citation_signature","submit_replication":"https://pith.science/pith/I6SYE4MELFFYAITQYEVPCXBMQJ/action/replication_record"}},"created_at":"2026-07-05T11:16:30.425457+00:00","updated_at":"2026-07-05T11:16:30.425457+00:00"}