{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:42KGE4QMWXT3ILBCMDTBVMYIRK","short_pith_number":"pith:42KGE4QM","schema_version":"1.0","canonical_sha256":"e69462720cb5e7b42c2260e61ab3088a9f17b632df8eec90c7b5e86d526c6a0a","source":{"kind":"arxiv","id":"2304.03287","version":1},"attestation_state":"computed","paper":{"title":"Synthesis of Mathematical programs from Natural Language Specifications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ganesh Prasath, Shirish Karande","submitted_at":"2023-03-30T06:10:00Z","abstract_excerpt":"Several decision problems that are encountered in various business domains can be modeled as mathematical programs, i.e. optimization problems. The process of conducting such modeling often requires the involvement of experts trained in operations research and advanced algorithms. Surprisingly, despite the significant advances in the methods for program and code synthesis, AutoML, learning to optimize etc., there has been little or no attention paid to automating the task of synthesizing mathematical programs. We imagine a scenario where the specifications for modeling, i.e. the objective and "},"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":"2304.03287","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.AI","submitted_at":"2023-03-30T06:10:00Z","cross_cats_sorted":["cs.CL","cs.LG"],"title_canon_sha256":"bbef596e0e58f50a2f4f8e1e2ad2e986704c5e80128b2a0f0c7667a3ebf0c238","abstract_canon_sha256":"6a7d98235896137c1f39750b14043276f93ceaf2fc68d1ae064b19e559914de1"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:58:54.280167Z","signature_b64":"pA+miPRK0hvLYSLoY5WQW/QwLcL/VDQaKfhJv2ky82VKpdtntiJbgspHpSgewYve0WsNPnoR4JxUToR0wmKfCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e69462720cb5e7b42c2260e61ab3088a9f17b632df8eec90c7b5e86d526c6a0a","last_reissued_at":"2026-07-05T05:58:54.279742Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:58:54.279742Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Synthesis of Mathematical programs from Natural Language Specifications","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.CL","cs.LG"],"primary_cat":"cs.AI","authors_text":"Ganesh Prasath, Shirish Karande","submitted_at":"2023-03-30T06:10:00Z","abstract_excerpt":"Several decision problems that are encountered in various business domains can be modeled as mathematical programs, i.e. optimization problems. The process of conducting such modeling often requires the involvement of experts trained in operations research and advanced algorithms. Surprisingly, despite the significant advances in the methods for program and code synthesis, AutoML, learning to optimize etc., there has been little or no attention paid to automating the task of synthesizing mathematical programs. We imagine a scenario where the specifications for modeling, i.e. the objective and "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2304.03287","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/2304.03287/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":"2304.03287","created_at":"2026-07-05T05:58:54.279800+00:00"},{"alias_kind":"arxiv_version","alias_value":"2304.03287v1","created_at":"2026-07-05T05:58:54.279800+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2304.03287","created_at":"2026-07-05T05:58:54.279800+00:00"},{"alias_kind":"pith_short_12","alias_value":"42KGE4QMWXT3","created_at":"2026-07-05T05:58:54.279800+00:00"},{"alias_kind":"pith_short_16","alias_value":"42KGE4QMWXT3ILBC","created_at":"2026-07-05T05:58:54.279800+00:00"},{"alias_kind":"pith_short_8","alias_value":"42KGE4QM","created_at":"2026-07-05T05:58:54.279800+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.00369","citing_title":"InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees","ref_index":60,"is_internal_anchor":false},{"citing_arxiv_id":"2605.00369","citing_title":"InvEvolve: Evolving White-Box Inventory Policies via Large Language Models with Performance Guarantees","ref_index":60,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK","json":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK.json","graph_json":"https://pith.science/api/pith-number/42KGE4QMWXT3ILBCMDTBVMYIRK/graph.json","events_json":"https://pith.science/api/pith-number/42KGE4QMWXT3ILBCMDTBVMYIRK/events.json","paper":"https://pith.science/paper/42KGE4QM"},"agent_actions":{"view_html":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK","download_json":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK.json","view_paper":"https://pith.science/paper/42KGE4QM","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2304.03287&json=true","fetch_graph":"https://pith.science/api/pith-number/42KGE4QMWXT3ILBCMDTBVMYIRK/graph.json","fetch_events":"https://pith.science/api/pith-number/42KGE4QMWXT3ILBCMDTBVMYIRK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK/action/storage_attestation","attest_author":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK/action/author_attestation","sign_citation":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK/action/citation_signature","submit_replication":"https://pith.science/pith/42KGE4QMWXT3ILBCMDTBVMYIRK/action/replication_record"}},"created_at":"2026-07-05T05:58:54.279800+00:00","updated_at":"2026-07-05T05:58:54.279800+00:00"}