{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:AGCBMSFLYC7Z5NEN64X4IOF6H4","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"1f5137bf9b97da59c9012eb0bb031534c8f3639c6cbe1b1dba1af1a503235cd9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T03:33:23Z","title_canon_sha256":"b9ccb165195e0603b5c1cdc22a968a606b9a637ad0af6f699a6bf139d41465c8"},"schema_version":"1.0","source":{"id":"2505.15068","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.15068","created_at":"2026-07-05T11:06:40Z"},{"alias_kind":"arxiv_version","alias_value":"2505.15068v1","created_at":"2026-07-05T11:06:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.15068","created_at":"2026-07-05T11:06:40Z"},{"alias_kind":"pith_short_12","alias_value":"AGCBMSFLYC7Z","created_at":"2026-07-05T11:06:40Z"},{"alias_kind":"pith_short_16","alias_value":"AGCBMSFLYC7Z5NEN","created_at":"2026-07-05T11:06:40Z"},{"alias_kind":"pith_short_8","alias_value":"AGCBMSFL","created_at":"2026-07-05T11:06:40Z"}],"graph_snapshots":[{"event_id":"sha256:01a0fd7471710107932658a91a3c5e7e9437002f3b914b6777c42a4cf0915cf3","target":"graph","created_at":"2026-07-05T11:06:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.15068/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in large language models (LLMs) has enabled substantial advances in solving mathematical problems. However, existing benchmarks often fail to reflect the complexity of real-world problems, which demand open-ended, interdisciplinary reasoning and integration of computational tools. To address this gap, we introduce ModelingBench, a novel benchmark featuring real-world-inspired, open-ended problems from math modeling competitions across diverse domains, ranging from urban traffic optimization to ecosystem resource planning. These tasks require translating natural language into fo","authors_text":"Avirup Sil, Cheng Qian, ChengXiang Zhai, Heng Ji, Hongru Wang, Hongyi Du, Kathleen McKeown, Xiusi Chen, Yuji Zhang","cross_cats":["cs.CL","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T03:33:23Z","title":"ModelingAgent: Bridging LLMs and Mathematical Modeling for Real-World Challenges"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.15068","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:f75aafe108fc1162c24891b5452250de9181a7d38f891fc9aedf2b011ebe19c3","target":"record","created_at":"2026-07-05T11:06:40Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"1f5137bf9b97da59c9012eb0bb031534c8f3639c6cbe1b1dba1af1a503235cd9","cross_cats_sorted":["cs.CL","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2025-05-21T03:33:23Z","title_canon_sha256":"b9ccb165195e0603b5c1cdc22a968a606b9a637ad0af6f699a6bf139d41465c8"},"schema_version":"1.0","source":{"id":"2505.15068","kind":"arxiv","version":1}},"canonical_sha256":"01841648abc0bf9eb48df72fc438be3f299eee925750ce968982d64f405724f8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"01841648abc0bf9eb48df72fc438be3f299eee925750ce968982d64f405724f8","first_computed_at":"2026-07-05T11:06:40.017592Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:06:40.017592Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7mhNPy91CuOr1UvL+7qc3v7nTArahD9X5LiLNo/HJukaukqUbx4G2VEFQR/lFf9VfUQssIYwCshd2myMXPgqAw==","signature_status":"signed_v1","signed_at":"2026-07-05T11:06:40.018078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.15068","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f75aafe108fc1162c24891b5452250de9181a7d38f891fc9aedf2b011ebe19c3","sha256:01a0fd7471710107932658a91a3c5e7e9437002f3b914b6777c42a4cf0915cf3"],"state_sha256":"7b87345274aac3e4919ce94c83bc6e23de2791fae97cc5e322bf975c4ab123ca"}