{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:OKMVPIPEJF3XHTF227SBVR62G5","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":"ea53909c8e45b323263bee9a19b4ec2f86e10a5c7769c0b2669ffb86829cb0b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T09:10:34Z","title_canon_sha256":"78c16850489681582920b79a906311cb5ca0328cabed954b6e5a37c0fae24183"},"schema_version":"1.0","source":{"id":"2412.17874","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2412.17874","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"arxiv_version","alias_value":"2412.17874v2","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.17874","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"pith_short_12","alias_value":"OKMVPIPEJF3X","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"pith_short_16","alias_value":"OKMVPIPEJF3XHTF2","created_at":"2026-07-05T10:11:30Z"},{"alias_kind":"pith_short_8","alias_value":"OKMVPIPE","created_at":"2026-07-05T10:11:30Z"}],"graph_snapshots":[{"event_id":"sha256:bb83d7e973c93b3b3e1f1510d578e9a874e91ddc9e789d6d597a8441c24143b3","target":"graph","created_at":"2026-07-05T10:11:30Z","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/2412.17874/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"In this paper, we introduce and apply Operations Research Question Answering (ORQA), a new benchmark designed to assess the generalization capabilities of Large Language Models (LLMs) in the specialized technical domain of Operations Research (OR). This benchmark evaluates whether LLMs can emulate the knowledge and reasoning skills of OR experts when confronted with diverse and complex optimization problems. The dataset, developed by OR experts, features real-world optimization problems that demand multistep reasoning to construct their mathematical models. Our evaluations of various open sour","authors_text":"Giuseppe Carenini, Jabo Serge Byusa, Mahdi Mostajabdaveh, Rindranirina Ramamonjison, Samarendra Chandan Bindu Dash, Timothy T. Yu, Yong Zhang, Zirui Zhou","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T09:10:34Z","title":"Evaluating LLM Reasoning in the Operations Research Domain with ORQA"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.17874","kind":"arxiv","version":2},"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":"sha256:0564bf80c0da26c46a78724d40362e7abe50e3d07400901ac5bc39ba44f91ae7","target":"record","created_at":"2026-07-05T10:11:30Z","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":"ea53909c8e45b323263bee9a19b4ec2f86e10a5c7769c0b2669ffb86829cb0b7","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-12-22T09:10:34Z","title_canon_sha256":"78c16850489681582920b79a906311cb5ca0328cabed954b6e5a37c0fae24183"},"schema_version":"1.0","source":{"id":"2412.17874","kind":"arxiv","version":2}},"canonical_sha256":"729957a1e4497773ccbad7e41ac7da376d99462b4fa2be4ae32a31dafdbaa64e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"729957a1e4497773ccbad7e41ac7da376d99462b4fa2be4ae32a31dafdbaa64e","first_computed_at":"2026-07-05T10:11:30.872220Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:11:30.872220Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"t5gttMOLWqqJ3nF9ZuHp+TdudTCTfrtsa4wylgb6gb8eZRdx9op0xo9YY5+I9LWSvQ3PIf7+nrKc23PK6ECGAA==","signature_status":"signed_v1","signed_at":"2026-07-05T10:11:30.872744Z","signed_message":"canonical_sha256_bytes"},"source_id":"2412.17874","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:0564bf80c0da26c46a78724d40362e7abe50e3d07400901ac5bc39ba44f91ae7","sha256:bb83d7e973c93b3b3e1f1510d578e9a874e91ddc9e789d6d597a8441c24143b3"],"state_sha256":"64b4721faf394f74d2ca4b99f107b7accde9047f632bd5d31f60bac3dc098a35"}