{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ULYOTOMCRJAWCYRFAOIY237WLE","short_pith_number":"pith:ULYOTOMC","schema_version":"1.0","canonical_sha256":"a2f0e9b9828a4161622503918d6ff6591a9297263eeb4df1b9099e4cf9ce5457","source":{"kind":"arxiv","id":"2606.19787","version":1},"attestation_state":"computed","paper":{"title":"ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanyu Nie, Jiajun Li, Mingshu Cai, Ran Hou, Wanyuan Wang, Xiongwei Han, Yixuan Li, Yu Ding","submitted_at":"2026-06-18T04:43:23Z","abstract_excerpt":"Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR) work remains unclear. Existing OR evaluations often decouple modeling from solving, rely on pre-formalized or text-only instances, and rarely test the full workflow from operational artifacts to validated decisions. In this work, we introduce ORAgentBench, an execution-grounded benchmark for evaluating autonomous agents on challenging end-to-end operations research tasks. It contains 107 human-reviewed tasks across"},"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":"2606.19787","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T04:43:23Z","cross_cats_sorted":[],"title_canon_sha256":"206aa0449f7876d131eb986fe34850d772716b7832205bd98cdf7a8bd7cc3d95","abstract_canon_sha256":"78f364241913934aa9b8216e9e0c6ea657c0aa0c52125788e115218a30f5e045"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-19T16:12:35.162729Z","signature_b64":"83kSOWlU3OcJb6LAE36NhDjg2kJMfzh30XHPzuWc/F2py8Jwq/kUn7PgxNVzNoPU1/tOjZTnHr1aSKBATjuLDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a2f0e9b9828a4161622503918d6ff6591a9297263eeb4df1b9099e4cf9ce5457","last_reissued_at":"2026-06-19T16:12:35.162391Z","signature_status":"signed_v1","first_computed_at":"2026-06-19T16:12:35.162391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Guanyu Nie, Jiajun Li, Mingshu Cai, Ran Hou, Wanyuan Wang, Xiongwei Han, Yixuan Li, Yu Ding","submitted_at":"2026-06-18T04:43:23Z","abstract_excerpt":"Large language models are increasingly deployed as autonomous agents for multi-step tasks in executable environments, yet their ability to perform realistic operations research (OR) work remains unclear. Existing OR evaluations often decouple modeling from solving, rely on pre-formalized or text-only instances, and rarely test the full workflow from operational artifacts to validated decisions. In this work, we introduce ORAgentBench, an execution-grounded benchmark for evaluating autonomous agents on challenging end-to-end operations research tasks. It contains 107 human-reviewed tasks across"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19787","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/2606.19787/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":"2606.19787","created_at":"2026-06-19T16:12:35.162452+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.19787v1","created_at":"2026-06-19T16:12:35.162452+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19787","created_at":"2026-06-19T16:12:35.162452+00:00"},{"alias_kind":"pith_short_12","alias_value":"ULYOTOMCRJAW","created_at":"2026-06-19T16:12:35.162452+00:00"},{"alias_kind":"pith_short_16","alias_value":"ULYOTOMCRJAWCYRF","created_at":"2026-06-19T16:12:35.162452+00:00"},{"alias_kind":"pith_short_8","alias_value":"ULYOTOMC","created_at":"2026-06-19T16:12:35.162452+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE","json":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE.json","graph_json":"https://pith.science/api/pith-number/ULYOTOMCRJAWCYRFAOIY237WLE/graph.json","events_json":"https://pith.science/api/pith-number/ULYOTOMCRJAWCYRFAOIY237WLE/events.json","paper":"https://pith.science/paper/ULYOTOMC"},"agent_actions":{"view_html":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE","download_json":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE.json","view_paper":"https://pith.science/paper/ULYOTOMC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.19787&json=true","fetch_graph":"https://pith.science/api/pith-number/ULYOTOMCRJAWCYRFAOIY237WLE/graph.json","fetch_events":"https://pith.science/api/pith-number/ULYOTOMCRJAWCYRFAOIY237WLE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE/action/storage_attestation","attest_author":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE/action/author_attestation","sign_citation":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE/action/citation_signature","submit_replication":"https://pith.science/pith/ULYOTOMCRJAWCYRFAOIY237WLE/action/replication_record"}},"created_at":"2026-06-19T16:12:35.162452+00:00","updated_at":"2026-06-19T16:12:35.162452+00:00"}