{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KHTGZXKXH2UKI5NIJGOYYMLF6X","short_pith_number":"pith:KHTGZXKX","schema_version":"1.0","canonical_sha256":"51e66cdd573ea8a475a8499d8c3165f5f35ee0660a4264842b6ecf40b8d62f15","source":{"kind":"arxiv","id":"2605.28158","version":1},"attestation_state":"computed","paper":{"title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyu Zhou, Dongdong Ge, Jianghao Lin, Jiangyue Zhao, Xinyun Lu, Yinyu Ye","submitted_at":"2026-05-27T08:41:30Z","abstract_excerpt":"Large language model (LLM) agents are increasingly used to assist with operations research (OR) modeling, yet existing OR-oriented benchmarks often reduce evaluation to one-shot translation from a self-contained problem statement into a mathematical formulation or solver program. Such settings abstract away two characteristics of real industrial OR workflows: persistent multi-artifact workspaces and multi-stage task lifecycles. We introduce OR-Space, a full-lifecycle workspace benchmark for evaluating industrial optimization agents across model construction, model revision, and grounded explan"},"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":"2605.28158","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-05-27T08:41:30Z","cross_cats_sorted":[],"title_canon_sha256":"8e94f7e09f648c51083479efa8aff6218a5ab10f5a98c3c99e5d3d9f28f6b671","abstract_canon_sha256":"d67754c67ee2caee0a512e0bd2d405f00e4ce8f4ea794efac1d0ad27b2455715"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-28T01:05:00.730080Z","signature_b64":"SPwL40jSr7iYq7d9spZPDvOFJ87Qvsn0pCK+vyh3GCN2AgIsTjUGgyx2eseIDJWD+j3+dciqmJ+HwSfI5UX8Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"51e66cdd573ea8a475a8499d8c3165f5f35ee0660a4264842b6ecf40b8d62f15","last_reissued_at":"2026-05-28T01:05:00.729667Z","signature_status":"signed_v1","first_computed_at":"2026-05-28T01:05:00.729667Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"OR-Space: A Full-Lifecycle Workspace Benchmark for Industrial Optimization Agents","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.AI","authors_text":"Chenyu Zhou, Dongdong Ge, Jianghao Lin, Jiangyue Zhao, Xinyun Lu, Yinyu Ye","submitted_at":"2026-05-27T08:41:30Z","abstract_excerpt":"Large language model (LLM) agents are increasingly used to assist with operations research (OR) modeling, yet existing OR-oriented benchmarks often reduce evaluation to one-shot translation from a self-contained problem statement into a mathematical formulation or solver program. Such settings abstract away two characteristics of real industrial OR workflows: persistent multi-artifact workspaces and multi-stage task lifecycles. We introduce OR-Space, a full-lifecycle workspace benchmark for evaluating industrial optimization agents across model construction, model revision, and grounded explan"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28158","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/2605.28158/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":"2605.28158","created_at":"2026-05-28T01:05:00.729725+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.28158v1","created_at":"2026-05-28T01:05:00.729725+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28158","created_at":"2026-05-28T01:05:00.729725+00:00"},{"alias_kind":"pith_short_12","alias_value":"KHTGZXKXH2UK","created_at":"2026-05-28T01:05:00.729725+00:00"},{"alias_kind":"pith_short_16","alias_value":"KHTGZXKXH2UKI5NI","created_at":"2026-05-28T01:05:00.729725+00:00"},{"alias_kind":"pith_short_8","alias_value":"KHTGZXKX","created_at":"2026-05-28T01:05:00.729725+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/KHTGZXKXH2UKI5NIJGOYYMLF6X","json":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X.json","graph_json":"https://pith.science/api/pith-number/KHTGZXKXH2UKI5NIJGOYYMLF6X/graph.json","events_json":"https://pith.science/api/pith-number/KHTGZXKXH2UKI5NIJGOYYMLF6X/events.json","paper":"https://pith.science/paper/KHTGZXKX"},"agent_actions":{"view_html":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X","download_json":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X.json","view_paper":"https://pith.science/paper/KHTGZXKX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.28158&json=true","fetch_graph":"https://pith.science/api/pith-number/KHTGZXKXH2UKI5NIJGOYYMLF6X/graph.json","fetch_events":"https://pith.science/api/pith-number/KHTGZXKXH2UKI5NIJGOYYMLF6X/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X/action/storage_attestation","attest_author":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X/action/author_attestation","sign_citation":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X/action/citation_signature","submit_replication":"https://pith.science/pith/KHTGZXKXH2UKI5NIJGOYYMLF6X/action/replication_record"}},"created_at":"2026-05-28T01:05:00.729725+00:00","updated_at":"2026-05-28T01:05:00.729725+00:00"}