{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:ULYOTOMCRJAWCYRFAOIY237WLE","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":"78f364241913934aa9b8216e9e0c6ea657c0aa0c52125788e115218a30f5e045","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T04:43:23Z","title_canon_sha256":"206aa0449f7876d131eb986fe34850d772716b7832205bd98cdf7a8bd7cc3d95"},"schema_version":"1.0","source":{"id":"2606.19787","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.19787","created_at":"2026-06-19T16:12:35Z"},{"alias_kind":"arxiv_version","alias_value":"2606.19787v1","created_at":"2026-06-19T16:12:35Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.19787","created_at":"2026-06-19T16:12:35Z"},{"alias_kind":"pith_short_12","alias_value":"ULYOTOMCRJAW","created_at":"2026-06-19T16:12:35Z"},{"alias_kind":"pith_short_16","alias_value":"ULYOTOMCRJAWCYRF","created_at":"2026-06-19T16:12:35Z"},{"alias_kind":"pith_short_8","alias_value":"ULYOTOMC","created_at":"2026-06-19T16:12:35Z"}],"graph_snapshots":[{"event_id":"sha256:10d3f624edcfb08fd4fc1b220cc5f47eac00f49c05dccc7b57f793f2136d3bdb","target":"graph","created_at":"2026-06-19T16:12:35Z","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/2606.19787/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guanyu Nie, Jiajun Li, Mingshu Cai, Ran Hou, Wanyuan Wang, Xiongwei Han, Yixuan Li, Yu Ding","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T04:43:23Z","title":"ORAgentBench: Can LLM Agents Solve Challenging Operations Research Tasks End to End?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.19787","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":"sha256:8e1c138357b8b7c3d8c89d157275b4c9428d1d1d733e97880accc06c27a5fffe","target":"record","created_at":"2026-06-19T16:12:35Z","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":"78f364241913934aa9b8216e9e0c6ea657c0aa0c52125788e115218a30f5e045","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.AI","submitted_at":"2026-06-18T04:43:23Z","title_canon_sha256":"206aa0449f7876d131eb986fe34850d772716b7832205bd98cdf7a8bd7cc3d95"},"schema_version":"1.0","source":{"id":"2606.19787","kind":"arxiv","version":1}},"canonical_sha256":"a2f0e9b9828a4161622503918d6ff6591a9297263eeb4df1b9099e4cf9ce5457","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a2f0e9b9828a4161622503918d6ff6591a9297263eeb4df1b9099e4cf9ce5457","first_computed_at":"2026-06-19T16:12:35.162391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:12:35.162391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"83kSOWlU3OcJb6LAE36NhDjg2kJMfzh30XHPzuWc/F2py8Jwq/kUn7PgxNVzNoPU1/tOjZTnHr1aSKBATjuLDA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:12:35.162729Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.19787","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e1c138357b8b7c3d8c89d157275b4c9428d1d1d733e97880accc06c27a5fffe","sha256:10d3f624edcfb08fd4fc1b220cc5f47eac00f49c05dccc7b57f793f2136d3bdb"],"state_sha256":"d60d70698aac48da1394a07ea495f616eee765b273b925ed9c5d6a39b05729c5"}