{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:PPA4QS5EFY7R4KBKAEQWTXNLDS","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":"630a976cf1cf075c97c79546ea4d3c40ca6729660e03dbe0ae75df5217c9df85","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T23:37:52Z","title_canon_sha256":"bfefd383d137318e258af4c9167fa4b12bbfeac72a4e5639f7f9263705837aa6"},"schema_version":"1.0","source":{"id":"2606.18543","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.18543","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"arxiv_version","alias_value":"2606.18543v1","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.18543","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_12","alias_value":"PPA4QS5EFY7R","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_16","alias_value":"PPA4QS5EFY7R4KBK","created_at":"2026-06-19T16:11:40Z"},{"alias_kind":"pith_short_8","alias_value":"PPA4QS5E","created_at":"2026-06-19T16:11:40Z"}],"graph_snapshots":[{"event_id":"sha256:85fdaf4f97d1fc2c80c91f9f92198b548a5b203edea64995fc9b94eb220951d1","target":"graph","created_at":"2026-06-19T16:11:40Z","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/2606.18543/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model agents are becoming proficient executors at isolated, short-horizon tasks such as software engineering and customer service. Yet real-world challenges require a combination of sophisticated skills that remain largely untested in agents: (1) navigating long horizons amid uncertainty; (2) acquiring information in noisy environments; (3) adapting to a changing world; (4) orchestrating multiple moving parts toward a coherent goal. We introduce CEO-Bench, which evaluates these capabilities together by simulating a representative real-world task: operating a startup for 500 days. An a","authors_text":"Haozhe Chen, Karthik Narasimhan, Zhuang Liu","cross_cats":["cs.CL","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T23:37:52Z","title":"CEO-Bench: Can Agents Play the Long Game?"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.18543","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":"sha256:95e4526ce1a3810019cd9be7fdf0b0cc5b24b6c079cdf3030322522c1e3b1cf1","target":"record","created_at":"2026-06-19T16:11:40Z","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":"630a976cf1cf075c97c79546ea4d3c40ca6729660e03dbe0ae75df5217c9df85","cross_cats_sorted":["cs.CL","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-16T23:37:52Z","title_canon_sha256":"bfefd383d137318e258af4c9167fa4b12bbfeac72a4e5639f7f9263705837aa6"},"schema_version":"1.0","source":{"id":"2606.18543","kind":"arxiv","version":1}},"canonical_sha256":"7bc1c84ba42e3f1e282a012169ddab1c939a074329da2bbaae115e6283253b65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7bc1c84ba42e3f1e282a012169ddab1c939a074329da2bbaae115e6283253b65","first_computed_at":"2026-06-19T16:11:40.528969Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-19T16:11:40.528969Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CblPGjrKFwDoQg2+J72Q05TizofAscth6uKk01qMmA5X2Is/9rnEdlAAjAW2VNQCDTbfF0SyO3qFS+eyLzzdCA==","signature_status":"signed_v1","signed_at":"2026-06-19T16:11:40.529300Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.18543","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:95e4526ce1a3810019cd9be7fdf0b0cc5b24b6c079cdf3030322522c1e3b1cf1","sha256:85fdaf4f97d1fc2c80c91f9f92198b548a5b203edea64995fc9b94eb220951d1"],"state_sha256":"7bc835f80111d1dd3e53920e68c66f2326608cb2d6ecc5008c163d0457a08197"}