{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:CF3MGPTR6X2MBB5CJTP4JBF7DK","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":"131efcce60e56d69ed486edb655f4e68b9fe62f4b68778309c37c2f3efc42197","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T15:32:23Z","title_canon_sha256":"10decd62bed24b6ac43e863188bf7e318154c9bf0fefcbd664398792c2cb337b"},"schema_version":"1.0","source":{"id":"2505.11368","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.11368","created_at":"2026-07-05T11:22:40Z"},{"alias_kind":"arxiv_version","alias_value":"2505.11368v2","created_at":"2026-07-05T11:22:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11368","created_at":"2026-07-05T11:22:40Z"},{"alias_kind":"pith_short_12","alias_value":"CF3MGPTR6X2M","created_at":"2026-07-05T11:22:40Z"},{"alias_kind":"pith_short_16","alias_value":"CF3MGPTR6X2MBB5C","created_at":"2026-07-05T11:22:40Z"},{"alias_kind":"pith_short_8","alias_value":"CF3MGPTR","created_at":"2026-07-05T11:22:40Z"}],"graph_snapshots":[{"event_id":"sha256:f446f90b3b2ca4f07de60e342770b471699d8af562edea5c1e9046f757eadd92","target":"graph","created_at":"2026-07-05T11:22:40Z","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/2505.11368/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large language models (LLMs) have been widely deployed as autonomous agents capable of following user instructions and making decisions in real-world applications. Previous studies have made notable progress in benchmarking the instruction following capabilities of LLMs in general domains, with a primary focus on their inherent commonsense knowledge. Recently, LLMs have been increasingly deployed as domain-oriented agents, which rely on domain-oriented guidelines that may conflict with their commonsense knowledge. These guidelines exhibit two key characteristics: they consist of a wide range o","authors_text":"Cheng Yang, Lingxiao Diao, Wanxuan Sun, Xinyue Xu, Zhuosheng Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T15:32:23Z","title":"GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11368","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:d02d097a94bae577ca2c8fd41e7d7ef1df671e08ed80c67c137e0234927501b5","target":"record","created_at":"2026-07-05T11:22:40Z","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":"131efcce60e56d69ed486edb655f4e68b9fe62f4b68778309c37c2f3efc42197","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T15:32:23Z","title_canon_sha256":"10decd62bed24b6ac43e863188bf7e318154c9bf0fefcbd664398792c2cb337b"},"schema_version":"1.0","source":{"id":"2505.11368","kind":"arxiv","version":2}},"canonical_sha256":"1176c33e71f5f4c087a24cdfc484bf1abbce61074a1517233ce7572695b8ff12","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"1176c33e71f5f4c087a24cdfc484bf1abbce61074a1517233ce7572695b8ff12","first_computed_at":"2026-07-05T11:22:40.146884Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:22:40.146884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"TQN535r0tCYqkjWJAD+CzbF8oa0+tN4Wzh6+v5+JnJ+Q3u+rfe+Vxtfb0CLOGzn6cL76KatkZt/SDNgZlYCSDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:22:40.147380Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.11368","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d02d097a94bae577ca2c8fd41e7d7ef1df671e08ed80c67c137e0234927501b5","sha256:f446f90b3b2ca4f07de60e342770b471699d8af562edea5c1e9046f757eadd92"],"state_sha256":"fa2d09f2db1ffe0b8582c7e3533128e3cbeaf9bee679be7889d03021e7c2ddaf"}