{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:CF3MGPTR6X2MBB5CJTP4JBF7DK","short_pith_number":"pith:CF3MGPTR","schema_version":"1.0","canonical_sha256":"1176c33e71f5f4c087a24cdfc484bf1abbce61074a1517233ce7572695b8ff12","source":{"kind":"arxiv","id":"2505.11368","version":2},"attestation_state":"computed","paper":{"title":"GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Lingxiao Diao, Wanxuan Sun, Xinyue Xu, Zhuosheng Zhang","submitted_at":"2025-05-16T15:32:23Z","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"},"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":"2505.11368","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-16T15:32:23Z","cross_cats_sorted":[],"title_canon_sha256":"10decd62bed24b6ac43e863188bf7e318154c9bf0fefcbd664398792c2cb337b","abstract_canon_sha256":"131efcce60e56d69ed486edb655f4e68b9fe62f4b68778309c37c2f3efc42197"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:22:40.147380Z","signature_b64":"TQN535r0tCYqkjWJAD+CzbF8oa0+tN4Wzh6+v5+JnJ+Q3u+rfe+Vxtfb0CLOGzn6cL76KatkZt/SDNgZlYCSDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1176c33e71f5f4c087a24cdfc484bf1abbce61074a1517233ce7572695b8ff12","last_reissued_at":"2026-07-05T11:22:40.146884Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:22:40.146884Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"GuideBench: Benchmarking Domain-Oriented Guideline Following for LLM Agents","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Cheng Yang, Lingxiao Diao, Wanxuan Sun, Xinyue Xu, Zhuosheng Zhang","submitted_at":"2025-05-16T15:32:23Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.11368","kind":"arxiv","version":2},"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/2505.11368/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":"2505.11368","created_at":"2026-07-05T11:22:40.146940+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.11368v2","created_at":"2026-07-05T11:22:40.146940+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.11368","created_at":"2026-07-05T11:22:40.146940+00:00"},{"alias_kind":"pith_short_12","alias_value":"CF3MGPTR6X2M","created_at":"2026-07-05T11:22:40.146940+00:00"},{"alias_kind":"pith_short_16","alias_value":"CF3MGPTR6X2MBB5C","created_at":"2026-07-05T11:22:40.146940+00:00"},{"alias_kind":"pith_short_8","alias_value":"CF3MGPTR","created_at":"2026-07-05T11:22:40.146940+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.09285","citing_title":"SAGE: A Service Agent Graph-guided Evaluation Benchmark","ref_index":9,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK","json":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK.json","graph_json":"https://pith.science/api/pith-number/CF3MGPTR6X2MBB5CJTP4JBF7DK/graph.json","events_json":"https://pith.science/api/pith-number/CF3MGPTR6X2MBB5CJTP4JBF7DK/events.json","paper":"https://pith.science/paper/CF3MGPTR"},"agent_actions":{"view_html":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK","download_json":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK.json","view_paper":"https://pith.science/paper/CF3MGPTR","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.11368&json=true","fetch_graph":"https://pith.science/api/pith-number/CF3MGPTR6X2MBB5CJTP4JBF7DK/graph.json","fetch_events":"https://pith.science/api/pith-number/CF3MGPTR6X2MBB5CJTP4JBF7DK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK/action/storage_attestation","attest_author":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK/action/author_attestation","sign_citation":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK/action/citation_signature","submit_replication":"https://pith.science/pith/CF3MGPTR6X2MBB5CJTP4JBF7DK/action/replication_record"}},"created_at":"2026-07-05T11:22:40.146940+00:00","updated_at":"2026-07-05T11:22:40.146940+00:00"}