{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:I2PMJS3IYJLMOXWJ6PIQ7YFYJJ","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":"30c1182357c09872da51e4edd9a09e8a732b7e5a7e32b11cbbb938983ba2a9fa","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T19:33:58Z","title_canon_sha256":"9cdc472148ed7056ebd03073eda2ac49e72646c486c1a8906e8d11fac60c0dc2"},"schema_version":"1.0","source":{"id":"2606.07805","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.07805","created_at":"2026-06-09T01:04:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.07805v1","created_at":"2026-06-09T01:04:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.07805","created_at":"2026-06-09T01:04:52Z"},{"alias_kind":"pith_short_12","alias_value":"I2PMJS3IYJLM","created_at":"2026-06-09T01:04:52Z"},{"alias_kind":"pith_short_16","alias_value":"I2PMJS3IYJLMOXWJ","created_at":"2026-06-09T01:04:52Z"},{"alias_kind":"pith_short_8","alias_value":"I2PMJS3I","created_at":"2026-06-09T01:04:52Z"}],"graph_snapshots":[{"event_id":"sha256:bc0c315be54dc8d79c3e1dc30bd21389360ed21b3b432c198e8fe00bf5d24d01","target":"graph","created_at":"2026-06-09T01:04:52Z","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/2606.07805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid evolution of Large Language Models (LLMs) from passive assistants to autonomous, execution-capable agents has introduced critical operational risks. Most current evaluation frameworks neglect procedural compliance, leading to ''Machiavellian'' behaviors where agents strategically violate safety rules to maximize rewards - a direct manifestation of Goodhart's Law. To address this blind spot, we introduce MAC-Bench, a dynamic, adversarial benchmark designed to evaluate the procedural alignment of multi-agent systems under realistic pressure. We propose the SERV(Seed - Evolve - Refine -","authors_text":"Lizhen Qu, Qingxuan Le, Yiyang Zhao, Zenglin Xu, Zhuo Zhang","cross_cats":["cs.MA"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T19:33:58Z","title":"Beyond Goodhart's Law: A Dynamic Benchmark for Evaluating Compliance in Multi-Agent Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.07805","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":"sha256:76def5b8acc8e9efcec2d2142ef6f2edeafdaad53921853d0cf00f5d0277c3c2","target":"record","created_at":"2026-06-09T01:04:52Z","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":"30c1182357c09872da51e4edd9a09e8a732b7e5a7e32b11cbbb938983ba2a9fa","cross_cats_sorted":["cs.MA"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2026-06-05T19:33:58Z","title_canon_sha256":"9cdc472148ed7056ebd03073eda2ac49e72646c486c1a8906e8d11fac60c0dc2"},"schema_version":"1.0","source":{"id":"2606.07805","kind":"arxiv","version":1}},"canonical_sha256":"469ec4cb68c256c75ec9f3d10fe0b84a570db94295868c65560b6e9394c411e1","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"469ec4cb68c256c75ec9f3d10fe0b84a570db94295868c65560b6e9394c411e1","first_computed_at":"2026-06-09T01:04:52.660892Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-09T01:04:52.660892Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vBp1eu31+bZZtGjFM52a4hiHmHmn52dEJUlqn6LzYFcMmMNJixBiYA/PxHFoW6b81Nm6KSoeR7vT+MxnGQGTDQ==","signature_status":"signed_v1","signed_at":"2026-06-09T01:04:52.661282Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.07805","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:76def5b8acc8e9efcec2d2142ef6f2edeafdaad53921853d0cf00f5d0277c3c2","sha256:bc0c315be54dc8d79c3e1dc30bd21389360ed21b3b432c198e8fe00bf5d24d01"],"state_sha256":"98cb901038f2e07cb3795d8ff85c1f7c357a0eee4e869d0dc6c7bf96ad18cb42"}