{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:GYN5AJGV3V6SJK5GLDUNOB2CGG","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":"3cf753d307571bff2fbc538664ea8982989baf1c3cf95f4dec2cdeb4bdadfee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-09T10:18:51Z","title_canon_sha256":"b5e0c6e18d710a4f5edea2814668a4c4139bd6a8ef8804c230a05a1f20c8f873"},"schema_version":"1.0","source":{"id":"2604.08059","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.08059","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"arxiv_version","alias_value":"2604.08059v5","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.08059","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_12","alias_value":"GYN5AJGV3V6S","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_16","alias_value":"GYN5AJGV3V6SJK5G","created_at":"2026-05-27T01:04:57Z"},{"alias_kind":"pith_short_8","alias_value":"GYN5AJGV","created_at":"2026-05-27T01:04:57Z"}],"graph_snapshots":[{"event_id":"sha256:cdac2edd2bc8e402fd593a0bc60b74e72c1d628185d27421f75920b246d00045","target":"graph","created_at":"2026-05-27T01:04:57Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"governed upgrade retains comparable success (67.4%) with zero unsafe activations across all rounds (Wilcoxon p=0.003)"},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"The four compatibility checks (interface, policy, behavioral, recovery) are sufficient to detect all unsafe evolutions in the target domain; the PyBullet/ROS 2 testbed with random seeds adequately represents real-world embodied agent upgrade scenarios."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"A governed capability evolution framework with interface, policy, behavioral, and recovery checks reduces unsafe activations to zero in embodied agent upgrades while preserving task success rates."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Governed upgrades keep AI agent success at 67% with zero unsafe cases"}],"snapshot_sha256":"a10296d12d2cadc8943a06719cebe9d3a6f41d1ef29d31f58b10e7d7eaadcbd1"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.08059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Software systems built from versioned AI components increasingly need lifecycle-time governance: when a capability module evolves into a new version, the hosting system must decide whether the new version may be activated safely, under what deployment conditions it should run, how it must be monitored, and when it should be rolled back. Existing software-deployment patterns (canary release, blue-green, feature flags, and MLOps pipelines) address parts of this loop but were designed for stateless web services rather than for stateful, policy-constrained runtimes that drive AI components in the ","authors_text":"Cong Yang, John See, Simin Luan, Xue Qin, Zeyd Boukhers, Zhijun Li","cross_cats":["cs.AI"],"headline":"Governed upgrades keep AI agent success at 67% with zero unsafe cases","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-09T10:18:51Z","title":"Governed Capability Evolution: Lifecycle-Time Compatibility Checking and Rollback for AI-Component-Based Systems, with Embodied Agents as Case Study"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.08059","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-11T00:42:08.629361Z","id":"12a1bc75-6737-423f-bac4-6bffffcf1639","model_set":{"reader":"grok-4.3"},"one_line_summary":"A governed capability evolution framework with interface, policy, behavioral, and recovery checks reduces unsafe activations to zero in embodied agent upgrades while preserving task success rates.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"Governed upgrades keep AI agent success at 67% with zero unsafe cases","strongest_claim":"governed upgrade retains comparable success (67.4%) with zero unsafe activations across all rounds (Wilcoxon p=0.003)","weakest_assumption":"The four compatibility checks (interface, policy, behavioral, recovery) are sufficient to detect all unsafe evolutions in the target domain; the PyBullet/ROS 2 testbed with random seeds adequately represents real-world embodied agent upgrade scenarios."}},"verdict_id":"12a1bc75-6737-423f-bac4-6bffffcf1639"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:d2fa98b3b367a644d241bfabdee07c90dd1c5b6099aade1c0c496da2573eca9b","target":"record","created_at":"2026-05-27T01:04:57Z","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":"3cf753d307571bff2fbc538664ea8982989baf1c3cf95f4dec2cdeb4bdadfee0","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.RO","submitted_at":"2026-04-09T10:18:51Z","title_canon_sha256":"b5e0c6e18d710a4f5edea2814668a4c4139bd6a8ef8804c230a05a1f20c8f873"},"schema_version":"1.0","source":{"id":"2604.08059","kind":"arxiv","version":5}},"canonical_sha256":"361bd024d5dd7d24aba658e8d707423182feee983043559c302a7ec938b71911","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"361bd024d5dd7d24aba658e8d707423182feee983043559c302a7ec938b71911","first_computed_at":"2026-05-27T01:04:57.863088Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:04:57.863088Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"rIoI0gnrU6pwhPmy+v1qlJBJTviSr9+YeQTBOt46RStmx6iqCUqI4vtImotZ1kVnaN2r9LDS3NB9PEqpFg8QDA==","signature_status":"signed_v1","signed_at":"2026-05-27T01:04:57.863760Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.08059","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d2fa98b3b367a644d241bfabdee07c90dd1c5b6099aade1c0c496da2573eca9b","sha256:cdac2edd2bc8e402fd593a0bc60b74e72c1d628185d27421f75920b246d00045"],"state_sha256":"ab3c5ac73f4226a5b7070e46d704a8ac0e4ad6c4579103031069d0ae68de9284"}