{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:ZK2C3OOBLLMWCX36LBAIXA5GIE","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":"c78fd9f570fd8a143038f7baae5ba76a1a3f2c8fc85cd8ab5dcc071634ab0bda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T13:00:53Z","title_canon_sha256":"54de1c70de0ae09ea1ef5abc9312dcb149c7817f0aa2fc1093b9454e79c349e7"},"schema_version":"1.0","source":{"id":"2508.15526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2508.15526","created_at":"2026-07-05T11:57:13Z"},{"alias_kind":"arxiv_version","alias_value":"2508.15526v1","created_at":"2026-07-05T11:57:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.15526","created_at":"2026-07-05T11:57:13Z"},{"alias_kind":"pith_short_12","alias_value":"ZK2C3OOBLLMW","created_at":"2026-07-05T11:57:13Z"},{"alias_kind":"pith_short_16","alias_value":"ZK2C3OOBLLMWCX36","created_at":"2026-07-05T11:57:13Z"},{"alias_kind":"pith_short_8","alias_value":"ZK2C3OOB","created_at":"2026-07-05T11:57:13Z"}],"graph_snapshots":[{"event_id":"sha256:63c1e2d8bc02062afc20d8f296527279585e33aaabc8d84f75bdfb21429b1760","target":"graph","created_at":"2026-07-05T11:57:13Z","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/2508.15526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The rapid proliferation of large language models (LLMs) has intensified the requirement for reliable safety evaluation to uncover model vulnerabilities. To this end, numerous LLM safety evaluation benchmarks are proposed. However, existing benchmarks generally rely on labor-intensive manual curation, which causes excessive time and resource consumption. They also exhibit significant redundancy and limited difficulty. To alleviate these problems, we introduce SafetyFlow, the first agent-flow system designed to automate the construction of LLM safety benchmarks. SafetyFlow can automatically buil","authors_text":"Chunyi Li, Guangtao Zhai, Kaiwei Zhang, Wei Sun, Xiangyang Zhu, Yuan Tian","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T13:00:53Z","title":"SafetyFlow: An Agent-Flow System for Automated LLM Safety Benchmarking"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.15526","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":"sha256:54ed63b2d8456278825a48a3f6c473d821e984ddb9bb722b1f00f47ed3de0d8c","target":"record","created_at":"2026-07-05T11:57:13Z","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":"c78fd9f570fd8a143038f7baae5ba76a1a3f2c8fc85cd8ab5dcc071634ab0bda","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-08-21T13:00:53Z","title_canon_sha256":"54de1c70de0ae09ea1ef5abc9312dcb149c7817f0aa2fc1093b9454e79c349e7"},"schema_version":"1.0","source":{"id":"2508.15526","kind":"arxiv","version":1}},"canonical_sha256":"cab42db9c15ad9615f7e58408b83a6412708344d7579ad594d6900fbb6c6b87b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"cab42db9c15ad9615f7e58408b83a6412708344d7579ad594d6900fbb6c6b87b","first_computed_at":"2026-07-05T11:57:13.963727Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:57:13.963727Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WubX8pJkpoYPt/zUGprrqV78qrOphTDgFtUjND6rvriutvNAZGqkjUEVESnpWc/7wv28VDECVs8PxmQTxscIDA==","signature_status":"signed_v1","signed_at":"2026-07-05T11:57:13.964212Z","signed_message":"canonical_sha256_bytes"},"source_id":"2508.15526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:54ed63b2d8456278825a48a3f6c473d821e984ddb9bb722b1f00f47ed3de0d8c","sha256:63c1e2d8bc02062afc20d8f296527279585e33aaabc8d84f75bdfb21429b1760"],"state_sha256":"b0999401345140bb7054a6b3f0d54d7ec823724f2c5d44f138830e35ac9af6dc"}