{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:7G453NL66CC5RKK7K7S4RKJKX7","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":"9bf0662f14643357f50865e5eda9a8573e822b076337d7a1b8f38f4bc9834bd9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-13T17:51:57Z","title_canon_sha256":"91cb122b14b572504678014cee1de4f35170b8224b19580841e9656a7d348deb"},"schema_version":"1.0","source":{"id":"2411.08813","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2411.08813","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"arxiv_version","alias_value":"2411.08813v1","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2411.08813","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"pith_short_12","alias_value":"7G453NL66CC5","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"pith_short_16","alias_value":"7G453NL66CC5RKK7","created_at":"2026-07-05T09:35:02Z"},{"alias_kind":"pith_short_8","alias_value":"7G453NL6","created_at":"2026-07-05T09:35:02Z"}],"graph_snapshots":[{"event_id":"sha256:7ab3b141f2dc0c7803d2c6be24ad54e63d4508a58cf4a393fa365d79ab53ee0c","target":"graph","created_at":"2026-07-05T09:35:02Z","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/2411.08813/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"A key development in the cybersecurity evaluations space is the work carried out by Meta, through their CyberSecEval approach. While this work is undoubtedly a useful contribution to a nascent field, there are notable features that limit its utility. Key drawbacks focus on the insecure code detection part of Meta's methodology. We explore these limitations, and use our exploration as a test case for LLM-assisted benchmark analysis.","authors_text":"Jacob Haimes, Jaime Raldua Veuthey, Suhas Hariharan, Zainab Ali Majid","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-13T17:51:57Z","title":"Rethinking CyberSecEval: An LLM-Aided Approach to Evaluation Critique"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2411.08813","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:ed9aa7ef85175f73620b65860e9f4ac78b97f8e366ff9c8fb7cb0262f6cf5155","target":"record","created_at":"2026-07-05T09:35:02Z","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":"9bf0662f14643357f50865e5eda9a8573e822b076337d7a1b8f38f4bc9834bd9","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.AI","submitted_at":"2024-11-13T17:51:57Z","title_canon_sha256":"91cb122b14b572504678014cee1de4f35170b8224b19580841e9656a7d348deb"},"schema_version":"1.0","source":{"id":"2411.08813","kind":"arxiv","version":1}},"canonical_sha256":"f9b9ddb57ef085d8a95f57e5c8a92abff5b9b4762d49d6cffbdaba3fd5e4e2dd","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f9b9ddb57ef085d8a95f57e5c8a92abff5b9b4762d49d6cffbdaba3fd5e4e2dd","first_computed_at":"2026-07-05T09:35:02.868461Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:35:02.868461Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xjOLQptldWFZ9TUj4Ojb5d+VSS+PN+/0bqd78yghxiiG6huGMhVjkq/EEDXShNLRPl8h1eF4jGTSP/GjNtEnBg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:35:02.868971Z","signed_message":"canonical_sha256_bytes"},"source_id":"2411.08813","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ed9aa7ef85175f73620b65860e9f4ac78b97f8e366ff9c8fb7cb0262f6cf5155","sha256:7ab3b141f2dc0c7803d2c6be24ad54e63d4508a58cf4a393fa365d79ab53ee0c"],"state_sha256":"82109352963f5beae078ce7be69b5e89419f5a887f8f03e8159a5fd50ea17bc9"}