{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:OSJNOZG2B2GXW2D6J46HAMVB5Q","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":"46474d9a05ae9efddb4ebb1dec700f48333f99663dd9d28c41477887ed22ac2d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-12-19T20:19:43Z","title_canon_sha256":"1b05f00e8976c23902841cb6bba74290344182f75cb5a55d7769be7c21c8e8d2"},"schema_version":"1.0","source":{"id":"2312.12575","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2312.12575","created_at":"2026-07-05T08:47:48Z"},{"alias_kind":"arxiv_version","alias_value":"2312.12575v3","created_at":"2026-07-05T08:47:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.12575","created_at":"2026-07-05T08:47:48Z"},{"alias_kind":"pith_short_12","alias_value":"OSJNOZG2B2GX","created_at":"2026-07-05T08:47:48Z"},{"alias_kind":"pith_short_16","alias_value":"OSJNOZG2B2GXW2D6","created_at":"2026-07-05T08:47:48Z"},{"alias_kind":"pith_short_8","alias_value":"OSJNOZG2","created_at":"2026-07-05T08:47:48Z"}],"graph_snapshots":[{"event_id":"sha256:79db5b43fdb7e4b2af30da7468708573e0cc217d63d3c6dbd7607922fdcc60ae","target":"graph","created_at":"2026-07-05T08:47:48Z","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/2312.12575/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models (LLMs) have been suggested for use in automated vulnerability repair, but benchmarks showing they can consistently identify security-related bugs are lacking. We thus develop SecLLMHolmes, a fully automated evaluation framework that performs the most detailed investigation to date on whether LLMs can reliably identify and reason about security-related bugs. We construct a set of 228 code scenarios and analyze eight of the most capable LLMs across eight different investigative dimensions using our framework. Our evaluation shows LLMs provide non-deterministic responses, in","authors_text":"Ayse Coskun, Gianluca Stringhini, Hammond Pearce, Mingji Han, Saad Ullah, Saurabh Pujar","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-12-19T20:19:43Z","title":"LLMs Cannot Reliably Identify and Reason About Security Vulnerabilities (Yet?): A Comprehensive Evaluation, Framework, and Benchmarks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.12575","kind":"arxiv","version":3},"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":"sha256:458835a5d148850c50f1fff6822046fa91e99090bf02b1f8f0d51f9bba81e6d4","target":"record","created_at":"2026-07-05T08:47:48Z","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":"46474d9a05ae9efddb4ebb1dec700f48333f99663dd9d28c41477887ed22ac2d","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CR","submitted_at":"2023-12-19T20:19:43Z","title_canon_sha256":"1b05f00e8976c23902841cb6bba74290344182f75cb5a55d7769be7c21c8e8d2"},"schema_version":"1.0","source":{"id":"2312.12575","kind":"arxiv","version":3}},"canonical_sha256":"7492d764da0e8d7b687e4f3c7032a1ec2474582f68792403db9ea7cc1bf6e932","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7492d764da0e8d7b687e4f3c7032a1ec2474582f68792403db9ea7cc1bf6e932","first_computed_at":"2026-07-05T08:47:48.832037Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:47:48.832037Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"qmsyS1IxMoAkr8oV30euYfd+BEUvRffBVnbMO4uDFCB9fX2kK2PsprQRmLW4O3WXbgFro0fSf6Vg2lT14VBuCg==","signature_status":"signed_v1","signed_at":"2026-07-05T08:47:48.832519Z","signed_message":"canonical_sha256_bytes"},"source_id":"2312.12575","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:458835a5d148850c50f1fff6822046fa91e99090bf02b1f8f0d51f9bba81e6d4","sha256:79db5b43fdb7e4b2af30da7468708573e0cc217d63d3c6dbd7607922fdcc60ae"],"state_sha256":"a1f2d8d55b08614073eb1541a27bc2839389f6b1068a3fdd40aed50909295645"}