{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:XE5HXYL2BCVF3TMC254LY7CGOP","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":"0c41a7e8e90953e3b677af4fc7e2ea1650ea5e0d9aaf5d569957fa8c61b0930e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-19T18:05:51Z","title_canon_sha256":"819768beda4a1e5a5db50d51caa383c4d72527db074a2f6102eb0fd816c4f34c"},"schema_version":"1.0","source":{"id":"2605.20351","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.20351","created_at":"2026-05-21T01:04:34Z"},{"alias_kind":"arxiv_version","alias_value":"2605.20351v1","created_at":"2026-05-21T01:04:34Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20351","created_at":"2026-05-21T01:04:34Z"},{"alias_kind":"pith_short_12","alias_value":"XE5HXYL2BCVF","created_at":"2026-05-21T01:04:34Z"},{"alias_kind":"pith_short_16","alias_value":"XE5HXYL2BCVF3TMC","created_at":"2026-05-21T01:04:34Z"},{"alias_kind":"pith_short_8","alias_value":"XE5HXYL2","created_at":"2026-05-21T01:04:34Z"}],"graph_snapshots":[{"event_id":"sha256:855bb3dbcbae8729c1d4491364349b314a1a2c2498bf76880811b4b36eab47f3","target":"graph","created_at":"2026-05-21T01:04:34Z","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/2605.20351/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The evaluation of large language model refusal on malicious-coding tasks now spans at least thirteen publicly released prompt corpora (AdvBench, the CyberSecEval family, RMCBench, RedCode, MCGMark, JailbreakBench, CySecBench, MalwareBench, CIRCLE, MOCHA, ASTRA, Scam2Prompt / Innoc2Scam-bench, and JAWS-Bench), each constructed under a different protocol, released under different licensing terms, and validated (or not) against different inter-rater reliability standards. Existing surveys treat code security, jailbreak taxonomy, or vulnerability detection as the central object and mention these c","authors_text":"Gregory D. Moody, Richard J. Young","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-19T18:05:51Z","title":"Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20351","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:ca65e04094bc4511bdcaae795ad721de24fc7e8efb9ec55faa7ce95123843a59","target":"record","created_at":"2026-05-21T01:04:34Z","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":"0c41a7e8e90953e3b677af4fc7e2ea1650ea5e0d9aaf5d569957fa8c61b0930e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-19T18:05:51Z","title_canon_sha256":"819768beda4a1e5a5db50d51caa383c4d72527db074a2f6102eb0fd816c4f34c"},"schema_version":"1.0","source":{"id":"2605.20351","kind":"arxiv","version":1}},"canonical_sha256":"b93a7be17a08aa5dcd82d778bc7c4673e5a17cab74e03c687de689e476f19012","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"b93a7be17a08aa5dcd82d778bc7c4673e5a17cab74e03c687de689e476f19012","first_computed_at":"2026-05-21T01:04:34.489308Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-21T01:04:34.489308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tZoii3BEG+a0uwLJvQSdkUpbXLT4nCiDXXDhkUtkj6rHlv/EGtK0ztGV7kjLbFso/3OBQM79YkJjQT1Tj+M5BQ==","signature_status":"signed_v1","signed_at":"2026-05-21T01:04:34.490186Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.20351","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ca65e04094bc4511bdcaae795ad721de24fc7e8efb9ec55faa7ce95123843a59","sha256:855bb3dbcbae8729c1d4491364349b314a1a2c2498bf76880811b4b36eab47f3"],"state_sha256":"1bc606042ed04e255c92fa43e7ea4fd5d1c396d58f1e2def768ca3c3841cd20b"}