{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XE5HXYL2BCVF3TMC254LY7CGOP","short_pith_number":"pith:XE5HXYL2","schema_version":"1.0","canonical_sha256":"b93a7be17a08aa5dcd82d778bc7c4673e5a17cab74e03c687de689e476f19012","source":{"kind":"arxiv","id":"2605.20351","version":1},"attestation_state":"computed","paper":{"title":"Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gregory D. Moody, Richard J. Young","submitted_at":"2026-05-19T18:05:51Z","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.20351","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-19T18:05:51Z","cross_cats_sorted":[],"title_canon_sha256":"819768beda4a1e5a5db50d51caa383c4d72527db074a2f6102eb0fd816c4f34c","abstract_canon_sha256":"0c41a7e8e90953e3b677af4fc7e2ea1650ea5e0d9aaf5d569957fa8c61b0930e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T01:04:34.490186Z","signature_b64":"tZoii3BEG+a0uwLJvQSdkUpbXLT4nCiDXXDhkUtkj6rHlv/EGtK0ztGV7kjLbFso/3OBQM79YkJjQT1Tj+M5BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b93a7be17a08aa5dcd82d778bc7c4673e5a17cab74e03c687de689e476f19012","last_reissued_at":"2026-05-21T01:04:34.489308Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T01:04:34.489308Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Refusal Evaluation in Coding LLMs and Code Agents: A Systematic Review of Thirteen Malicious-Code Prompt Corpora (2023-2025)","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CR","authors_text":"Gregory D. Moody, Richard J. Young","submitted_at":"2026-05-19T18:05:51Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.20351","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.20351/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"references":{"count":0,"sample":[],"resolved_work":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","internal_anchors":0},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.20351","created_at":"2026-05-21T01:04:34.489453+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.20351v1","created_at":"2026-05-21T01:04:34.489453+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.20351","created_at":"2026-05-21T01:04:34.489453+00:00"},{"alias_kind":"pith_short_12","alias_value":"XE5HXYL2BCVF","created_at":"2026-05-21T01:04:34.489453+00:00"},{"alias_kind":"pith_short_16","alias_value":"XE5HXYL2BCVF3TMC","created_at":"2026-05-21T01:04:34.489453+00:00"},{"alias_kind":"pith_short_8","alias_value":"XE5HXYL2","created_at":"2026-05-21T01:04:34.489453+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP","json":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP.json","graph_json":"https://pith.science/api/pith-number/XE5HXYL2BCVF3TMC254LY7CGOP/graph.json","events_json":"https://pith.science/api/pith-number/XE5HXYL2BCVF3TMC254LY7CGOP/events.json","paper":"https://pith.science/paper/XE5HXYL2"},"agent_actions":{"view_html":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP","download_json":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP.json","view_paper":"https://pith.science/paper/XE5HXYL2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.20351&json=true","fetch_graph":"https://pith.science/api/pith-number/XE5HXYL2BCVF3TMC254LY7CGOP/graph.json","fetch_events":"https://pith.science/api/pith-number/XE5HXYL2BCVF3TMC254LY7CGOP/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP/action/storage_attestation","attest_author":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP/action/author_attestation","sign_citation":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP/action/citation_signature","submit_replication":"https://pith.science/pith/XE5HXYL2BCVF3TMC254LY7CGOP/action/replication_record"}},"created_at":"2026-05-21T01:04:34.489453+00:00","updated_at":"2026-05-21T01:04:34.489453+00:00"}