{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:2XBZGLH2C4H2CFQXL4SZI4Q3XH","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":"1c147ba145dacfcc93972e94f52c0ec8861635d9904c6d22d562535e83b52b2e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2025-11-16T07:47:31Z","title_canon_sha256":"b30ed043a64b28d74daaea932d6b7cf13d22fa916f8fca6309b7faa89bcd5889"},"schema_version":"1.0","source":{"id":"2511.12487","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2511.12487","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"arxiv_version","alias_value":"2511.12487v2","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2511.12487","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"pith_short_12","alias_value":"2XBZGLH2C4H2","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"pith_short_16","alias_value":"2XBZGLH2C4H2CFQX","created_at":"2026-06-02T03:05:04Z"},{"alias_kind":"pith_short_8","alias_value":"2XBZGLH2","created_at":"2026-06-02T03:05:04Z"}],"graph_snapshots":[{"event_id":"sha256:af3509801eeff98e569d2db060dc57c90124d07171ccaa0bd973a399f7ba4b4c","target":"graph","created_at":"2026-06-02T03:05:04Z","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/2511.12487/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Large Language Models remain vulnerable to adversarial prompts that elicit toxic content even after safety alignment. We present ToxSearch, a black-box evolutionary framework that tests model safety by evolving prompts in a synchronous steady-state loop. The system employs a diverse set of operators, including lexical substitutions, negation, back-translation, paraphrasing, and two semantic crossover operators, while a moderation oracle provides fitness guidance. Operator-level analysis shows heterogeneous behavior: lexical substitutions offer the best yield-variance trade-off, semantic-simila","authors_text":"Onkar Shelar, Travis Desell","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2025-11-16T07:47:31Z","title":"ToxSearch: Evolving Prompts for Toxicity Search in Large Language Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2511.12487","kind":"arxiv","version":2},"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":"sha256:90373ea6a7acce80029a3ca9220fabd88fca27118098cef1c53506271a8495a0","target":"record","created_at":"2026-06-02T03:05:04Z","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":"1c147ba145dacfcc93972e94f52c0ec8861635d9904c6d22d562535e83b52b2e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NE","submitted_at":"2025-11-16T07:47:31Z","title_canon_sha256":"b30ed043a64b28d74daaea932d6b7cf13d22fa916f8fca6309b7faa89bcd5889"},"schema_version":"1.0","source":{"id":"2511.12487","kind":"arxiv","version":2}},"canonical_sha256":"d5c3932cfa170fa116175f2594721bb9fa370ccbd9095157baaaab6f3e6c8ba5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5c3932cfa170fa116175f2594721bb9fa370ccbd9095157baaaab6f3e6c8ba5","first_computed_at":"2026-06-02T03:05:04.328762Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-02T03:05:04.328762Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Djv8vW3iY1xEbtgOoN09RbY4YDY3ZIsid722cpcajesmWI413tD3sBWks4Lourh3MtrbopC0Tdgm4MrUhNnLBQ==","signature_status":"signed_v1","signed_at":"2026-06-02T03:05:04.329249Z","signed_message":"canonical_sha256_bytes"},"source_id":"2511.12487","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:90373ea6a7acce80029a3ca9220fabd88fca27118098cef1c53506271a8495a0","sha256:af3509801eeff98e569d2db060dc57c90124d07171ccaa0bd973a399f7ba4b4c"],"state_sha256":"79e8115431b2a29fb52433dab95372012911f19a5e33074a709c06be2ace6ac2"}