{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:DEDY7WTKLLKERMTHQ3PPIMMWFJ","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":"272ed8c1ad7f63381684889c13d4199512c509670f7fbcb855ce3f60fc6705b8","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T04:18:42Z","title_canon_sha256":"069c2fb54a149384c42ed89d93af31f3f84a100aed6c5ea0e8ec91b205b756a7"},"schema_version":"1.0","source":{"id":"2605.26526","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.26526","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"arxiv_version","alias_value":"2605.26526v1","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.26526","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"pith_short_12","alias_value":"DEDY7WTKLLKE","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"pith_short_16","alias_value":"DEDY7WTKLLKERMTH","created_at":"2026-05-27T01:05:25Z"},{"alias_kind":"pith_short_8","alias_value":"DEDY7WTK","created_at":"2026-05-27T01:05:25Z"}],"graph_snapshots":[{"event_id":"sha256:b7df9e8c2d923967c08cd6eac06f3e5f636de8fcfc06eb7b22cdcb268baf0a22","target":"graph","created_at":"2026-05-27T01:05:25Z","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/2605.26526/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an assumption that new harmful behavior is learned through fine-tuning rather than elicited by jailbreaking the model. Yet, pretrained LLMs already encode substantial harmful knowledge across many domains, which raises an important question: can an adversary jailbreak safeguarded models, to achieve harmful usage without fine-tuning at all? In this paper, we show that open-weight safeguards are susceptible to simpler strategies that, despite being wel","authors_text":"Chhavi Yadav, Kevin Kuo, Virginia Smith","cross_cats":["cs.CR"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T04:18:42Z","title":"Open-Weight LLM Fine-Tuning Defenses are Susceptible to Simple Attacks"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.26526","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:e14194bb2f6a7ce4ec299653da9690e913de6e1545dd423c1db98e3080e3934f","target":"record","created_at":"2026-05-27T01:05:25Z","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":"272ed8c1ad7f63381684889c13d4199512c509670f7fbcb855ce3f60fc6705b8","cross_cats_sorted":["cs.CR"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-05-26T04:18:42Z","title_canon_sha256":"069c2fb54a149384c42ed89d93af31f3f84a100aed6c5ea0e8ec91b205b756a7"},"schema_version":"1.0","source":{"id":"2605.26526","kind":"arxiv","version":1}},"canonical_sha256":"19078fda6a5ad448b26786def431962a4f50cb4c38fcbc35bd1002750067a1f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"19078fda6a5ad448b26786def431962a4f50cb4c38fcbc35bd1002750067a1f6","first_computed_at":"2026-05-27T01:05:25.269535Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-27T01:05:25.269535Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8D0mnCG7Cbj+4+sXPHSjT6jooO/2vOPp5HRiC0lEl9yofx7kuemqfEc702CPPUaz2UtGrYw5WVqY8qXLaO8+Dw==","signature_status":"signed_v1","signed_at":"2026-05-27T01:05:25.270063Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.26526","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e14194bb2f6a7ce4ec299653da9690e913de6e1545dd423c1db98e3080e3934f","sha256:b7df9e8c2d923967c08cd6eac06f3e5f636de8fcfc06eb7b22cdcb268baf0a22"],"state_sha256":"896928a826dae362489ac9196378c7ff3ad96007153ee394de3eee31039b1392"}