{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:QCU3G3IB45MD64HTSTJ5XZ33IA","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":"c6093263fd591c085a46cc6d96739062360ebc7b0f89ad41ee9f66d6e5683f65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-22T11:52:43Z","title_canon_sha256":"2a1ecf4acb5ac7c748528d9d854b27cbb19ecf93f0dc32d16667e21fedecb0eb"},"schema_version":"1.0","source":{"id":"2607.20581","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.20581","created_at":"2026-07-24T00:23:23Z"},{"alias_kind":"arxiv_version","alias_value":"2607.20581v1","created_at":"2026-07-24T00:23:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.20581","created_at":"2026-07-24T00:23:23Z"},{"alias_kind":"pith_short_12","alias_value":"QCU3G3IB45MD","created_at":"2026-07-24T00:23:23Z"},{"alias_kind":"pith_short_16","alias_value":"QCU3G3IB45MD64HT","created_at":"2026-07-24T00:23:23Z"},{"alias_kind":"pith_short_8","alias_value":"QCU3G3IB","created_at":"2026-07-24T00:23:23Z"}],"graph_snapshots":[{"event_id":"sha256:507f124e140d7604db4065eea29eb0258c10b708ad36a078299d2b6d00d6d32c","target":"graph","created_at":"2026-07-24T00:23:23Z","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/2607.20581/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Perturbation techniques that turn unsuccessful jailbreak prompts into successful ones are continuously evolving, constituting a major security threat to LLM safety. In this paper, we investigate the internal representations of such string-level perturbed jailbreak inputs in the small weight models of the Qwen-2.5-1.5B/-3B/-7B-Instruct and Llama-3.2-1B/-3B/-3.1-8B-Instruct families. We select two representation spaces: the last-layer-last-token embedding space and the top-50 next-token probability space. The former space separates prompts based on their spelling and format, while the latter spa","authors_text":"Andres Algaba, Lynn Delcon, Vincent Ginis","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-22T11:52:43Z","title":"Geometric Configurations of Perturbed Jailbreak Prompts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.20581","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":"sha256:04dbbd141116b8c0c683e6aa4d85431a713e24c63e0136a1f74f656226ded9f9","target":"record","created_at":"2026-07-24T00:23:23Z","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":"c6093263fd591c085a46cc6d96739062360ebc7b0f89ad41ee9f66d6e5683f65","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CR","submitted_at":"2026-07-22T11:52:43Z","title_canon_sha256":"2a1ecf4acb5ac7c748528d9d854b27cbb19ecf93f0dc32d16667e21fedecb0eb"},"schema_version":"1.0","source":{"id":"2607.20581","kind":"arxiv","version":1}},"canonical_sha256":"80a9b36d01e7583f70f394d3dbe77b403e33878afc4a3c4ba1c3cce9f3b6bbc3","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"80a9b36d01e7583f70f394d3dbe77b403e33878afc4a3c4ba1c3cce9f3b6bbc3","first_computed_at":"2026-07-24T00:23:23.703933Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-24T00:23:23.703933Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Ori69sa9m/4TcHX3vF6d+JTtq2VAfdqWjmDugug5N4a8QcSFuzP5TsFQ/YAUbpAMIIWFG4b3V+py0hLVzkjRAg==","signature_status":"signed_v1","signed_at":"2026-07-24T00:23:23.704863Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.20581","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04dbbd141116b8c0c683e6aa4d85431a713e24c63e0136a1f74f656226ded9f9","sha256:507f124e140d7604db4065eea29eb0258c10b708ad36a078299d2b6d00d6d32c"],"state_sha256":"70e4e366acf4a116ba5f733d5a802ca8a7b92ea839f7d8c5e18d788ec7258a09"}