{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4IIDPVM7PDLSFM7XS2ZL6N7ZSX","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":"a38602cfeda0a95e22522a35d34dc77577ffcaefa53f7fbabd3fd12082c43971","cross_cats_sorted":["cs.CL","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T19:18:16Z","title_canon_sha256":"46f1a94988a0ce7be83bc28d44fa6c03f80cca366070e41b4588719e4a5c2ecc"},"schema_version":"1.0","source":{"id":"2407.00075","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2407.00075","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"arxiv_version","alias_value":"2407.00075v5","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.00075","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_12","alias_value":"4IIDPVM7PDLS","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_16","alias_value":"4IIDPVM7PDLSFM7X","created_at":"2026-07-05T10:21:21Z"},{"alias_kind":"pith_short_8","alias_value":"4IIDPVM7","created_at":"2026-07-05T10:21:21Z"}],"graph_snapshots":[{"event_id":"sha256:470d679283fb36e846330acb5a6f66ce4df7a9d6bf7d74682bdedf45d092cf9d","target":"graph","created_at":"2026-07-05T10:21:21Z","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/2407.00075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We study how to subvert large language models (LLMs) from following prompt-specified rules. We first formalize rule-following as inference in propositional Horn logic, a mathematical system in which rules have the form \"if $P$ and $Q$, then $R$\" for some propositions $P$, $Q$, and $R$. Next, we prove that although small transformers can faithfully follow such rules, maliciously crafted prompts can still mislead both theoretical constructions and models learned from data. Furthermore, we demonstrate that popular attack algorithms on LLMs find adversarial prompts and induce attention patterns th","authors_text":"Anton Xue, Avishree Khare, Eric Wong, Rajeev Alur, Surbhi Goel","cross_cats":["cs.CL","cs.CR","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T19:18:16Z","title":"Logicbreaks: A Framework for Understanding Subversion of Rule-based Inference"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.00075","kind":"arxiv","version":5},"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:f6f3854ff9840accb57f69bec1e9ac046aceb8cf41a44cb3b25d889048a8c826","target":"record","created_at":"2026-07-05T10:21:21Z","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":"a38602cfeda0a95e22522a35d34dc77577ffcaefa53f7fbabd3fd12082c43971","cross_cats_sorted":["cs.CL","cs.CR","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2024-06-21T19:18:16Z","title_canon_sha256":"46f1a94988a0ce7be83bc28d44fa6c03f80cca366070e41b4588719e4a5c2ecc"},"schema_version":"1.0","source":{"id":"2407.00075","kind":"arxiv","version":5}},"canonical_sha256":"e21037d59f78d722b3f796b2bf37f995df8210a267f01587b7b0f4bf6d161165","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e21037d59f78d722b3f796b2bf37f995df8210a267f01587b7b0f4bf6d161165","first_computed_at":"2026-07-05T10:21:21.256337Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T10:21:21.256337Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"i5QQEnN921A03Th9s4mPyuTRQGTaU08aK0BUMFhVcFctxkKPDc0xOuN3vjbdEovAdLXH0g57+482m6MzYpScAg==","signature_status":"signed_v1","signed_at":"2026-07-05T10:21:21.256844Z","signed_message":"canonical_sha256_bytes"},"source_id":"2407.00075","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f6f3854ff9840accb57f69bec1e9ac046aceb8cf41a44cb3b25d889048a8c826","sha256:470d679283fb36e846330acb5a6f66ce4df7a9d6bf7d74682bdedf45d092cf9d"],"state_sha256":"45b7cc873a9245de1357ff1562b8baa5eabcad81525d13e6ad45d73a5858582d"}