{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:XZY4ZXL3XZ2D2LICCL4JKYQFZE","short_pith_number":"pith:XZY4ZXL3","schema_version":"1.0","canonical_sha256":"be71ccdd7bbe743d2d0212f8956205c917e64bd2b553330318ae754b2634ae0a","source":{"kind":"arxiv","id":"2605.02958","version":2},"attestation_state":"computed","paper":{"title":"Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Refusal in language models follows a persistent upstream trajectory that remains detectable even when attacks suppress the final output.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Che Wang, Jianbo Gao, Wei Yang Bryan Lim, Xulin Hu, Zhong Chen","submitted_at":"2026-05-02T14:56:37Z","abstract_excerpt":"Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusal is constructed across layer-token positions. Using causal tracing, we identify a \\textit{Refusal Trajectory}: a sparse upstream activation pattern that often persists even when attacks such as GCG suppress terminal refusal signals. Based on this observation, we propose SALO (Sparse Activation Localization Operator), a lightweight white-box detector that operates on raw hidden-state volumes from a selected layer win"},"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":"2605.02958","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-05-02T14:56:37Z","cross_cats_sorted":["cs.AI","cs.CL","cs.LG"],"title_canon_sha256":"7a717b3cf54a281cb8222adc6d592e0a68a6c5804b8f43693ec264675e837ec2","abstract_canon_sha256":"cf1283eaae0d3c3f8260207ad798c8cb1550b8dc42bd189aacf550e82cc713e6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:05:20.996373Z","signature_b64":"VHr4mqMrWRtokhaZiSpkB1gIf1/OrdvRAK7O2uu0L6Vp3efD9LxZPV5nmWgZ9QO3iHItgWZ69dTOoAeMO7g3Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"be71ccdd7bbe743d2d0212f8956205c917e64bd2b553330318ae754b2634ae0a","last_reissued_at":"2026-05-27T02:05:20.995842Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:05:20.995842Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Tracing the Dynamics of Refusal: Exploiting Latent Refusal Trajectories for Robust Jailbreak Detection","license":"http://creativecommons.org/licenses/by/4.0/","headline":"Refusal in language models follows a persistent upstream trajectory that remains detectable even when attacks suppress the final output.","cross_cats":["cs.AI","cs.CL","cs.LG"],"primary_cat":"cs.CR","authors_text":"Che Wang, Jianbo Gao, Wei Yang Bryan Lim, Xulin Hu, Zhong Chen","submitted_at":"2026-05-02T14:56:37Z","abstract_excerpt":"Representation Engineering analyses often characterize refusal using static directions extracted from terminal or pooled representations. We ask whether this view misses how refusal is constructed across layer-token positions. Using causal tracing, we identify a \\textit{Refusal Trajectory}: a sparse upstream activation pattern that often persists even when attacks such as GCG suppress terminal refusal signals. Based on this observation, we propose SALO (Sparse Activation Localization Operator), a lightweight white-box detector that operates on raw hidden-state volumes from a selected layer win"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"SALO effectively recovers defense capabilities against forced-decoding attacks, improving detection rates from ~0% to >90% where methods relying on terminal states perform poorly.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the refusal trajectory uncovered by causal tracing is a stable, generalizable signature rather than an artifact of the specific models, prompts, or attack implementations tested.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"Refusal in LLMs leaves a detectable upstream trajectory that SALO exploits to raise jailbreak detection from near zero to over 90 percent even under forced-decoding attacks.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Refusal in language models follows a persistent upstream trajectory that remains detectable even when attacks suppress the final output.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"98f8241d2d7d8505d4472f6174cf11b249fde10448a9087056e960d42b906000"},"source":{"id":"2605.02958","kind":"arxiv","version":2},"verdict":{"id":"6cc86458-824d-4c8e-a196-1b6d49eba5b7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-09T14:08:46.459279Z","strongest_claim":"SALO effectively recovers defense capabilities against forced-decoding attacks, improving detection rates from ~0% to >90% where methods relying on terminal states perform poorly.","one_line_summary":"Refusal in LLMs leaves a detectable upstream trajectory that SALO exploits to raise jailbreak detection from near zero to over 90 percent even under forced-decoding attacks.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the refusal trajectory uncovered by causal tracing is a stable, generalizable signature rather than an artifact of the specific models, prompts, or attack implementations tested.","pith_extraction_headline":"Refusal in language models follows a persistent upstream trajectory that remains detectable even when attacks suppress the final output."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2605.02958/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-20T17:41:08.913207Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"doi_compliance","ran_at":"2026-05-19T17:16:24.573853Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"75ce4b50a859a889d1999293782c18672c4f12c631159e8e7cd1f0e05517dd4d"},"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":"2605.02958","created_at":"2026-05-27T02:05:20.995910+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.02958v2","created_at":"2026-05-27T02:05:20.995910+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.02958","created_at":"2026-05-27T02:05:20.995910+00:00"},{"alias_kind":"pith_short_12","alias_value":"XZY4ZXL3XZ2D","created_at":"2026-05-27T02:05:20.995910+00:00"},{"alias_kind":"pith_short_16","alias_value":"XZY4ZXL3XZ2D2LIC","created_at":"2026-05-27T02:05:20.995910+00:00"},{"alias_kind":"pith_short_8","alias_value":"XZY4ZXL3","created_at":"2026-05-27T02:05:20.995910+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/XZY4ZXL3XZ2D2LICCL4JKYQFZE","json":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE.json","graph_json":"https://pith.science/api/pith-number/XZY4ZXL3XZ2D2LICCL4JKYQFZE/graph.json","events_json":"https://pith.science/api/pith-number/XZY4ZXL3XZ2D2LICCL4JKYQFZE/events.json","paper":"https://pith.science/paper/XZY4ZXL3"},"agent_actions":{"view_html":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE","download_json":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE.json","view_paper":"https://pith.science/paper/XZY4ZXL3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.02958&json=true","fetch_graph":"https://pith.science/api/pith-number/XZY4ZXL3XZ2D2LICCL4JKYQFZE/graph.json","fetch_events":"https://pith.science/api/pith-number/XZY4ZXL3XZ2D2LICCL4JKYQFZE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE/action/storage_attestation","attest_author":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE/action/author_attestation","sign_citation":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE/action/citation_signature","submit_replication":"https://pith.science/pith/XZY4ZXL3XZ2D2LICCL4JKYQFZE/action/replication_record"}},"created_at":"2026-05-27T02:05:20.995910+00:00","updated_at":"2026-05-27T02:05:20.995910+00:00"}