{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:4PB5LOYAEKXOWAF24JTEJMH5HO","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":"c07df44865cd7813f77b0af8bb1ae082191ca6609f948a9d77cdb9a5765ec3df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T01:19:25Z","title_canon_sha256":"a397ae88039a0c847d323642fbed796b658278d3c27d056bf520916e957d8488"},"schema_version":"1.0","source":{"id":"2401.16656","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2401.16656","created_at":"2026-07-05T07:38:58Z"},{"alias_kind":"arxiv_version","alias_value":"2401.16656v1","created_at":"2026-07-05T07:38:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2401.16656","created_at":"2026-07-05T07:38:58Z"},{"alias_kind":"pith_short_12","alias_value":"4PB5LOYAEKXO","created_at":"2026-07-05T07:38:58Z"},{"alias_kind":"pith_short_16","alias_value":"4PB5LOYAEKXOWAF2","created_at":"2026-07-05T07:38:58Z"},{"alias_kind":"pith_short_8","alias_value":"4PB5LOYA","created_at":"2026-07-05T07:38:58Z"}],"graph_snapshots":[{"event_id":"sha256:84058775d27740f7ca18010fb76ea86329b48d7371dafccaeda698cbdab87ea0","target":"graph","created_at":"2026-07-05T07:38:58Z","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/2401.16656/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Red teaming is a common strategy for identifying weaknesses in generative language models (LMs), where adversarial prompts are produced that trigger an LM to generate unsafe responses. Red teaming is instrumental for both model alignment and evaluation, but is labor-intensive and difficult to scale when done by humans. In this paper, we present Gradient-Based Red Teaming (GBRT), a red teaming method for automatically generating diverse prompts that are likely to cause an LM to output unsafe responses. GBRT is a form of prompt learning, trained by scoring an LM response with a safety classifier","authors_text":"Ahmad Beirami, Carson Denison, Nevan Wichers","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T01:19:25Z","title":"Gradient-Based Language Model Red Teaming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2401.16656","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:ea473a8cfd05bf3a343dbcf16543199dd2c7738ddf7cc0f22e7ddd57d8a86ce9","target":"record","created_at":"2026-07-05T07:38:58Z","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":"c07df44865cd7813f77b0af8bb1ae082191ca6609f948a9d77cdb9a5765ec3df","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-01-30T01:19:25Z","title_canon_sha256":"a397ae88039a0c847d323642fbed796b658278d3c27d056bf520916e957d8488"},"schema_version":"1.0","source":{"id":"2401.16656","kind":"arxiv","version":1}},"canonical_sha256":"e3c3d5bb0022aeeb00bae26644b0fd3b9b21994dbe89245b5566c43f2eacea0b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e3c3d5bb0022aeeb00bae26644b0fd3b9b21994dbe89245b5566c43f2eacea0b","first_computed_at":"2026-07-05T07:38:58.336228Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:38:58.336228Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"2BLgnxV6SkxiHN7liHOL4IRtLGU3RcSRLRWHlGLTqTB2+rorcxxekRo9exN/tWZGTtVnJlr1Pha9a12NWvrEAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T07:38:58.336663Z","signed_message":"canonical_sha256_bytes"},"source_id":"2401.16656","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ea473a8cfd05bf3a343dbcf16543199dd2c7738ddf7cc0f22e7ddd57d8a86ce9","sha256:84058775d27740f7ca18010fb76ea86329b48d7371dafccaeda698cbdab87ea0"],"state_sha256":"30a21750be094d891805804fd53dbada57883fc55d9269a92adcaf9957a73ba5"}