{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:LU6PTQBHLZ7PHKUV6SZDFMMIM4","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":"09183dad19e114e968a0c5d78da41270dabaf44ec9a4975d5f24dce9b9b002de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T14:03:08Z","title_canon_sha256":"325de94219a8276f825d6ab2d6a965a88f3cb18aa4f9e4817149ce6a833d5b52"},"schema_version":"1.0","source":{"id":"2308.04265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2308.04265","created_at":"2026-07-05T09:32:39Z"},{"alias_kind":"arxiv_version","alias_value":"2308.04265v2","created_at":"2026-07-05T09:32:39Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2308.04265","created_at":"2026-07-05T09:32:39Z"},{"alias_kind":"pith_short_12","alias_value":"LU6PTQBHLZ7P","created_at":"2026-07-05T09:32:39Z"},{"alias_kind":"pith_short_16","alias_value":"LU6PTQBHLZ7PHKUV","created_at":"2026-07-05T09:32:39Z"},{"alias_kind":"pith_short_8","alias_value":"LU6PTQBH","created_at":"2026-07-05T09:32:39Z"}],"graph_snapshots":[{"event_id":"sha256:f844110ad7a9e6fc267eca332c50a6fe9e236250b720856173c6c4c97ec1327e","target":"graph","created_at":"2026-07-05T09:32:39Z","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/2308.04265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Warning: this paper contains content that may be inappropriate or offensive. As generative models become available for public use in various applications, testing and analyzing vulnerabilities of these models has become a priority. In this work, we propose an automatic red teaming framework that evaluates a given black-box model and exposes its vulnerabilities against unsafe and inappropriate content generation. Our framework uses in-context learning in a feedback loop to red team models and trigger them into unsafe content generation. In particular, taking text-to-image models as target model","authors_text":"Aram Galstyan, Christophe Dupuy, Kai-Wei Chang, Ninareh Mehrabi, Palash Goyal, Qian Hu, Rahul Gupta, Richard Zemel, Shalini Ghosh","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T14:03:08Z","title":"FLIRT: Feedback Loop In-context Red Teaming"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2308.04265","kind":"arxiv","version":2},"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:c8f7f9a2a968acc55d372c43c91f1c52705ab434d020cd6f93a1f4bcdcee9947","target":"record","created_at":"2026-07-05T09:32:39Z","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":"09183dad19e114e968a0c5d78da41270dabaf44ec9a4975d5f24dce9b9b002de","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2023-08-08T14:03:08Z","title_canon_sha256":"325de94219a8276f825d6ab2d6a965a88f3cb18aa4f9e4817149ce6a833d5b52"},"schema_version":"1.0","source":{"id":"2308.04265","kind":"arxiv","version":2}},"canonical_sha256":"5d3cf9c0275e7ef3aa95f4b232b188670816fd3ad9ac104fc7cdfe7749012da8","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5d3cf9c0275e7ef3aa95f4b232b188670816fd3ad9ac104fc7cdfe7749012da8","first_computed_at":"2026-07-05T09:32:39.849732Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:32:39.849732Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x1dtwtC4ZCg8Tcz5mqBmIi4AcZR0ub6Y0ng/soVFoT1LPvhbNtZrTfac6osRxhs0MxNF/OlTENeQpxzZUFyQDg==","signature_status":"signed_v1","signed_at":"2026-07-05T09:32:39.850272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2308.04265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c8f7f9a2a968acc55d372c43c91f1c52705ab434d020cd6f93a1f4bcdcee9947","sha256:f844110ad7a9e6fc267eca332c50a6fe9e236250b720856173c6c4c97ec1327e"],"state_sha256":"35db0dce5a2b6226b008584a35d94d0ac15282071acfedee194cb42babcdfcb9"}