{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:RUGDIMKMFSFO4GV7EEMGPPIAGB","short_pith_number":"pith:RUGDIMKM","canonical_record":{"source":{"id":"2402.12100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T12:31:56Z","cross_cats_sorted":["cs.AI","cs.CR","cs.SE"],"title_canon_sha256":"9e073cd9c64ddfe59b83abe6702d66880f81c43b632041c0ded7e7bc3b33c96b","abstract_canon_sha256":"bd03235f8a6955fe532287ca8f52128922a82a7c5d707d86181cf1722802e072"},"schema_version":"1.0"},"canonical_sha256":"8d0c34314c2c8aee1abf211867bd00306b4f96a982ff0287418ecedc42ebdc03","source":{"kind":"arxiv","id":"2402.12100","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12100","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12100v1","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12100","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"pith_short_12","alias_value":"RUGDIMKMFSFO","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"pith_short_16","alias_value":"RUGDIMKMFSFO4GV7","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"pith_short_8","alias_value":"RUGDIMKM","created_at":"2026-07-05T07:46:48Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:RUGDIMKMFSFO4GV7EEMGPPIAGB","target":"record","payload":{"canonical_record":{"source":{"id":"2402.12100","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T12:31:56Z","cross_cats_sorted":["cs.AI","cs.CR","cs.SE"],"title_canon_sha256":"9e073cd9c64ddfe59b83abe6702d66880f81c43b632041c0ded7e7bc3b33c96b","abstract_canon_sha256":"bd03235f8a6955fe532287ca8f52128922a82a7c5d707d86181cf1722802e072"},"schema_version":"1.0"},"canonical_sha256":"8d0c34314c2c8aee1abf211867bd00306b4f96a982ff0287418ecedc42ebdc03","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:46:48.685261Z","signature_b64":"SAnkC9Hm/o1kglDLT0AKlOeDPCRhH6Sx/KYB6iIpUpcitBnVsLsbBfImRQyk1k/XO7zrNlh8H1dZ0r2zssZyCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8d0c34314c2c8aee1abf211867bd00306b4f96a982ff0287418ecedc42ebdc03","last_reissued_at":"2026-07-05T07:46:48.684747Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:46:48.684747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2402.12100","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:46:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/gfpEkZ+eaDr3nUJCRD9KFR4v4OEurWK/VhmLzGPkE6TLkOAPQdooLqT9sOfRw4tOXV6yVvvAbkwDevulk2OCQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:25:06.755014Z"},"content_sha256":"6824ebd340b75cff75aced07d4e829dbd2ec01fb9241f92749bb6f0320c7b9e0","schema_version":"1.0","event_id":"sha256:6824ebd340b75cff75aced07d4e829dbd2ec01fb9241f92749bb6f0320c7b9e0"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:RUGDIMKMFSFO4GV7EEMGPPIAGB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.CR","cs.SE"],"primary_cat":"cs.CL","authors_text":"Feiyue Chen, Gelei Deng, Guowei Yang, Ling Shi, Tianwei Zhang, Yang Liu, Yi Liu, Yuqi Chen","submitted_at":"2024-02-19T12:31:56Z","abstract_excerpt":"With the prevalence of text-to-image generative models, their safety becomes a critical concern. adversarial testing techniques have been developed to probe whether such models can be prompted to produce Not-Safe-For-Work (NSFW) content. However, existing solutions face several challenges, including low success rate and inefficiency. We introduce Groot, the first automated framework leveraging tree-based semantic transformation for adversarial testing of text-to-image models. Groot employs semantic decomposition and sensitive element drowning strategies in conjunction with LLMs to systematical"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12100","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2402.12100/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T07:46:48Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aMnZbyWcgY1L9Vu5dNfyeRrueGzGr8QdTuJsCJB/1npplZe2jz6qc/bhLdKqNVZivwv3zZxL1y/qF8xGX0trAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-13T16:25:06.755553Z"},"content_sha256":"918304a979f9623b3e64594e900c2c023d1047c2f05158f7a68264b01d924ed7","schema_version":"1.0","event_id":"sha256:918304a979f9623b3e64594e900c2c023d1047c2f05158f7a68264b01d924ed7"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/RUGDIMKMFSFO4GV7EEMGPPIAGB/bundle.json","state_url":"https://pith.science/pith/RUGDIMKMFSFO4GV7EEMGPPIAGB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/RUGDIMKMFSFO4GV7EEMGPPIAGB/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-13T16:25:06Z","links":{"resolver":"https://pith.science/pith/RUGDIMKMFSFO4GV7EEMGPPIAGB","bundle":"https://pith.science/pith/RUGDIMKMFSFO4GV7EEMGPPIAGB/bundle.json","state":"https://pith.science/pith/RUGDIMKMFSFO4GV7EEMGPPIAGB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/RUGDIMKMFSFO4GV7EEMGPPIAGB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:RUGDIMKMFSFO4GV7EEMGPPIAGB","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":"bd03235f8a6955fe532287ca8f52128922a82a7c5d707d86181cf1722802e072","cross_cats_sorted":["cs.AI","cs.CR","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T12:31:56Z","title_canon_sha256":"9e073cd9c64ddfe59b83abe6702d66880f81c43b632041c0ded7e7bc3b33c96b"},"schema_version":"1.0","source":{"id":"2402.12100","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2402.12100","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"arxiv_version","alias_value":"2402.12100v1","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.12100","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"pith_short_12","alias_value":"RUGDIMKMFSFO","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"pith_short_16","alias_value":"RUGDIMKMFSFO4GV7","created_at":"2026-07-05T07:46:48Z"},{"alias_kind":"pith_short_8","alias_value":"RUGDIMKM","created_at":"2026-07-05T07:46:48Z"}],"graph_snapshots":[{"event_id":"sha256:918304a979f9623b3e64594e900c2c023d1047c2f05158f7a68264b01d924ed7","target":"graph","created_at":"2026-07-05T07:46:48Z","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/2402.12100/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"With the prevalence of text-to-image generative models, their safety becomes a critical concern. adversarial testing techniques have been developed to probe whether such models can be prompted to produce Not-Safe-For-Work (NSFW) content. However, existing solutions face several challenges, including low success rate and inefficiency. We introduce Groot, the first automated framework leveraging tree-based semantic transformation for adversarial testing of text-to-image models. Groot employs semantic decomposition and sensitive element drowning strategies in conjunction with LLMs to systematical","authors_text":"Feiyue Chen, Gelei Deng, Guowei Yang, Ling Shi, Tianwei Zhang, Yang Liu, Yi Liu, Yuqi Chen","cross_cats":["cs.AI","cs.CR","cs.SE"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T12:31:56Z","title":"Groot: Adversarial Testing for Generative Text-to-Image Models with Tree-based Semantic Transformation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.12100","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":"sha256:6824ebd340b75cff75aced07d4e829dbd2ec01fb9241f92749bb6f0320c7b9e0","target":"record","created_at":"2026-07-05T07:46:48Z","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":"bd03235f8a6955fe532287ca8f52128922a82a7c5d707d86181cf1722802e072","cross_cats_sorted":["cs.AI","cs.CR","cs.SE"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-02-19T12:31:56Z","title_canon_sha256":"9e073cd9c64ddfe59b83abe6702d66880f81c43b632041c0ded7e7bc3b33c96b"},"schema_version":"1.0","source":{"id":"2402.12100","kind":"arxiv","version":1}},"canonical_sha256":"8d0c34314c2c8aee1abf211867bd00306b4f96a982ff0287418ecedc42ebdc03","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8d0c34314c2c8aee1abf211867bd00306b4f96a982ff0287418ecedc42ebdc03","first_computed_at":"2026-07-05T07:46:48.684747Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T07:46:48.684747Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"SAnkC9Hm/o1kglDLT0AKlOeDPCRhH6Sx/KYB6iIpUpcitBnVsLsbBfImRQyk1k/XO7zrNlh8H1dZ0r2zssZyCA==","signature_status":"signed_v1","signed_at":"2026-07-05T07:46:48.685261Z","signed_message":"canonical_sha256_bytes"},"source_id":"2402.12100","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6824ebd340b75cff75aced07d4e829dbd2ec01fb9241f92749bb6f0320c7b9e0","sha256:918304a979f9623b3e64594e900c2c023d1047c2f05158f7a68264b01d924ed7"],"state_sha256":"829405298c9b339e05f6a526b659ef2b82bec59b63e88a60ad581cf899b0610c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yXyxwtbRvgeKRC9wN3OcF17ZLnaIiM7BDX1+jF334F4yRNUWbjGEJ5AK3zu/x/B9Hgse+hb0QRnyoNb7K5sJDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-13T16:25:06.761399Z","bundle_sha256":"1d330dbd5cab46a9694119c6be7748cdaff83acea06fd03e9bba8857d8ff4daf"}}