{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:IEGNBUD7G6PVOBI5AG4H3ACV7V","short_pith_number":"pith:IEGNBUD7","canonical_record":{"source":{"id":"2210.04610","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-03T14:04:46Z","cross_cats_sorted":["cs.CR","cs.CV","cs.CY","cs.LG"],"title_canon_sha256":"aecda0f957904c7648aeeb3547fb1bd0c333876b3731061bcd049fbabbd72864","abstract_canon_sha256":"8efd1b284b3d7ba8edebf7fda2785efe364c6d199da72d0e15516147eac77861"},"schema_version":"1.0"},"canonical_sha256":"410cd0d07f379f57051d01b87d8055fd4420925ba9755b3d3537506e6ea107c7","source":{"kind":"arxiv","id":"2210.04610","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04610","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04610v5","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04610","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"IEGNBUD7G6PV","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"IEGNBUD7G6PVOBI5","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"IEGNBUD7","created_at":"2026-07-05T05:15:00Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:IEGNBUD7G6PVOBI5AG4H3ACV7V","target":"record","payload":{"canonical_record":{"source":{"id":"2210.04610","kind":"arxiv","version":5},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-03T14:04:46Z","cross_cats_sorted":["cs.CR","cs.CV","cs.CY","cs.LG"],"title_canon_sha256":"aecda0f957904c7648aeeb3547fb1bd0c333876b3731061bcd049fbabbd72864","abstract_canon_sha256":"8efd1b284b3d7ba8edebf7fda2785efe364c6d199da72d0e15516147eac77861"},"schema_version":"1.0"},"canonical_sha256":"410cd0d07f379f57051d01b87d8055fd4420925ba9755b3d3537506e6ea107c7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:00.254776Z","signature_b64":"vMNcRCjd+ZPlrFdpy9pjwSEYkGFCZZnLMUzMUIM6AFnir47qsDClOK5jjRzzRe9KoQmkcsQb/jeQ2eK8b4uPBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"410cd0d07f379f57051d01b87d8055fd4420925ba9755b3d3537506e6ea107c7","last_reissued_at":"2026-07-05T05:15:00.254391Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:00.254391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2210.04610","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"lEg7nPO3bzJoTw5oV1eoSqVRaRkWT6dNFiiXh/x2ER8LfCt6ar4TgrLozgf88G7KJkIl/p3NfHCmCYCzViN1CQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:52:17.989792Z"},"content_sha256":"1a1efac00910f260fb51eb986ad455e04098da5b4ea5917ce19d48ee6c94097d","schema_version":"1.0","event_id":"sha256:1a1efac00910f260fb51eb986ad455e04098da5b4ea5917ce19d48ee6c94097d"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:IEGNBUD7G6PVOBI5AG4H3ACV7V","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Red-Teaming the Stable Diffusion Safety Filter","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CR","cs.CV","cs.CY","cs.LG"],"primary_cat":"cs.AI","authors_text":"Daniel Paleka, David Lindner, Florian Tram\\`er, Javier Rando, Lennart Heim","submitted_at":"2022-10-03T14:04:46Z","abstract_excerpt":"Stable Diffusion is a recent open-source image generation model comparable to proprietary models such as DALLE, Imagen, or Parti. Stable Diffusion comes with a safety filter that aims to prevent generating explicit images. Unfortunately, the filter is obfuscated and poorly documented. This makes it hard for users to prevent misuse in their applications, and to understand the filter's limitations and improve it. We first show that it is easy to generate disturbing content that bypasses the safety filter. We then reverse-engineer the filter and find that while it aims to prevent sexual content, "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04610","kind":"arxiv","version":5},"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/2210.04610/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":"2026-07-05T05:15:00Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2UXagDzGoccQ4i5Ze/itsGulT46K0pO78LVpVDSyoTytd0Dfw2s/yWqf36tHKG09TGIPs6u7U217CT16xntxBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-04T15:52:17.990555Z"},"content_sha256":"639e5758b886ac82ea6e9a740ae72a0cce00b186dfd8a93cbe38a816b5e536ef","schema_version":"1.0","event_id":"sha256:639e5758b886ac82ea6e9a740ae72a0cce00b186dfd8a93cbe38a816b5e536ef"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IEGNBUD7G6PVOBI5AG4H3ACV7V/bundle.json","state_url":"https://pith.science/pith/IEGNBUD7G6PVOBI5AG4H3ACV7V/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IEGNBUD7G6PVOBI5AG4H3ACV7V/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":"2026-08-04T15:52:18Z","links":{"resolver":"https://pith.science/pith/IEGNBUD7G6PVOBI5AG4H3ACV7V","bundle":"https://pith.science/pith/IEGNBUD7G6PVOBI5AG4H3ACV7V/bundle.json","state":"https://pith.science/pith/IEGNBUD7G6PVOBI5AG4H3ACV7V/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IEGNBUD7G6PVOBI5AG4H3ACV7V/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:IEGNBUD7G6PVOBI5AG4H3ACV7V","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":"8efd1b284b3d7ba8edebf7fda2785efe364c6d199da72d0e15516147eac77861","cross_cats_sorted":["cs.CR","cs.CV","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-03T14:04:46Z","title_canon_sha256":"aecda0f957904c7648aeeb3547fb1bd0c333876b3731061bcd049fbabbd72864"},"schema_version":"1.0","source":{"id":"2210.04610","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2210.04610","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"arxiv_version","alias_value":"2210.04610v5","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2210.04610","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_12","alias_value":"IEGNBUD7G6PV","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_16","alias_value":"IEGNBUD7G6PVOBI5","created_at":"2026-07-05T05:15:00Z"},{"alias_kind":"pith_short_8","alias_value":"IEGNBUD7","created_at":"2026-07-05T05:15:00Z"}],"graph_snapshots":[{"event_id":"sha256:639e5758b886ac82ea6e9a740ae72a0cce00b186dfd8a93cbe38a816b5e536ef","target":"graph","created_at":"2026-07-05T05:15:00Z","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/2210.04610/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Stable Diffusion is a recent open-source image generation model comparable to proprietary models such as DALLE, Imagen, or Parti. Stable Diffusion comes with a safety filter that aims to prevent generating explicit images. Unfortunately, the filter is obfuscated and poorly documented. This makes it hard for users to prevent misuse in their applications, and to understand the filter's limitations and improve it. We first show that it is easy to generate disturbing content that bypasses the safety filter. We then reverse-engineer the filter and find that while it aims to prevent sexual content, ","authors_text":"Daniel Paleka, David Lindner, Florian Tram\\`er, Javier Rando, Lennart Heim","cross_cats":["cs.CR","cs.CV","cs.CY","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-03T14:04:46Z","title":"Red-Teaming the Stable Diffusion Safety Filter"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2210.04610","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":"sha256:1a1efac00910f260fb51eb986ad455e04098da5b4ea5917ce19d48ee6c94097d","target":"record","created_at":"2026-07-05T05:15:00Z","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":"8efd1b284b3d7ba8edebf7fda2785efe364c6d199da72d0e15516147eac77861","cross_cats_sorted":["cs.CR","cs.CV","cs.CY","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.AI","submitted_at":"2022-10-03T14:04:46Z","title_canon_sha256":"aecda0f957904c7648aeeb3547fb1bd0c333876b3731061bcd049fbabbd72864"},"schema_version":"1.0","source":{"id":"2210.04610","kind":"arxiv","version":5}},"canonical_sha256":"410cd0d07f379f57051d01b87d8055fd4420925ba9755b3d3537506e6ea107c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"410cd0d07f379f57051d01b87d8055fd4420925ba9755b3d3537506e6ea107c7","first_computed_at":"2026-07-05T05:15:00.254391Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:00.254391Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vMNcRCjd+ZPlrFdpy9pjwSEYkGFCZZnLMUzMUIM6AFnir47qsDClOK5jjRzzRe9KoQmkcsQb/jeQ2eK8b4uPBA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:00.254776Z","signed_message":"canonical_sha256_bytes"},"source_id":"2210.04610","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:1a1efac00910f260fb51eb986ad455e04098da5b4ea5917ce19d48ee6c94097d","sha256:639e5758b886ac82ea6e9a740ae72a0cce00b186dfd8a93cbe38a816b5e536ef"],"state_sha256":"4dfa532544c18b1ee1cdc1ea666ce67320e4d74d98488e53ede2ba312c430bc9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9UzfYK2m0bYSsibtui1L1EqiNwu6+XayRWLJFvQ6qC9kC8L5kySz80u3uHYFFcza38fJ3JDiJskOBYmTacovBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-04T15:52:18.015290Z","bundle_sha256":"3d018aea94f72e2f3400c724dc24147606f5711ead03d536a5bd3100e4fdf91f"}}