{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:5HCL7PVZJQX7KAZYP657WEO3MW","short_pith_number":"pith:5HCL7PVZ","canonical_record":{"source":{"id":"2507.06282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:21:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"147026ee0e6147e09d26c255772966761d411d28bbadc7102b9f2c8691c72fce","abstract_canon_sha256":"25760b207398cac48954873660fed63a7bc24258f972d310245da45bc6a2391e"},"schema_version":"1.0"},"canonical_sha256":"e9c4bfbeb94c2ff503387fbbfb11db659bd554df5e129c38c8a61fb05d75e4eb","source":{"kind":"arxiv","id":"2507.06282","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06282","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06282v1","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06282","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"5HCL7PVZJQX7","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"5HCL7PVZJQX7KAZY","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"5HCL7PVZ","created_at":"2026-07-05T11:34:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:5HCL7PVZJQX7KAZYP657WEO3MW","target":"record","payload":{"canonical_record":{"source":{"id":"2507.06282","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:21:17Z","cross_cats_sorted":["cs.AI","cs.CL"],"title_canon_sha256":"147026ee0e6147e09d26c255772966761d411d28bbadc7102b9f2c8691c72fce","abstract_canon_sha256":"25760b207398cac48954873660fed63a7bc24258f972d310245da45bc6a2391e"},"schema_version":"1.0"},"canonical_sha256":"e9c4bfbeb94c2ff503387fbbfb11db659bd554df5e129c38c8a61fb05d75e4eb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:34:13.019913Z","signature_b64":"tvSc3fEL0KLgd+9DYxa5iuusMZhdKX8hjoTpPetcTOaniPeFpjC8ymGX5QpBCDhkL4Tq5LJ8BS+U1vcUz1uYBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e9c4bfbeb94c2ff503387fbbfb11db659bd554df5e129c38c8a61fb05d75e4eb","last_reissued_at":"2026-07-05T11:34:13.019473Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:34:13.019473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.06282","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":"2026-07-05T11:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jrUrOJDoqOfVYWyutYvbeVvwpf5bkMRAXbz18Mnay0gCK5FqPCDVx9+64cvnj6qlQjeKVTw5fu2dKQafNX8ZBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:48:24.649858Z"},"content_sha256":"b3ba9cef4019d1ff0c1e3567ec6934d49c75ea86e6c4f494b5e2140b3e5900fb","schema_version":"1.0","event_id":"sha256:b3ba9cef4019d1ff0c1e3567ec6934d49c75ea86e6c4f494b5e2140b3e5900fb"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:5HCL7PVZJQX7KAZYP657WEO3MW","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"The bitter lesson of misuse detection","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.CL"],"primary_cat":"cs.CR","authors_text":"Charbel-Rapha\\\"el Segerie, Diego Dorn, Hadrien Mariaccia","submitted_at":"2025-07-08T15:21:17Z","abstract_excerpt":"Prior work on jailbreak detection has established the importance of adversarial robustness for LLMs but has largely focused on the model ability to resist adversarial inputs and to output safe content, rather than the effectiveness of external supervision systems. The only public and independent benchmark of these guardrails to date evaluates a narrow set of supervisors on limited scenarios. Consequently, no comprehensive public benchmark yet verifies how well supervision systems from the market perform under realistic, diverse attacks. To address this, we introduce BELLS, a Benchmark for the "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06282","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/2507.06282/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":"2026-07-05T11:34:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"6pD6uNtU3uGzrZD0kOVyWNbokOu68G2sn0uFiF8Y0ZanWzqJPelelVg2wNOVg3wlvrhOUPWRAjdKOH/ATMZwAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T04:48:24.650404Z"},"content_sha256":"8895037b41527d57ff63f14493fc581323f4a490b6b992f9e071177185a0dd48","schema_version":"1.0","event_id":"sha256:8895037b41527d57ff63f14493fc581323f4a490b6b992f9e071177185a0dd48"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5HCL7PVZJQX7KAZYP657WEO3MW/bundle.json","state_url":"https://pith.science/pith/5HCL7PVZJQX7KAZYP657WEO3MW/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5HCL7PVZJQX7KAZYP657WEO3MW/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":"2026-08-07T04:48:24Z","links":{"resolver":"https://pith.science/pith/5HCL7PVZJQX7KAZYP657WEO3MW","bundle":"https://pith.science/pith/5HCL7PVZJQX7KAZYP657WEO3MW/bundle.json","state":"https://pith.science/pith/5HCL7PVZJQX7KAZYP657WEO3MW/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5HCL7PVZJQX7KAZYP657WEO3MW/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:5HCL7PVZJQX7KAZYP657WEO3MW","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":"25760b207398cac48954873660fed63a7bc24258f972d310245da45bc6a2391e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:21:17Z","title_canon_sha256":"147026ee0e6147e09d26c255772966761d411d28bbadc7102b9f2c8691c72fce"},"schema_version":"1.0","source":{"id":"2507.06282","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.06282","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"arxiv_version","alias_value":"2507.06282v1","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.06282","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"pith_short_12","alias_value":"5HCL7PVZJQX7","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"pith_short_16","alias_value":"5HCL7PVZJQX7KAZY","created_at":"2026-07-05T11:34:13Z"},{"alias_kind":"pith_short_8","alias_value":"5HCL7PVZ","created_at":"2026-07-05T11:34:13Z"}],"graph_snapshots":[{"event_id":"sha256:8895037b41527d57ff63f14493fc581323f4a490b6b992f9e071177185a0dd48","target":"graph","created_at":"2026-07-05T11:34:13Z","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/2507.06282/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Prior work on jailbreak detection has established the importance of adversarial robustness for LLMs but has largely focused on the model ability to resist adversarial inputs and to output safe content, rather than the effectiveness of external supervision systems. The only public and independent benchmark of these guardrails to date evaluates a narrow set of supervisors on limited scenarios. Consequently, no comprehensive public benchmark yet verifies how well supervision systems from the market perform under realistic, diverse attacks. To address this, we introduce BELLS, a Benchmark for the ","authors_text":"Charbel-Rapha\\\"el Segerie, Diego Dorn, Hadrien Mariaccia","cross_cats":["cs.AI","cs.CL"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:21:17Z","title":"The bitter lesson of misuse detection"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.06282","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:b3ba9cef4019d1ff0c1e3567ec6934d49c75ea86e6c4f494b5e2140b3e5900fb","target":"record","created_at":"2026-07-05T11:34:13Z","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":"25760b207398cac48954873660fed63a7bc24258f972d310245da45bc6a2391e","cross_cats_sorted":["cs.AI","cs.CL"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CR","submitted_at":"2025-07-08T15:21:17Z","title_canon_sha256":"147026ee0e6147e09d26c255772966761d411d28bbadc7102b9f2c8691c72fce"},"schema_version":"1.0","source":{"id":"2507.06282","kind":"arxiv","version":1}},"canonical_sha256":"e9c4bfbeb94c2ff503387fbbfb11db659bd554df5e129c38c8a61fb05d75e4eb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e9c4bfbeb94c2ff503387fbbfb11db659bd554df5e129c38c8a61fb05d75e4eb","first_computed_at":"2026-07-05T11:34:13.019473Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:34:13.019473Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tvSc3fEL0KLgd+9DYxa5iuusMZhdKX8hjoTpPetcTOaniPeFpjC8ymGX5QpBCDhkL4Tq5LJ8BS+U1vcUz1uYBg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:34:13.019913Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.06282","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b3ba9cef4019d1ff0c1e3567ec6934d49c75ea86e6c4f494b5e2140b3e5900fb","sha256:8895037b41527d57ff63f14493fc581323f4a490b6b992f9e071177185a0dd48"],"state_sha256":"a2c19db03b2b643c10442f4620bc2655b9326e40723810e14296c04805d7eabe"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jnzN6kvqex/gCFIZtpiTwrbLyOkpn5lrTNAUdX9mkInfgimHHJNfHMxGQrkn2Ekq+aHLuknwLl33fPvkGeQWCQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T04:48:24.654185Z","bundle_sha256":"c506cc491c9b790615d5a590c74a6a190090011c6486e36ce375d5fb7e481441"}}