{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:MTEHRZWUONLAG4VRBDCDTBXSPG","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":"76f3dc99c4cd5742356f4fc492626afedb9886f46621fb6dcddc3e08148614f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-12T07:25:12Z","title_canon_sha256":"9ddfbcd33fa4fc34f63fb16c53d130dca6366560aa86e0170cbde0b55c4cedbe"},"schema_version":"1.0","source":{"id":"2606.20668","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.20668","created_at":"2026-06-23T00:11:53Z"},{"alias_kind":"arxiv_version","alias_value":"2606.20668v1","created_at":"2026-06-23T00:11:53Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.20668","created_at":"2026-06-23T00:11:53Z"},{"alias_kind":"pith_short_12","alias_value":"MTEHRZWUONLA","created_at":"2026-06-23T00:11:53Z"},{"alias_kind":"pith_short_16","alias_value":"MTEHRZWUONLAG4VR","created_at":"2026-06-23T00:11:53Z"},{"alias_kind":"pith_short_8","alias_value":"MTEHRZWU","created_at":"2026-06-23T00:11:53Z"}],"graph_snapshots":[{"event_id":"sha256:a1efd26d89ff6130410b6076fa034813371119dd22fce4dcfc1d70a11c936194","target":"graph","created_at":"2026-06-23T00:11:53Z","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/2606.20668/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"LLM supervision systems, namely input/output moderation filters and jailbreak detectors, are the primary safeguard against misuse in deployed AI applications, yet existing benchmarks are often vendor-biased, omit cost and latency, and rarely compare specialized guardrails against repurposed generalist LLMs. We present BELLS-O (Benchmark for the Evaluation of LLM Supervision Systems, Operational), the first independent operational benchmark of LLM supervision systems. BELLS-O evaluates 28 systems from 17 providers: every major specialized guardrail (e.g., LlamaGuard-4, ShieldGemma-2, Lakera Gua","authors_text":"Felix Michalak, Hadrien Mariaccia, Leonhard Waibl","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-12T07:25:12Z","title":"BELLS-O: Evaluating the Operational Trade-offs of LLM Supervision Systems"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.20668","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":"sha256:612ad43265cfed62fbdd6c109b70d9c550d96800646ddaafe1e44cb0b06ac6c4","target":"record","created_at":"2026-06-23T00:11:53Z","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":"76f3dc99c4cd5742356f4fc492626afedb9886f46621fb6dcddc3e08148614f1","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2026-06-12T07:25:12Z","title_canon_sha256":"9ddfbcd33fa4fc34f63fb16c53d130dca6366560aa86e0170cbde0b55c4cedbe"},"schema_version":"1.0","source":{"id":"2606.20668","kind":"arxiv","version":1}},"canonical_sha256":"64c878e6d473560372b108c43986f279b55f25d72832cbc338a15d6adb589de4","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"64c878e6d473560372b108c43986f279b55f25d72832cbc338a15d6adb589de4","first_computed_at":"2026-06-23T00:11:53.093857Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-23T00:11:53.093857Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"QN8N6uMS4P9W697yoHZfS+3sfYZmDxRkmGtlGyj37jwV8uOgO/tVRbwfecwC8vG9EjN7b5qWYGMv5+lKs19kDA==","signature_status":"signed_v1","signed_at":"2026-06-23T00:11:53.094254Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.20668","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:612ad43265cfed62fbdd6c109b70d9c550d96800646ddaafe1e44cb0b06ac6c4","sha256:a1efd26d89ff6130410b6076fa034813371119dd22fce4dcfc1d70a11c936194"],"state_sha256":"c05bf0219d635e0f231b7c4f3d7fc93cb3cfb75c81a7586f1de4a831ef1ba4d4"}