{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:YEJU657KWRV3SKWAOLTA2XSEFL","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":"2d7e7725cc0153ffa1ba7c898b32447a98b1dd41b25f77ad44ba9a91255a6c69","cross_cats_sorted":["cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T03:54:28Z","title_canon_sha256":"ae4e9fc05795b1444c7f8be80e95de4028df2b136a8f3efb925d35bc11c3abf0"},"schema_version":"1.0","source":{"id":"2404.05993","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2404.05993","created_at":"2026-07-05T09:05:54Z"},{"alias_kind":"arxiv_version","alias_value":"2404.05993v2","created_at":"2026-07-05T09:05:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05993","created_at":"2026-07-05T09:05:54Z"},{"alias_kind":"pith_short_12","alias_value":"YEJU657KWRV3","created_at":"2026-07-05T09:05:54Z"},{"alias_kind":"pith_short_16","alias_value":"YEJU657KWRV3SKWA","created_at":"2026-07-05T09:05:54Z"},{"alias_kind":"pith_short_8","alias_value":"YEJU657K","created_at":"2026-07-05T09:05:54Z"}],"graph_snapshots":[{"event_id":"sha256:650a34898cd5e9dd4ec5faf2b4af7aef2206221293b86b7c37bcedafc833a354","target":"graph","created_at":"2026-07-05T09:05:54Z","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/2404.05993/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As Large Language Models (LLMs) and generative AI become more widespread, the content safety risks associated with their use also increase. We find a notable deficiency in high-quality content safety datasets and benchmarks that comprehensively cover a wide range of critical safety areas. To address this, we define a broad content safety risk taxonomy, comprising 13 critical risk and 9 sparse risk categories. Additionally, we curate AEGISSAFETYDATASET, a new dataset of approximately 26, 000 human-LLM interaction instances, complete with human annotations adhering to the taxonomy. We plan to re","authors_text":"Christopher Parisien, Erick Galinkin, Prasoon Varshney, Shaona Ghosh","cross_cats":["cs.CL","cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T03:54:28Z","title":"AEGIS: Online Adaptive AI Content Safety Moderation with Ensemble of LLM Experts"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05993","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:a439d1052b0188c163dce6ab68049e726c0e06dc73a682f4f4264a641bb66173","target":"record","created_at":"2026-07-05T09:05:54Z","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":"2d7e7725cc0153ffa1ba7c898b32447a98b1dd41b25f77ad44ba9a91255a6c69","cross_cats_sorted":["cs.CL","cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-04-09T03:54:28Z","title_canon_sha256":"ae4e9fc05795b1444c7f8be80e95de4028df2b136a8f3efb925d35bc11c3abf0"},"schema_version":"1.0","source":{"id":"2404.05993","kind":"arxiv","version":2}},"canonical_sha256":"c1134f77eab46bb92ac072e60d5e442ac72989b3cef0330587816b751743d116","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c1134f77eab46bb92ac072e60d5e442ac72989b3cef0330587816b751743d116","first_computed_at":"2026-07-05T09:05:54.291821Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T09:05:54.291821Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"nIx0z+Lj62RPi9LtA1uS60tR8ub5hHmBHH2Jc3W7M9lxV9WU5lI5vI6OP1xVu4fRqbBjHO6+0vzw4LxclqZtCA==","signature_status":"signed_v1","signed_at":"2026-07-05T09:05:54.292232Z","signed_message":"canonical_sha256_bytes"},"source_id":"2404.05993","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a439d1052b0188c163dce6ab68049e726c0e06dc73a682f4f4264a641bb66173","sha256:650a34898cd5e9dd4ec5faf2b4af7aef2206221293b86b7c37bcedafc833a354"],"state_sha256":"dcce42f3657c07186e7c19b1386572576f21bae8bbc62d3f422980d532c0f962"}