{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:6DKZJRFPR2Y647BAU54APF3TPA","short_pith_number":"pith:6DKZJRFP","schema_version":"1.0","canonical_sha256":"f0d594c4af8eb1ee7c20a778079773781f672b762a7d56573ca924831e91ad76","source":{"kind":"arxiv","id":"2404.05399","version":2},"attestation_state":"computed","paper":{"title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bertie Vidgen, Dirk Hovy, Fabio Pernisi, Paul R\\\"ottger","submitted_at":"2024-04-08T10:57:25Z","abstract_excerpt":"The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety. However, much of this work has happened in parallel, and with very different goals in mind, ranging from the mitigation of near-term risks around bias and toxic content generation to the assessment of longer-term catastrophic risk potential. This makes it difficult for researchers and practitioners to find the most relevant datasets for their use case, and to"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2404.05399","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-04-08T10:57:25Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"880c3bcd083424ed44b30ef67000f1fb56997c8bb6b5f34be9f78766dcaf5fbe","abstract_canon_sha256":"aa563f4eeaca9e50bc7e61aa602c395a024e25cc8fb0f5232d49065376fd82b5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:59:14.810874Z","signature_b64":"bT5qkdRC2Dvk6z/7u3nh2ahKnMY8PIiqr3tUOToXxseXfxYPfWcn010cw857pbMauxvtyEbmqkBpmxscBjY9CA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f0d594c4af8eb1ee7c20a778079773781f672b762a7d56573ca924831e91ad76","last_reissued_at":"2026-07-05T09:59:14.810443Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:59:14.810443Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SafetyPrompts: a Systematic Review of Open Datasets for Evaluating and Improving Large Language Model Safety","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bertie Vidgen, Dirk Hovy, Fabio Pernisi, Paul R\\\"ottger","submitted_at":"2024-04-08T10:57:25Z","abstract_excerpt":"The last two years have seen a rapid growth in concerns around the safety of large language models (LLMs). Researchers and practitioners have met these concerns by creating an abundance of datasets for evaluating and improving LLM safety. However, much of this work has happened in parallel, and with very different goals in mind, ranging from the mitigation of near-term risks around bias and toxic content generation to the assessment of longer-term catastrophic risk potential. This makes it difficult for researchers and practitioners to find the most relevant datasets for their use case, and to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2404.05399","kind":"arxiv","version":2},"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/2404.05399/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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2404.05399","created_at":"2026-07-05T09:59:14.810496+00:00"},{"alias_kind":"arxiv_version","alias_value":"2404.05399v2","created_at":"2026-07-05T09:59:14.810496+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2404.05399","created_at":"2026-07-05T09:59:14.810496+00:00"},{"alias_kind":"pith_short_12","alias_value":"6DKZJRFPR2Y6","created_at":"2026-07-05T09:59:14.810496+00:00"},{"alias_kind":"pith_short_16","alias_value":"6DKZJRFPR2Y647BA","created_at":"2026-07-05T09:59:14.810496+00:00"},{"alias_kind":"pith_short_8","alias_value":"6DKZJRFP","created_at":"2026-07-05T09:59:14.810496+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.07874","citing_title":"Safety is Contextual, LLM-Judges Are Not: Navigating the Rigid Priors of Evaluators","ref_index":38,"is_internal_anchor":false},{"citing_arxiv_id":"2409.18169","citing_title":"Harmful Fine-tuning Attacks and Defenses for Large Language Models: A Survey","ref_index":130,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":98,"is_internal_anchor":false},{"citing_arxiv_id":"2604.02406","citing_title":"Evaluating AI-Generated Images of Cultural Artifacts with Community-Informed Rubrics","ref_index":98,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA","json":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA.json","graph_json":"https://pith.science/api/pith-number/6DKZJRFPR2Y647BAU54APF3TPA/graph.json","events_json":"https://pith.science/api/pith-number/6DKZJRFPR2Y647BAU54APF3TPA/events.json","paper":"https://pith.science/paper/6DKZJRFP"},"agent_actions":{"view_html":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA","download_json":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA.json","view_paper":"https://pith.science/paper/6DKZJRFP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2404.05399&json=true","fetch_graph":"https://pith.science/api/pith-number/6DKZJRFPR2Y647BAU54APF3TPA/graph.json","fetch_events":"https://pith.science/api/pith-number/6DKZJRFPR2Y647BAU54APF3TPA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA/action/storage_attestation","attest_author":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA/action/author_attestation","sign_citation":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA/action/citation_signature","submit_replication":"https://pith.science/pith/6DKZJRFPR2Y647BAU54APF3TPA/action/replication_record"}},"created_at":"2026-07-05T09:59:14.810496+00:00","updated_at":"2026-07-05T09:59:14.810496+00:00"}