{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UU5SL5MX56CEY7H7MVT52AOWVK","short_pith_number":"pith:UU5SL5MX","schema_version":"1.0","canonical_sha256":"a53b25f597ef844c7cff6567dd01d6aa9b9c1008ce855fc8c0047ba1fc787a95","source":{"kind":"arxiv","id":"2501.16750","version":1},"attestation_state":"computed","paper":{"title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Savvas Zannettou, Xinyue Shen, Yang Zhang, Yiting Qu, Yixin Wu","submitted_at":"2025-01-28T07:00:45Z","abstract_excerpt":"Large Language Models (LLMs) have raised increasing concerns about their misuse in generating hate speech. Among all the efforts to address this issue, hate speech detectors play a crucial role. However, the effectiveness of different detectors against LLM-generated hate speech remains largely unknown. In this paper, we propose HateBench, a framework for benchmarking hate speech detectors on LLM-generated hate speech. We first construct a hate speech dataset of 7,838 samples generated by six widely-used LLMs covering 34 identity groups, with meticulous annotations by three labelers. We then as"},"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":"2501.16750","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CR","submitted_at":"2025-01-28T07:00:45Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"06eebe793922fec0d58b9db33135b7f11f89577ad9e5bd38e70b73df3391297a","abstract_canon_sha256":"26c96b7bc80e86932554ad9b865bec7914d81e515f45a828eacae2c093bf5342"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:18.024765Z","signature_b64":"jd9iXtsFYDTVUeRalDBJKFx2/YrGQuSP0LQxVrwGdfQTwub47hbMpm1LXZCsS3olFf1/i3Puq+68v5jJjxO1Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a53b25f597ef844c7cff6567dd01d6aa9b9c1008ce855fc8c0047ba1fc787a95","last_reissued_at":"2026-07-05T10:06:18.024328Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:18.024328Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"HateBench: Benchmarking Hate Speech Detectors on LLM-Generated Content and Hate Campaigns","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CR","authors_text":"Michael Backes, Savvas Zannettou, Xinyue Shen, Yang Zhang, Yiting Qu, Yixin Wu","submitted_at":"2025-01-28T07:00:45Z","abstract_excerpt":"Large Language Models (LLMs) have raised increasing concerns about their misuse in generating hate speech. Among all the efforts to address this issue, hate speech detectors play a crucial role. However, the effectiveness of different detectors against LLM-generated hate speech remains largely unknown. In this paper, we propose HateBench, a framework for benchmarking hate speech detectors on LLM-generated hate speech. We first construct a hate speech dataset of 7,838 samples generated by six widely-used LLMs covering 34 identity groups, with meticulous annotations by three labelers. We then as"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16750","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/2501.16750/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":"2501.16750","created_at":"2026-07-05T10:06:18.024387+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16750v1","created_at":"2026-07-05T10:06:18.024387+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16750","created_at":"2026-07-05T10:06:18.024387+00:00"},{"alias_kind":"pith_short_12","alias_value":"UU5SL5MX56CE","created_at":"2026-07-05T10:06:18.024387+00:00"},{"alias_kind":"pith_short_16","alias_value":"UU5SL5MX56CEY7H7","created_at":"2026-07-05T10:06:18.024387+00:00"},{"alias_kind":"pith_short_8","alias_value":"UU5SL5MX","created_at":"2026-07-05T10:06:18.024387+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.03990","citing_title":"Are Today's LLMs Ready to Explain Well-Being Concepts?","ref_index":42,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK","json":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK.json","graph_json":"https://pith.science/api/pith-number/UU5SL5MX56CEY7H7MVT52AOWVK/graph.json","events_json":"https://pith.science/api/pith-number/UU5SL5MX56CEY7H7MVT52AOWVK/events.json","paper":"https://pith.science/paper/UU5SL5MX"},"agent_actions":{"view_html":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK","download_json":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK.json","view_paper":"https://pith.science/paper/UU5SL5MX","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16750&json=true","fetch_graph":"https://pith.science/api/pith-number/UU5SL5MX56CEY7H7MVT52AOWVK/graph.json","fetch_events":"https://pith.science/api/pith-number/UU5SL5MX56CEY7H7MVT52AOWVK/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK/action/storage_attestation","attest_author":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK/action/author_attestation","sign_citation":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK/action/citation_signature","submit_replication":"https://pith.science/pith/UU5SL5MX56CEY7H7MVT52AOWVK/action/replication_record"}},"created_at":"2026-07-05T10:06:18.024387+00:00","updated_at":"2026-07-05T10:06:18.024387+00:00"}