{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:24OOJSFA74KAUUPBJBKVUK4FCT","short_pith_number":"pith:24OOJSFA","schema_version":"1.0","canonical_sha256":"d71ce4c8a0ff140a51e148555a2b8514fcaf93981cfe433f4cd6a6a92b9930ca","source":{"kind":"arxiv","id":"2407.12018","version":1},"attestation_state":"computed","paper":{"title":"Empirical Evaluation of Public HateSpeech Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Basel Barakat, Sadar Jaf","submitted_at":"2024-06-27T11:20:52Z","abstract_excerpt":"Despite the extensive communication benefits offered by social media platforms, numerous challenges must be addressed to ensure user safety. One of the most significant risks faced by users on these platforms is targeted hate speech. Social media platforms are widely utilised for generating datasets employed in training and evaluating machine learning algorithms for hate speech detection. However, existing public datasets exhibit numerous limitations, hindering the effective training of these algorithms and leading to inaccurate hate speech classification. This study provides a comprehensive e"},"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":"2407.12018","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-27T11:20:52Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"45565ead035abacf0558219b2f119f57bceef04261d92fbc01c9f7ac231b6f58","abstract_canon_sha256":"f9d2cb596c1f612b321c71de311bb5386413acc4e9c440e0184832fb00ca42c5"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:44:58.834764Z","signature_b64":"ulh5CLJH2OucU+pBEt8r2JaHhaYrkr5Bpgrvf0bRx/SnYxTNVoWCuXlEFHbC6J1UlH6NESqHMBtJqSZXcD3uAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d71ce4c8a0ff140a51e148555a2b8514fcaf93981cfe433f4cd6a6a92b9930ca","last_reissued_at":"2026-07-05T08:44:58.834413Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:44:58.834413Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Empirical Evaluation of Public HateSpeech Datasets","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Basel Barakat, Sadar Jaf","submitted_at":"2024-06-27T11:20:52Z","abstract_excerpt":"Despite the extensive communication benefits offered by social media platforms, numerous challenges must be addressed to ensure user safety. One of the most significant risks faced by users on these platforms is targeted hate speech. Social media platforms are widely utilised for generating datasets employed in training and evaluating machine learning algorithms for hate speech detection. However, existing public datasets exhibit numerous limitations, hindering the effective training of these algorithms and leading to inaccurate hate speech classification. This study provides a comprehensive e"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2407.12018","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/2407.12018/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":"2407.12018","created_at":"2026-07-05T08:44:58.834476+00:00"},{"alias_kind":"arxiv_version","alias_value":"2407.12018v1","created_at":"2026-07-05T08:44:58.834476+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2407.12018","created_at":"2026-07-05T08:44:58.834476+00:00"},{"alias_kind":"pith_short_12","alias_value":"24OOJSFA74KA","created_at":"2026-07-05T08:44:58.834476+00:00"},{"alias_kind":"pith_short_16","alias_value":"24OOJSFA74KAUUPB","created_at":"2026-07-05T08:44:58.834476+00:00"},{"alias_kind":"pith_short_8","alias_value":"24OOJSFA","created_at":"2026-07-05T08:44:58.834476+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.13578","citing_title":"Socio-Culturally Aware Evaluation Framework for LLM-Based Content Moderation","ref_index":18,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT","json":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT.json","graph_json":"https://pith.science/api/pith-number/24OOJSFA74KAUUPBJBKVUK4FCT/graph.json","events_json":"https://pith.science/api/pith-number/24OOJSFA74KAUUPBJBKVUK4FCT/events.json","paper":"https://pith.science/paper/24OOJSFA"},"agent_actions":{"view_html":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT","download_json":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT.json","view_paper":"https://pith.science/paper/24OOJSFA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2407.12018&json=true","fetch_graph":"https://pith.science/api/pith-number/24OOJSFA74KAUUPBJBKVUK4FCT/graph.json","fetch_events":"https://pith.science/api/pith-number/24OOJSFA74KAUUPBJBKVUK4FCT/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT/action/timestamp_anchor","attest_storage":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT/action/storage_attestation","attest_author":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT/action/author_attestation","sign_citation":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT/action/citation_signature","submit_replication":"https://pith.science/pith/24OOJSFA74KAUUPBJBKVUK4FCT/action/replication_record"}},"created_at":"2026-07-05T08:44:58.834476+00:00","updated_at":"2026-07-05T08:44:58.834476+00:00"}