{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:CFCCPHEYYKMFOXLW6RVR6VWEEL","short_pith_number":"pith:CFCCPHEY","schema_version":"1.0","canonical_sha256":"1144279c98c298575d76f46b1f56c422e9d2ed1e69040722848eaeaa542760b3","source":{"kind":"arxiv","id":"2311.06446","version":1},"attestation_state":"computed","paper":{"title":"THOS: A Benchmark Dataset for Targeted Hate and Offensive Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashfaq Ali Shafin, Bogdan Carbunar, Ladislau B\\\"ol\\\"oni, Saad Almohaimeed, Saleh Almohaimeed","submitted_at":"2023-11-11T00:30:31Z","abstract_excerpt":"Detecting harmful content on social media, such as Twitter, is made difficult by the fact that the seemingly simple yes/no classification conceals a significant amount of complexity. Unfortunately, while several datasets have been collected for training classifiers in hate and offensive speech, there is a scarcity of datasets labeled with a finer granularity of target classes and specific targets. In this paper, we introduce THOS, a dataset of 8.3k tweets manually labeled with fine-grained annotations about the target of the message. We demonstrate that this dataset makes it feasible to train "},"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":"2311.06446","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2023-11-11T00:30:31Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5ad5048062c8a4342dcd45aaec536b42a3342a84448023914567f623c1acd661","abstract_canon_sha256":"32d541aec7524c64d652477f6c8cf477dd84259e61dadb18218bf20e5b1abfa7"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:11:40.109791Z","signature_b64":"LZUZHX9xdlESt8YgfC4VbY2UFQe+3u1fF5pLK4+GS+TUcHCNGuqUi9XUabxYlEZ0O29JgRdX1E6hVzazwCJ1CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"1144279c98c298575d76f46b1f56c422e9d2ed1e69040722848eaeaa542760b3","last_reissued_at":"2026-07-05T07:11:40.109216Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:11:40.109216Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"THOS: A Benchmark Dataset for Targeted Hate and Offensive Speech","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Ashfaq Ali Shafin, Bogdan Carbunar, Ladislau B\\\"ol\\\"oni, Saad Almohaimeed, Saleh Almohaimeed","submitted_at":"2023-11-11T00:30:31Z","abstract_excerpt":"Detecting harmful content on social media, such as Twitter, is made difficult by the fact that the seemingly simple yes/no classification conceals a significant amount of complexity. Unfortunately, while several datasets have been collected for training classifiers in hate and offensive speech, there is a scarcity of datasets labeled with a finer granularity of target classes and specific targets. In this paper, we introduce THOS, a dataset of 8.3k tweets manually labeled with fine-grained annotations about the target of the message. We demonstrate that this dataset makes it feasible to train "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2311.06446","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/2311.06446/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":"2311.06446","created_at":"2026-07-05T07:11:40.109282+00:00"},{"alias_kind":"arxiv_version","alias_value":"2311.06446v1","created_at":"2026-07-05T07:11:40.109282+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2311.06446","created_at":"2026-07-05T07:11:40.109282+00:00"},{"alias_kind":"pith_short_12","alias_value":"CFCCPHEYYKMF","created_at":"2026-07-05T07:11:40.109282+00:00"},{"alias_kind":"pith_short_16","alias_value":"CFCCPHEYYKMFOXLW","created_at":"2026-07-05T07:11:40.109282+00:00"},{"alias_kind":"pith_short_8","alias_value":"CFCCPHEY","created_at":"2026-07-05T07:11:40.109282+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2505.07212","citing_title":"The Language of Influence: Sentiment, Emotion, and Hate Speech in State Sponsored Influence Operations","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL","json":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL.json","graph_json":"https://pith.science/api/pith-number/CFCCPHEYYKMFOXLW6RVR6VWEEL/graph.json","events_json":"https://pith.science/api/pith-number/CFCCPHEYYKMFOXLW6RVR6VWEEL/events.json","paper":"https://pith.science/paper/CFCCPHEY"},"agent_actions":{"view_html":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL","download_json":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL.json","view_paper":"https://pith.science/paper/CFCCPHEY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2311.06446&json=true","fetch_graph":"https://pith.science/api/pith-number/CFCCPHEYYKMFOXLW6RVR6VWEEL/graph.json","fetch_events":"https://pith.science/api/pith-number/CFCCPHEYYKMFOXLW6RVR6VWEEL/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL/action/timestamp_anchor","attest_storage":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL/action/storage_attestation","attest_author":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL/action/author_attestation","sign_citation":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL/action/citation_signature","submit_replication":"https://pith.science/pith/CFCCPHEYYKMFOXLW6RVR6VWEEL/action/replication_record"}},"created_at":"2026-07-05T07:11:40.109282+00:00","updated_at":"2026-07-05T07:11:40.109282+00:00"}