{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ZEOQ7CK3FU2ROEYSYQOQVIMS4P","short_pith_number":"pith:ZEOQ7CK3","schema_version":"1.0","canonical_sha256":"c91d0f895b2d35171312c41d0aa192e3d279123a9ef789874d299e74065e890b","source":{"kind":"arxiv","id":"2605.27313","version":1},"attestation_state":"computed","paper":{"title":"When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Reza Zafarani, Weibin Cai","submitted_at":"2026-05-26T17:24:41Z","abstract_excerpt":"Demographic information is often used to model annotator perspectives in subjective tasks such as hate speech detection, but its benefit is inconsistent: it improves performance in some settings and behaves as noise in others. This paper asks when demographic features help. We analyze demographic gain as a function of both data split properties and modeling frameworks. For data splits, we measure annotator disagreement, namely how often annotators assign different labels to the same example, along with training size and train-test demographic coverage. We find that demographic gains concentrat"},"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":"2605.27313","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-05-26T17:24:41Z","cross_cats_sorted":[],"title_canon_sha256":"c89367124654e110d8a6ebbe89269f2f9177f25d605f70700edac38d345c09f5","abstract_canon_sha256":"16aaf2050217275a1dbb8cef4321109a36661282b9f6ff4783f33ed8161ffeb4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-27T02:06:17.654586Z","signature_b64":"8mw8TpNuvmrWHku7h1kaaKSWeYZ4TufD5RuaXjUflcH0HGihjoFrZP9rcAeW/ewxvqjhJJvo+e4px9dNUCJEDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c91d0f895b2d35171312c41d0aa192e3d279123a9ef789874d299e74065e890b","last_reissued_at":"2026-05-27T02:06:17.653826Z","signature_status":"signed_v1","first_computed_at":"2026-05-27T02:06:17.653826Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Does Demographic Information Help? Data and Modeling Regimes for Perspective-Aware Hate Speech Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Reza Zafarani, Weibin Cai","submitted_at":"2026-05-26T17:24:41Z","abstract_excerpt":"Demographic information is often used to model annotator perspectives in subjective tasks such as hate speech detection, but its benefit is inconsistent: it improves performance in some settings and behaves as noise in others. This paper asks when demographic features help. We analyze demographic gain as a function of both data split properties and modeling frameworks. For data splits, we measure annotator disagreement, namely how often annotators assign different labels to the same example, along with training size and train-test demographic coverage. We find that demographic gains concentrat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.27313","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/2605.27313/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":"2605.27313","created_at":"2026-05-27T02:06:17.653934+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.27313v1","created_at":"2026-05-27T02:06:17.653934+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.27313","created_at":"2026-05-27T02:06:17.653934+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZEOQ7CK3FU2R","created_at":"2026-05-27T02:06:17.653934+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZEOQ7CK3FU2ROEYS","created_at":"2026-05-27T02:06:17.653934+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZEOQ7CK3","created_at":"2026-05-27T02:06:17.653934+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P","json":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P.json","graph_json":"https://pith.science/api/pith-number/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/graph.json","events_json":"https://pith.science/api/pith-number/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/events.json","paper":"https://pith.science/paper/ZEOQ7CK3"},"agent_actions":{"view_html":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P","download_json":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P.json","view_paper":"https://pith.science/paper/ZEOQ7CK3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.27313&json=true","fetch_graph":"https://pith.science/api/pith-number/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/graph.json","fetch_events":"https://pith.science/api/pith-number/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/action/storage_attestation","attest_author":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/action/author_attestation","sign_citation":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/action/citation_signature","submit_replication":"https://pith.science/pith/ZEOQ7CK3FU2ROEYSYQOQVIMS4P/action/replication_record"}},"created_at":"2026-05-27T02:06:17.653934+00:00","updated_at":"2026-05-27T02:06:17.653934+00:00"}