{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:VQMUK4UISVGLKCBX5YBTTYRQN2","short_pith_number":"pith:VQMUK4UI","schema_version":"1.0","canonical_sha256":"ac19457288954cb50837ee0339e2306eb02aa5b2ad7fc535591594ac4527ef14","source":{"kind":"arxiv","id":"2604.05318","version":2},"attestation_state":"computed","paper":{"title":"DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Disinformation detectors show reduced performance on non-Standard American English dialects.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adaku Uchendu, Ali Al-Lawati, Dongwon Lee, Jason Lucas, Matt Murtagh, Uchendu Uchendu","submitted_at":"2026-04-07T01:43:48Z","abstract_excerpt":"Harmful content detectors, particularly disinformation classifiers, are predominantly developed and evaluated on Standard American English (SAE), leaving their robustness to dialectal variation unexplored. We present DIA-HARM, the first benchmark for evaluating disinformation detection robustness across 50 English dialects spanning U.S., British, African, Caribbean, and Asia-Pacific varieties. Using Multi-VALUE's linguistically grounded transformations, we introduce D-CUBE (Dialectal Disinformation Detection Corpus), a core corpus component of DIA-HARM comprising 195K samples derived from esta"},"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":true},"canonical_record":{"source":{"id":"2604.05318","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-07T01:43:48Z","cross_cats_sorted":[],"title_canon_sha256":"54e782d7d692316bca82133f6dab87ffc8d388b8d7041c199cc791adb350e214","abstract_canon_sha256":"0968d120cb847dc2faa6a83d1511196a1a9e11ba0f41bdd0703456b6aaef3ef4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T02:17:20.224078Z","signature_b64":"x74DxsrjWQBVvCWs7r7/wg1rmsnFT6TPUdKRoe6VIamWURWR8JNWf06qKGvz//FqMJdtMVXx6bEFqwTr2f+kBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ac19457288954cb50837ee0339e2306eb02aa5b2ad7fc535591594ac4527ef14","last_reissued_at":"2026-06-30T02:17:20.223611Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T02:17:20.223611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"Disinformation detectors show reduced performance on non-Standard American English dialects.","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Adaku Uchendu, Ali Al-Lawati, Dongwon Lee, Jason Lucas, Matt Murtagh, Uchendu Uchendu","submitted_at":"2026-04-07T01:43:48Z","abstract_excerpt":"Harmful content detectors, particularly disinformation classifiers, are predominantly developed and evaluated on Standard American English (SAE), leaving their robustness to dialectal variation unexplored. We present DIA-HARM, the first benchmark for evaluating disinformation detection robustness across 50 English dialects spanning U.S., British, African, Caribbean, and Asia-Pacific varieties. Using Multi-VALUE's linguistically grounded transformations, we introduce D-CUBE (Dialectal Disinformation Detection Corpus), a core corpus component of DIA-HARM comprising 195K samples derived from esta"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non-SAE speakers worldwide.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"The Multi-VALUE transformations produce dialectal variants that accurately reflect real-world usage and preserve the original disinformation label without introducing confounding artifacts that independently affect model performance.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"DIA-HARM reveals that human-written dialectal English degrades disinformation detector F1 by 1.4-3.6% while AI-generated dialectal content stays stable, with multilingual models generalizing better than monolingual ones.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Disinformation detectors show reduced performance on non-Standard American English dialects.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"46db342ff9b6cf0b240c782adf595863a283d8b41c492b3b604aa627d04cc3b4"},"source":{"id":"2604.05318","kind":"arxiv","version":2},"verdict":{"id":"a0716a5b-bee0-41aa-8128-e061161c7c68","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T19:54:06.000936Z","strongest_claim":"These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non-SAE speakers worldwide.","one_line_summary":"DIA-HARM reveals that human-written dialectal English degrades disinformation detector F1 by 1.4-3.6% while AI-generated dialectal content stays stable, with multilingual models generalizing better than monolingual ones.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"The Multi-VALUE transformations produce dialectal variants that accurately reflect real-world usage and preserve the original disinformation label without introducing confounding artifacts that independently affect model performance.","pith_extraction_headline":"Disinformation detectors show reduced performance on non-Standard American English dialects."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.05318/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":1,"snapshot_sha256":"f36025ff4f6cf2e5fcfb318468941ed99e24987c37487f6b66ea7d055f9e2cfb"},"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":"2604.05318","created_at":"2026-06-30T02:17:20.223674+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.05318v2","created_at":"2026-06-30T02:17:20.223674+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.05318","created_at":"2026-06-30T02:17:20.223674+00:00"},{"alias_kind":"pith_short_12","alias_value":"VQMUK4UISVGL","created_at":"2026-06-30T02:17:20.223674+00:00"},{"alias_kind":"pith_short_16","alias_value":"VQMUK4UISVGLKCBX","created_at":"2026-06-30T02:17:20.223674+00:00"},{"alias_kind":"pith_short_8","alias_value":"VQMUK4UI","created_at":"2026-06-30T02:17:20.223674+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":1,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2","json":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2.json","graph_json":"https://pith.science/api/pith-number/VQMUK4UISVGLKCBX5YBTTYRQN2/graph.json","events_json":"https://pith.science/api/pith-number/VQMUK4UISVGLKCBX5YBTTYRQN2/events.json","paper":"https://pith.science/paper/VQMUK4UI"},"agent_actions":{"view_html":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2","download_json":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2.json","view_paper":"https://pith.science/paper/VQMUK4UI","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.05318&json=true","fetch_graph":"https://pith.science/api/pith-number/VQMUK4UISVGLKCBX5YBTTYRQN2/graph.json","fetch_events":"https://pith.science/api/pith-number/VQMUK4UISVGLKCBX5YBTTYRQN2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2/action/storage_attestation","attest_author":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2/action/author_attestation","sign_citation":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2/action/citation_signature","submit_replication":"https://pith.science/pith/VQMUK4UISVGLKCBX5YBTTYRQN2/action/replication_record"}},"created_at":"2026-06-30T02:17:20.223674+00:00","updated_at":"2026-06-30T02:17:20.223674+00:00"}