{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:VQMUK4UISVGLKCBX5YBTTYRQN2","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"0968d120cb847dc2faa6a83d1511196a1a9e11ba0f41bdd0703456b6aaef3ef4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-07T01:43:48Z","title_canon_sha256":"54e782d7d692316bca82133f6dab87ffc8d388b8d7041c199cc791adb350e214"},"schema_version":"1.0","source":{"id":"2604.05318","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2604.05318","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"arxiv_version","alias_value":"2604.05318v2","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.05318","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"pith_short_12","alias_value":"VQMUK4UISVGL","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"pith_short_16","alias_value":"VQMUK4UISVGLKCBX","created_at":"2026-06-30T02:17:20Z"},{"alias_kind":"pith_short_8","alias_value":"VQMUK4UI","created_at":"2026-06-30T02:17:20Z"}],"graph_snapshots":[{"event_id":"sha256:d036706854d5f9f288d2319773f7f2ecf82d2d565a1382aac955c5935a25ef21","target":"graph","created_at":"2026-06-30T02:17:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","text":"These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non-SAE speakers worldwide."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"Disinformation detectors show reduced performance on non-Standard American English dialects."}],"snapshot_sha256":"46db342ff9b6cf0b240c782adf595863a283d8b41c492b3b604aa627d04cc3b4"},"formal_canon":{"evidence_count":1,"snapshot_sha256":"f36025ff4f6cf2e5fcfb318468941ed99e24987c37487f6b66ea7d055f9e2cfb"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2604.05318/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Adaku Uchendu, Ali Al-Lawati, Dongwon Lee, Jason Lucas, Matt Murtagh, Uchendu Uchendu","cross_cats":[],"headline":"Disinformation detectors show reduced performance on non-Standard American English dialects.","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-07T01:43:48Z","title":"DIA-HARM: Dialectal Disparities in Harmful Content Detection Across 50 English Dialects"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2604.05318","kind":"arxiv","version":2},"verdict":{"created_at":"2026-05-10T19:54:06.000936Z","id":"a0716a5b-bee0-41aa-8128-e061161c7c68","model_set":{"reader":"grok-4.3"},"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","pith_extraction_headline":"Disinformation detectors show reduced performance on non-Standard American English dialects.","strongest_claim":"These findings demonstrate that current disinformation detectors may systematically disadvantage hundreds of millions of non-SAE speakers worldwide.","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."}},"verdict_id":"a0716a5b-bee0-41aa-8128-e061161c7c68"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:b1ac7d8996569e4bf9fb1e9ebad022c09a5caf52e596e04b0922a3b6ffdcd786","target":"record","created_at":"2026-06-30T02:17:20Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"0968d120cb847dc2faa6a83d1511196a1a9e11ba0f41bdd0703456b6aaef3ef4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2026-04-07T01:43:48Z","title_canon_sha256":"54e782d7d692316bca82133f6dab87ffc8d388b8d7041c199cc791adb350e214"},"schema_version":"1.0","source":{"id":"2604.05318","kind":"arxiv","version":2}},"canonical_sha256":"ac19457288954cb50837ee0339e2306eb02aa5b2ad7fc535591594ac4527ef14","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ac19457288954cb50837ee0339e2306eb02aa5b2ad7fc535591594ac4527ef14","first_computed_at":"2026-06-30T02:17:20.223611Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-30T02:17:20.223611Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"x74DxsrjWQBVvCWs7r7/wg1rmsnFT6TPUdKRoe6VIamWURWR8JNWf06qKGvz//FqMJdtMVXx6bEFqwTr2f+kBQ==","signature_status":"signed_v1","signed_at":"2026-06-30T02:17:20.224078Z","signed_message":"canonical_sha256_bytes"},"source_id":"2604.05318","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:b1ac7d8996569e4bf9fb1e9ebad022c09a5caf52e596e04b0922a3b6ffdcd786","sha256:d036706854d5f9f288d2319773f7f2ecf82d2d565a1382aac955c5935a25ef21"],"state_sha256":"749545c8b4e5ba0cc783b0f9f09399b65127ca1a437f4f39422f0cad7e5e171f"}