{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:GJNUVZFHRHTD36NJYR2CBK2SQA","short_pith_number":"pith:GJNUVZFH","schema_version":"1.0","canonical_sha256":"325b4ae4a789e63df9a9c47420ab5280186222cbe1b62fff299d16daa14a6493","source":{"kind":"arxiv","id":"2508.00760","version":1},"attestation_state":"computed","paper":{"title":"MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Qiyao Xue, Ryan Shi, Wei Gao, Xiang Lorraine Li, Yuchen Dou","submitted_at":"2025-08-01T16:34:57Z","abstract_excerpt":"Hate speech detection on Chinese social networks presents distinct challenges, particularly due to the widespread use of cloaking techniques designed to evade conventional text-based detection systems. Although large language models (LLMs) have recently improved hate speech detection capabilities, the majority of existing work has concentrated on English datasets, with limited attention given to multimodal strategies in the Chinese context. In this study, we propose MMBERT, a novel BERT-based multimodal framework that integrates textual, speech, and visual modalities through a Mixture-of-Exper"},"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":"2508.00760","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-08-01T16:34:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5f6c20ae0d3d3a4592715807f46e28ad06bc78f3850c5793622924ffb37723c2","abstract_canon_sha256":"0028456fc41a34a617f2e83d7549f6783d58c7e816dfd2ee53e5337e2413256e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:47:02.816673Z","signature_b64":"K1uT8Fu4KJjfTYTsPC/xkxxp9xqlDudP4av65aMmRjeUqz5KWnDTDOz51gs2aVnYzfmWGs+kfpz5xr/1quTrAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"325b4ae4a789e63df9a9c47420ab5280186222cbe1b62fff299d16daa14a6493","last_reissued_at":"2026-07-05T11:47:02.816173Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:47:02.816173Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"MMBERT: Scaled Mixture-of-Experts Multimodal BERT for Robust Chinese Hate Speech Detection under Cloaking Perturbations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Qiyao Xue, Ryan Shi, Wei Gao, Xiang Lorraine Li, Yuchen Dou","submitted_at":"2025-08-01T16:34:57Z","abstract_excerpt":"Hate speech detection on Chinese social networks presents distinct challenges, particularly due to the widespread use of cloaking techniques designed to evade conventional text-based detection systems. Although large language models (LLMs) have recently improved hate speech detection capabilities, the majority of existing work has concentrated on English datasets, with limited attention given to multimodal strategies in the Chinese context. In this study, we propose MMBERT, a novel BERT-based multimodal framework that integrates textual, speech, and visual modalities through a Mixture-of-Exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2508.00760","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/2508.00760/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":"2508.00760","created_at":"2026-07-05T11:47:02.816230+00:00"},{"alias_kind":"arxiv_version","alias_value":"2508.00760v1","created_at":"2026-07-05T11:47:02.816230+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2508.00760","created_at":"2026-07-05T11:47:02.816230+00:00"},{"alias_kind":"pith_short_12","alias_value":"GJNUVZFHRHTD","created_at":"2026-07-05T11:47:02.816230+00:00"},{"alias_kind":"pith_short_16","alias_value":"GJNUVZFHRHTD36NJ","created_at":"2026-07-05T11:47:02.816230+00:00"},{"alias_kind":"pith_short_8","alias_value":"GJNUVZFH","created_at":"2026-07-05T11:47:02.816230+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/GJNUVZFHRHTD36NJYR2CBK2SQA","json":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA.json","graph_json":"https://pith.science/api/pith-number/GJNUVZFHRHTD36NJYR2CBK2SQA/graph.json","events_json":"https://pith.science/api/pith-number/GJNUVZFHRHTD36NJYR2CBK2SQA/events.json","paper":"https://pith.science/paper/GJNUVZFH"},"agent_actions":{"view_html":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA","download_json":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA.json","view_paper":"https://pith.science/paper/GJNUVZFH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2508.00760&json=true","fetch_graph":"https://pith.science/api/pith-number/GJNUVZFHRHTD36NJYR2CBK2SQA/graph.json","fetch_events":"https://pith.science/api/pith-number/GJNUVZFHRHTD36NJYR2CBK2SQA/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA/action/timestamp_anchor","attest_storage":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA/action/storage_attestation","attest_author":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA/action/author_attestation","sign_citation":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA/action/citation_signature","submit_replication":"https://pith.science/pith/GJNUVZFHRHTD36NJYR2CBK2SQA/action/replication_record"}},"created_at":"2026-07-05T11:47:02.816230+00:00","updated_at":"2026-07-05T11:47:02.816230+00:00"}