{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:JU2Q557IYTOPFVGQ47Z5PLZ74N","short_pith_number":"pith:JU2Q557I","schema_version":"1.0","canonical_sha256":"4d350ef7e8c4dcf2d4d0e7f3d7af3fe35adbb65f93010c5f904a314ff77769a5","source":{"kind":"arxiv","id":"2507.07640","version":1},"attestation_state":"computed","paper":{"title":"Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyang Zhang, Haotan Guo, Hongbin Na, Jianfei He, Jiayuan Ma, Ling Chen, Qi Chen, Tao Shen, Wei Wang, Zijing Shi, Zimu Wang","submitted_at":"2025-07-10T11:09:26Z","abstract_excerpt":"Phonetic Cloaking Replacement (PCR), defined as the deliberate use of homophonic or near-homophonic variants to hide toxic intent, has become a major obstacle to Chinese content moderation. While this problem is well-recognized, existing evaluations predominantly rely on rule-based, synthetic perturbations that ignore the creativity of real users. We organize PCR into a four-way surface-form taxonomy and compile \\ours, a dataset of 500 naturally occurring, phonetically cloaked offensive posts gathered from the RedNote platform. Benchmarking state-of-the-art LLMs on this dataset exposes a serio"},"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":"2507.07640","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-07-10T11:09:26Z","cross_cats_sorted":[],"title_canon_sha256":"a550939817166557bd1582b2ecbcef6a4a76d4aa394b7e6ec176d82fcfd46d9d","abstract_canon_sha256":"68e42daa7c0408c430ff9d4111d83b9ea8f0b597461ad47407b78b96d42e0d41"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:02.354465Z","signature_b64":"d6cNdjOsuIsXZU65tAb8ZF+R9QPQsvVFZovAlg33Qt82abfyGDZUdkmi6LuvQ5vfia2+eqakGlHtNLihZR/8Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4d350ef7e8c4dcf2d4d0e7f3d7af3fe35adbb65f93010c5f904a314ff77769a5","last_reissued_at":"2026-07-05T11:35:02.354049Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:02.354049Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Lost in Pronunciation: Detecting Chinese Offensive Language Disguised by Phonetic Cloaking Replacement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Haiyang Zhang, Haotan Guo, Hongbin Na, Jianfei He, Jiayuan Ma, Ling Chen, Qi Chen, Tao Shen, Wei Wang, Zijing Shi, Zimu Wang","submitted_at":"2025-07-10T11:09:26Z","abstract_excerpt":"Phonetic Cloaking Replacement (PCR), defined as the deliberate use of homophonic or near-homophonic variants to hide toxic intent, has become a major obstacle to Chinese content moderation. While this problem is well-recognized, existing evaluations predominantly rely on rule-based, synthetic perturbations that ignore the creativity of real users. We organize PCR into a four-way surface-form taxonomy and compile \\ours, a dataset of 500 naturally occurring, phonetically cloaked offensive posts gathered from the RedNote platform. Benchmarking state-of-the-art LLMs on this dataset exposes a serio"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07640","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/2507.07640/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":"2507.07640","created_at":"2026-07-05T11:35:02.354105+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07640v1","created_at":"2026-07-05T11:35:02.354105+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07640","created_at":"2026-07-05T11:35:02.354105+00:00"},{"alias_kind":"pith_short_12","alias_value":"JU2Q557IYTOP","created_at":"2026-07-05T11:35:02.354105+00:00"},{"alias_kind":"pith_short_16","alias_value":"JU2Q557IYTOPFVGQ","created_at":"2026-07-05T11:35:02.354105+00:00"},{"alias_kind":"pith_short_8","alias_value":"JU2Q557I","created_at":"2026-07-05T11:35:02.354105+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/JU2Q557IYTOPFVGQ47Z5PLZ74N","json":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N.json","graph_json":"https://pith.science/api/pith-number/JU2Q557IYTOPFVGQ47Z5PLZ74N/graph.json","events_json":"https://pith.science/api/pith-number/JU2Q557IYTOPFVGQ47Z5PLZ74N/events.json","paper":"https://pith.science/paper/JU2Q557I"},"agent_actions":{"view_html":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N","download_json":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N.json","view_paper":"https://pith.science/paper/JU2Q557I","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07640&json=true","fetch_graph":"https://pith.science/api/pith-number/JU2Q557IYTOPFVGQ47Z5PLZ74N/graph.json","fetch_events":"https://pith.science/api/pith-number/JU2Q557IYTOPFVGQ47Z5PLZ74N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N/action/storage_attestation","attest_author":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N/action/author_attestation","sign_citation":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N/action/citation_signature","submit_replication":"https://pith.science/pith/JU2Q557IYTOPFVGQ47Z5PLZ74N/action/replication_record"}},"created_at":"2026-07-05T11:35:02.354105+00:00","updated_at":"2026-07-05T11:35:02.354105+00:00"}