{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:SRNQ3BRD2UQNZTKNGRG4QXRAXF","short_pith_number":"pith:SRNQ3BRD","canonical_record":{"source":{"id":"2505.24341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T08:32:45Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"969e6230b936228b04b225c7ca77e4a810e168f913bafc90b274157448013a22","abstract_canon_sha256":"af8dac7d5a7441642ee40a9d21cb6015265a912ed099d9638345abfb2f0adc53"},"schema_version":"1.0"},"canonical_sha256":"945b0d8623d520dccd4d344dc85e20b97693ca2f339d1e77161186f7cc3076e7","source":{"kind":"arxiv","id":"2505.24341","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24341","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24341v1","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24341","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"pith_short_12","alias_value":"SRNQ3BRD2UQN","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"pith_short_16","alias_value":"SRNQ3BRD2UQNZTKN","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"pith_short_8","alias_value":"SRNQ3BRD","created_at":"2026-07-05T11:12:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:SRNQ3BRD2UQNZTKNGRG4QXRAXF","target":"record","payload":{"canonical_record":{"source":{"id":"2505.24341","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T08:32:45Z","cross_cats_sorted":["cs.AI","cs.CY"],"title_canon_sha256":"969e6230b936228b04b225c7ca77e4a810e168f913bafc90b274157448013a22","abstract_canon_sha256":"af8dac7d5a7441642ee40a9d21cb6015265a912ed099d9638345abfb2f0adc53"},"schema_version":"1.0"},"canonical_sha256":"945b0d8623d520dccd4d344dc85e20b97693ca2f339d1e77161186f7cc3076e7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:12:47.206925Z","signature_b64":"MZ0Bfjme15FlTYWKoRp4Tly+6ZHTjKRW+nRX9hLSw8+hAJ+3tBOx9roQtS4IEXl5Jr392ocKOq2G0IJq6XE0CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"945b0d8623d520dccd4d344dc85e20b97693ca2f339d1e77161186f7cc3076e7","last_reissued_at":"2026-07-05T11:12:47.206395Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:12:47.206395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2505.24341","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"+scfz6qnV97AuoWn5JPPKUWa3dBAcexsds6kBYs4zBPE3do1ELZtLsFqu7K53OtGYYmBDyQw+LTCNjYN6iMIAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:23:15.104960Z"},"content_sha256":"dd3ab4367fafa9e278538f35fe6b63f0cf73df221c30473017b98db026307ac5","schema_version":"1.0","event_id":"sha256:dd3ab4367fafa9e278538f35fe6b63f0cf73df221c30473017b98db026307ac5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:SRNQ3BRD2UQNZTKNGRG4QXRAXF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.CY"],"primary_cat":"cs.CL","authors_text":"Chuanrui Hu, Haicheng Wang, Han Qiu, Jialiang Lu, Minlie Huang, Shiyao Cui, Shujian Yang, Tianwei Zhang","submitted_at":"2025-05-30T08:32:45Z","abstract_excerpt":"Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent studies show that simple character substitutions in toxic Chinese text can easily confuse the state-of-the-art (SOTA) LLMs. In this paper, we highlight the multimodal nature of Chinese language as a key challenge for deploying LLMs in toxic Chinese detection. First, we propose a taxonomy of 3 perturbation strategies and 8 specific approaches in toxic Chinese content. Then, we curate a dataset based on this taxonomy,"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24341","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/2505.24341/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T11:12:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"65SUNB5OarvQO+Q/OogDwSUCT3kX4RGQc6BgvOBcDswCegR/sckItqLMjbPDeH/LE+bBDiWmBJ4t0VYL5UoTDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T20:23:15.105874Z"},"content_sha256":"a8b93a8e8ab84e09b9e5a76023bf40d7f0fe0e938fb11f0ee7a3deea24aac504","schema_version":"1.0","event_id":"sha256:a8b93a8e8ab84e09b9e5a76023bf40d7f0fe0e938fb11f0ee7a3deea24aac504"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/SRNQ3BRD2UQNZTKNGRG4QXRAXF/bundle.json","state_url":"https://pith.science/pith/SRNQ3BRD2UQNZTKNGRG4QXRAXF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/SRNQ3BRD2UQNZTKNGRG4QXRAXF/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-09T20:23:15Z","links":{"resolver":"https://pith.science/pith/SRNQ3BRD2UQNZTKNGRG4QXRAXF","bundle":"https://pith.science/pith/SRNQ3BRD2UQNZTKNGRG4QXRAXF/bundle.json","state":"https://pith.science/pith/SRNQ3BRD2UQNZTKNGRG4QXRAXF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/SRNQ3BRD2UQNZTKNGRG4QXRAXF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:SRNQ3BRD2UQNZTKNGRG4QXRAXF","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":"af8dac7d5a7441642ee40a9d21cb6015265a912ed099d9638345abfb2f0adc53","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T08:32:45Z","title_canon_sha256":"969e6230b936228b04b225c7ca77e4a810e168f913bafc90b274157448013a22"},"schema_version":"1.0","source":{"id":"2505.24341","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2505.24341","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"arxiv_version","alias_value":"2505.24341v1","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.24341","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"pith_short_12","alias_value":"SRNQ3BRD2UQN","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"pith_short_16","alias_value":"SRNQ3BRD2UQNZTKN","created_at":"2026-07-05T11:12:47Z"},{"alias_kind":"pith_short_8","alias_value":"SRNQ3BRD","created_at":"2026-07-05T11:12:47Z"}],"graph_snapshots":[{"event_id":"sha256:a8b93a8e8ab84e09b9e5a76023bf40d7f0fe0e938fb11f0ee7a3deea24aac504","target":"graph","created_at":"2026-07-05T11:12:47Z","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":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2505.24341/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting toxic content using language models is important but challenging. While large language models (LLMs) have demonstrated strong performance in understanding Chinese, recent studies show that simple character substitutions in toxic Chinese text can easily confuse the state-of-the-art (SOTA) LLMs. In this paper, we highlight the multimodal nature of Chinese language as a key challenge for deploying LLMs in toxic Chinese detection. First, we propose a taxonomy of 3 perturbation strategies and 8 specific approaches in toxic Chinese content. Then, we curate a dataset based on this taxonomy,","authors_text":"Chuanrui Hu, Haicheng Wang, Han Qiu, Jialiang Lu, Minlie Huang, Shiyao Cui, Shujian Yang, Tianwei Zhang","cross_cats":["cs.AI","cs.CY"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T08:32:45Z","title":"Exploring Multimodal Challenges in Toxic Chinese Detection: Taxonomy, Benchmark, and Findings"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.24341","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:dd3ab4367fafa9e278538f35fe6b63f0cf73df221c30473017b98db026307ac5","target":"record","created_at":"2026-07-05T11:12:47Z","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":"af8dac7d5a7441642ee40a9d21cb6015265a912ed099d9638345abfb2f0adc53","cross_cats_sorted":["cs.AI","cs.CY"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-05-30T08:32:45Z","title_canon_sha256":"969e6230b936228b04b225c7ca77e4a810e168f913bafc90b274157448013a22"},"schema_version":"1.0","source":{"id":"2505.24341","kind":"arxiv","version":1}},"canonical_sha256":"945b0d8623d520dccd4d344dc85e20b97693ca2f339d1e77161186f7cc3076e7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"945b0d8623d520dccd4d344dc85e20b97693ca2f339d1e77161186f7cc3076e7","first_computed_at":"2026-07-05T11:12:47.206395Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:12:47.206395Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MZ0Bfjme15FlTYWKoRp4Tly+6ZHTjKRW+nRX9hLSw8+hAJ+3tBOx9roQtS4IEXl5Jr392ocKOq2G0IJq6XE0CQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:12:47.206925Z","signed_message":"canonical_sha256_bytes"},"source_id":"2505.24341","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:dd3ab4367fafa9e278538f35fe6b63f0cf73df221c30473017b98db026307ac5","sha256:a8b93a8e8ab84e09b9e5a76023bf40d7f0fe0e938fb11f0ee7a3deea24aac504"],"state_sha256":"9972657d165497c9d0bee88ab3f94ea3c9ef62e1275f17a46e5c93ffb06e6902"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vTri13CPEx2oQuU810ZLrbTkb6x8pE+Lq/L9LzFra99XXdmR1Ft08ar3GB9ASKANE5EOPHPfEBKarFaiQEgjCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T20:23:15.111782Z","bundle_sha256":"bf24306c33702898d74b3e57d4947f99f4c6d2eed00cc019f62a52c69d722d0c"}}