{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2024:GSGZUFYOMWNXAZZJM2XNJQ7TRX","short_pith_number":"pith:GSGZUFYO","canonical_record":{"source":{"id":"2406.12223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T02:44:56Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"fe39d057b083d53afc6a122ce404808ebd33a636cd22253c81e272593dd2c3cc","abstract_canon_sha256":"5091ec7df41710340adab48d0dcb4d896afbd0c47a59d59237707c2dbbdb28d5"},"schema_version":"1.0"},"canonical_sha256":"348d9a170e659b70672966aed4c3f38df0c98cc4590871a53e8cde6871f8042f","source":{"kind":"arxiv","id":"2406.12223","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12223","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12223v1","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12223","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"GSGZUFYOMWNX","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"GSGZUFYOMWNXAZZJ","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"GSGZUFYO","created_at":"2026-07-05T08:33:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2024:GSGZUFYOMWNXAZZJM2XNJQ7TRX","target":"record","payload":{"canonical_record":{"source":{"id":"2406.12223","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T02:44:56Z","cross_cats_sorted":["cs.CY"],"title_canon_sha256":"fe39d057b083d53afc6a122ce404808ebd33a636cd22253c81e272593dd2c3cc","abstract_canon_sha256":"5091ec7df41710340adab48d0dcb4d896afbd0c47a59d59237707c2dbbdb28d5"},"schema_version":"1.0"},"canonical_sha256":"348d9a170e659b70672966aed4c3f38df0c98cc4590871a53e8cde6871f8042f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:33:42.793400Z","signature_b64":"shI450OY42I4tvtTPYPJia6/V6TBO76gyWeRw4ZCQHF2HrHIOYC9bQJk2KqkjwklTT134i+chvqY1hS96BwvDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"348d9a170e659b70672966aed4c3f38df0c98cc4590871a53e8cde6871f8042f","last_reissued_at":"2026-07-05T08:33:42.792929Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:33:42.792929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2406.12223","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":"2026-07-05T08:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"GnO4PeDiD5ZSHrL0Fobnb3IUEGqUyEIB8rkOxblZl+HCw92jbGksgK+I3FK0SZYA1VP9QNJsKsORN8SWEHB2CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:14:16.823098Z"},"content_sha256":"690c1cd2d46ebf1d2059b845fc407b2ddf8544506af3d78f331d539edbe8e3c2","schema_version":"1.0","event_id":"sha256:690c1cd2d46ebf1d2059b845fc407b2ddf8544506af3d78f331d539edbe8e3c2"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2024:GSGZUFYOMWNXAZZJM2XNJQ7TRX","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.CY"],"primary_cat":"cs.CL","authors_text":"Kenny Tsu Wei Choo, Roy Ka-Wei Lee, Yujia Hu, Yunze Xiao","submitted_at":"2024-06-18T02:44:56Z","abstract_excerpt":"Detecting hate speech and offensive language is essential for maintaining a safe and respectful digital environment. This study examines the limitations of state-of-the-art large language models (LLMs) in identifying offensive content within systematically perturbed data, with a focus on Chinese, a language particularly susceptible to such perturbations. We introduce \\textsf{ToxiCloakCN}, an enhanced dataset derived from ToxiCN, augmented with homophonic substitutions and emoji transformations, to test the robustness of LLMs against these cloaking perturbations. Our findings reveal that existi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12223","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/2406.12223/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":"2026-07-05T08:33:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hPGU3Vja4uiThGVadA0sNHXjCHcid9cvdcoHwnHPBp2oDYUay2S/r5FiTA1MDkk5G3F0jYGuCDk5SSz57gZpBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-09T13:14:16.823618Z"},"content_sha256":"0814ad760bada2c8db6ea849f21498ae5a78898bbba82813ab8d549ff9704977","schema_version":"1.0","event_id":"sha256:0814ad760bada2c8db6ea849f21498ae5a78898bbba82813ab8d549ff9704977"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/GSGZUFYOMWNXAZZJM2XNJQ7TRX/bundle.json","state_url":"https://pith.science/pith/GSGZUFYOMWNXAZZJM2XNJQ7TRX/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/GSGZUFYOMWNXAZZJM2XNJQ7TRX/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":"2026-08-09T13:14:16Z","links":{"resolver":"https://pith.science/pith/GSGZUFYOMWNXAZZJM2XNJQ7TRX","bundle":"https://pith.science/pith/GSGZUFYOMWNXAZZJM2XNJQ7TRX/bundle.json","state":"https://pith.science/pith/GSGZUFYOMWNXAZZJM2XNJQ7TRX/state.json","well_known_bundle":"https://pith.science/.well-known/pith/GSGZUFYOMWNXAZZJM2XNJQ7TRX/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2024:GSGZUFYOMWNXAZZJM2XNJQ7TRX","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":"5091ec7df41710340adab48d0dcb4d896afbd0c47a59d59237707c2dbbdb28d5","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T02:44:56Z","title_canon_sha256":"fe39d057b083d53afc6a122ce404808ebd33a636cd22253c81e272593dd2c3cc"},"schema_version":"1.0","source":{"id":"2406.12223","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2406.12223","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"arxiv_version","alias_value":"2406.12223v1","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2406.12223","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"pith_short_12","alias_value":"GSGZUFYOMWNX","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"pith_short_16","alias_value":"GSGZUFYOMWNXAZZJ","created_at":"2026-07-05T08:33:42Z"},{"alias_kind":"pith_short_8","alias_value":"GSGZUFYO","created_at":"2026-07-05T08:33:42Z"}],"graph_snapshots":[{"event_id":"sha256:0814ad760bada2c8db6ea849f21498ae5a78898bbba82813ab8d549ff9704977","target":"graph","created_at":"2026-07-05T08:33:42Z","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/2406.12223/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Detecting hate speech and offensive language is essential for maintaining a safe and respectful digital environment. This study examines the limitations of state-of-the-art large language models (LLMs) in identifying offensive content within systematically perturbed data, with a focus on Chinese, a language particularly susceptible to such perturbations. We introduce \\textsf{ToxiCloakCN}, an enhanced dataset derived from ToxiCN, augmented with homophonic substitutions and emoji transformations, to test the robustness of LLMs against these cloaking perturbations. Our findings reveal that existi","authors_text":"Kenny Tsu Wei Choo, Roy Ka-Wei Lee, Yujia Hu, Yunze Xiao","cross_cats":["cs.CY"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T02:44:56Z","title":"ToxiCloakCN: Evaluating Robustness of Offensive Language Detection in Chinese with Cloaking Perturbations"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2406.12223","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":"sha256:690c1cd2d46ebf1d2059b845fc407b2ddf8544506af3d78f331d539edbe8e3c2","target":"record","created_at":"2026-07-05T08:33:42Z","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":"5091ec7df41710340adab48d0dcb4d896afbd0c47a59d59237707c2dbbdb28d5","cross_cats_sorted":["cs.CY"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2024-06-18T02:44:56Z","title_canon_sha256":"fe39d057b083d53afc6a122ce404808ebd33a636cd22253c81e272593dd2c3cc"},"schema_version":"1.0","source":{"id":"2406.12223","kind":"arxiv","version":1}},"canonical_sha256":"348d9a170e659b70672966aed4c3f38df0c98cc4590871a53e8cde6871f8042f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"348d9a170e659b70672966aed4c3f38df0c98cc4590871a53e8cde6871f8042f","first_computed_at":"2026-07-05T08:33:42.792929Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:33:42.792929Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"shI450OY42I4tvtTPYPJia6/V6TBO76gyWeRw4ZCQHF2HrHIOYC9bQJk2KqkjwklTT134i+chvqY1hS96BwvDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:33:42.793400Z","signed_message":"canonical_sha256_bytes"},"source_id":"2406.12223","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:690c1cd2d46ebf1d2059b845fc407b2ddf8544506af3d78f331d539edbe8e3c2","sha256:0814ad760bada2c8db6ea849f21498ae5a78898bbba82813ab8d549ff9704977"],"state_sha256":"202140ee465462217feb4a7eb46ccf1caa1fd89a4428abcbe3dc66ca4bca4ddd"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4XnpdcusWdzYgvXmBh0Qcxoo9GcjenQ6YLVt0nbzHOw3A11cCeP8ctz2+h+KWXJKGaIgt6Ct0AAQ7YbC5C9gDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-09T13:14:16.827482Z","bundle_sha256":"e2a099e70903663028808b0b6c3ab172f6058a230581622c96610bd86bd9564e"}}