{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FNANIQ7ZAJYEJVUS2PFD45TG4C","short_pith_number":"pith:FNANIQ7Z","schema_version":"1.0","canonical_sha256":"2b40d443f9027044d692d3ca3e7666e092b1be3e47c3d6ea03f1a8bc18196c15","source":{"kind":"arxiv","id":"2510.10961","version":3},"attestation_state":"computed","paper":{"title":"Obfuscation Rules for Detecting and Detoxifying Korean Toxicity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dayoung Kim, Hyundong Jin, Su-Hyeon Kim, Yejin Lee, Yeonsoo Kim, Yo-Sub Han","submitted_at":"2025-10-13T03:12:37Z","abstract_excerpt":"As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on non-obfuscated text, which limits robustness when users intentionally disguise toxic expressions. In particular, Korean toxic expressions can be easily disguised through agglutinative morphology and Hangeul-specific orthographic variation. However, obfuscation in Korean remains largely unexplored, which motivates us to introduce a KOTOX: Korean toxic dataset for deobfuscation and detoxification. We categorize Korean o"},"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":"2510.10961","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-10-13T03:12:37Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"3bdc8d981e4273b82d879bdd37b7c1d26dd58c121f7a7beb64a42697542aaabc","abstract_canon_sha256":"5fe2199a937624d8661cf6d9e7ccf762bebb4945204c9e8ba054888449c6e6bb"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T01:04:56.702154Z","signature_b64":"sugdbsd61Q5U5iyEEMtZDSzlToFzIpxHjIQlD06ywzR/ZK3tfCwDVSrazsRDL8TNGuLnB7SOAOFnnIeFXITNAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2b40d443f9027044d692d3ca3e7666e092b1be3e47c3d6ea03f1a8bc18196c15","last_reissued_at":"2026-05-29T01:04:56.701549Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T01:04:56.701549Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Obfuscation Rules for Detecting and Detoxifying Korean Toxicity","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Dayoung Kim, Hyundong Jin, Su-Hyeon Kim, Yejin Lee, Yeonsoo Kim, Yo-Sub Han","submitted_at":"2025-10-13T03:12:37Z","abstract_excerpt":"As language models become increasingly deployed in online environments, toxicity detection and detoxification have received growing attention. Existing studies primarily focus on non-obfuscated text, which limits robustness when users intentionally disguise toxic expressions. In particular, Korean toxic expressions can be easily disguised through agglutinative morphology and Hangeul-specific orthographic variation. However, obfuscation in Korean remains largely unexplored, which motivates us to introduce a KOTOX: Korean toxic dataset for deobfuscation and detoxification. We categorize Korean o"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.10961","kind":"arxiv","version":3},"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/2510.10961/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":"2510.10961","created_at":"2026-05-29T01:04:56.701604+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.10961v3","created_at":"2026-05-29T01:04:56.701604+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.10961","created_at":"2026-05-29T01:04:56.701604+00:00"},{"alias_kind":"pith_short_12","alias_value":"FNANIQ7ZAJYE","created_at":"2026-05-29T01:04:56.701604+00:00"},{"alias_kind":"pith_short_16","alias_value":"FNANIQ7ZAJYEJVUS","created_at":"2026-05-29T01:04:56.701604+00:00"},{"alias_kind":"pith_short_8","alias_value":"FNANIQ7Z","created_at":"2026-05-29T01:04:56.701604+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/FNANIQ7ZAJYEJVUS2PFD45TG4C","json":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C.json","graph_json":"https://pith.science/api/pith-number/FNANIQ7ZAJYEJVUS2PFD45TG4C/graph.json","events_json":"https://pith.science/api/pith-number/FNANIQ7ZAJYEJVUS2PFD45TG4C/events.json","paper":"https://pith.science/paper/FNANIQ7Z"},"agent_actions":{"view_html":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C","download_json":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C.json","view_paper":"https://pith.science/paper/FNANIQ7Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.10961&json=true","fetch_graph":"https://pith.science/api/pith-number/FNANIQ7ZAJYEJVUS2PFD45TG4C/graph.json","fetch_events":"https://pith.science/api/pith-number/FNANIQ7ZAJYEJVUS2PFD45TG4C/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C/action/storage_attestation","attest_author":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C/action/author_attestation","sign_citation":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C/action/citation_signature","submit_replication":"https://pith.science/pith/FNANIQ7ZAJYEJVUS2PFD45TG4C/action/replication_record"}},"created_at":"2026-05-29T01:04:56.701604+00:00","updated_at":"2026-05-29T01:04:56.701604+00:00"}