{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:IBKT6ECBUE6FNGVTIIDDWLPPZC","short_pith_number":"pith:IBKT6ECB","schema_version":"1.0","canonical_sha256":"40553f1041a13c569ab342063b2defc89bd77684767d25956bfe0d7d4c95422c","source":{"kind":"arxiv","id":"2201.06025","version":2},"attestation_state":"computed","paper":{"title":"COLD: A Benchmark for Chinese Offensive Language Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chujie Zheng, Fei Mi, Hao Sun, Helen Meng, Jiawen Deng, Jingyan Zhou, Minlie Huang","submitted_at":"2022-01-16T11:47:23Z","abstract_excerpt":"Offensive language detection is increasingly crucial for maintaining a civilized social media platform and deploying pre-trained language models. However, this task in Chinese is still under exploration due to the scarcity of reliable datasets. To this end, we propose a benchmark --COLD for Chinese offensive language analysis, including a Chinese Offensive Language Dataset --COLDATASET and a baseline detector --COLDETECTOR which is trained on the dataset. We show that the COLD benchmark contributes to Chinese offensive language detection which is challenging for existing resources. We then dep"},"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":"2201.06025","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-16T11:47:23Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"d719075534d73e57223beedab0dcf597342df78112454618ab251c77b48e4e71","abstract_canon_sha256":"076a1aa89ee94a675ff5473b5925bda5c947f1d82cdc4dd129e0371fb441053e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:08:03.302021Z","signature_b64":"SvxnW0DIGz1mXPchis9D57ClG85jLM3KfQ0f9KM+/ZQdgicOB1wHDo8lX84YNERg3oUURQt5T0WjEoPorNoHAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"40553f1041a13c569ab342063b2defc89bd77684767d25956bfe0d7d4c95422c","last_reissued_at":"2026-07-05T05:08:03.301528Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:08:03.301528Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"COLD: A Benchmark for Chinese Offensive Language Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Chujie Zheng, Fei Mi, Hao Sun, Helen Meng, Jiawen Deng, Jingyan Zhou, Minlie Huang","submitted_at":"2022-01-16T11:47:23Z","abstract_excerpt":"Offensive language detection is increasingly crucial for maintaining a civilized social media platform and deploying pre-trained language models. However, this task in Chinese is still under exploration due to the scarcity of reliable datasets. To this end, we propose a benchmark --COLD for Chinese offensive language analysis, including a Chinese Offensive Language Dataset --COLDATASET and a baseline detector --COLDETECTOR which is trained on the dataset. We show that the COLD benchmark contributes to Chinese offensive language detection which is challenging for existing resources. We then dep"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.06025","kind":"arxiv","version":2},"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/2201.06025/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":"2201.06025","created_at":"2026-07-05T05:08:03.301598+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.06025v2","created_at":"2026-07-05T05:08:03.301598+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.06025","created_at":"2026-07-05T05:08:03.301598+00:00"},{"alias_kind":"pith_short_12","alias_value":"IBKT6ECBUE6F","created_at":"2026-07-05T05:08:03.301598+00:00"},{"alias_kind":"pith_short_16","alias_value":"IBKT6ECBUE6FNGVT","created_at":"2026-07-05T05:08:03.301598+00:00"},{"alias_kind":"pith_short_8","alias_value":"IBKT6ECB","created_at":"2026-07-05T05:08:03.301598+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.11292","citing_title":"Fine-Grained Chinese Hate Speech Understanding: Span-Level Resources, Coded Term Lexicon, and Enhanced Detection Frameworks","ref_index":14,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC","json":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC.json","graph_json":"https://pith.science/api/pith-number/IBKT6ECBUE6FNGVTIIDDWLPPZC/graph.json","events_json":"https://pith.science/api/pith-number/IBKT6ECBUE6FNGVTIIDDWLPPZC/events.json","paper":"https://pith.science/paper/IBKT6ECB"},"agent_actions":{"view_html":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC","download_json":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC.json","view_paper":"https://pith.science/paper/IBKT6ECB","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.06025&json=true","fetch_graph":"https://pith.science/api/pith-number/IBKT6ECBUE6FNGVTIIDDWLPPZC/graph.json","fetch_events":"https://pith.science/api/pith-number/IBKT6ECBUE6FNGVTIIDDWLPPZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC/action/storage_attestation","attest_author":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC/action/author_attestation","sign_citation":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC/action/citation_signature","submit_replication":"https://pith.science/pith/IBKT6ECBUE6FNGVTIIDDWLPPZC/action/replication_record"}},"created_at":"2026-07-05T05:08:03.301598+00:00","updated_at":"2026-07-05T05:08:03.301598+00:00"}