{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:XRDTBJ4R2X3ZPOSQ66FG5SFDKB","short_pith_number":"pith:XRDTBJ4R","schema_version":"1.0","canonical_sha256":"bc4730a791d5f797ba50f78a6ec8a3504220d04e8025dd646452f2f05814e2ab","source":{"kind":"arxiv","id":"2202.12459","version":3},"attestation_state":"computed","paper":{"title":"APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kichang Yang, Won Ik Cho, Wonjun Jang","submitted_at":"2022-02-25T02:04:38Z","abstract_excerpt":"In hate speech detection, developing training and evaluation datasets across various domains is the critical issue. Whereas, major approaches crawl social media texts and hire crowd-workers to annotate the data. Following this convention often restricts the scope of pejorative expressions to a single domain lacking generalization. Sometimes domain overlap between training corpus and evaluation set overestimate the prediction performance when pretraining language models on low-data language. To alleviate these problems in Korean, we propose APEACH that asks unspecified users to generate hate sp"},"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":"2202.12459","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-02-25T02:04:38Z","cross_cats_sorted":[],"title_canon_sha256":"5721514b888082a68f5346209a5f5871f4e204065ddd84452334a7ccedc7bc1d","abstract_canon_sha256":"c2724e27f9495ed2be28b361d6646c529dc150ab79098926645b43b6192310b9"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:10:36.691947Z","signature_b64":"0C29aj3QffBYQ+OYGchWIvmEG7xOdWL9y6NvRGEbt1pezcpviSHQdirIA5+SKpaFsbu3IjZ+icvcH1D1WMlJBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"bc4730a791d5f797ba50f78a6ec8a3504220d04e8025dd646452f2f05814e2ab","last_reissued_at":"2026-07-05T05:10:36.691438Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:10:36.691438Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"APEACH: Attacking Pejorative Expressions with Analysis on Crowd-Generated Hate Speech Evaluation Datasets","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Kichang Yang, Won Ik Cho, Wonjun Jang","submitted_at":"2022-02-25T02:04:38Z","abstract_excerpt":"In hate speech detection, developing training and evaluation datasets across various domains is the critical issue. Whereas, major approaches crawl social media texts and hire crowd-workers to annotate the data. Following this convention often restricts the scope of pejorative expressions to a single domain lacking generalization. Sometimes domain overlap between training corpus and evaluation set overestimate the prediction performance when pretraining language models on low-data language. To alleviate these problems in Korean, we propose APEACH that asks unspecified users to generate hate sp"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2202.12459","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/2202.12459/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":"2202.12459","created_at":"2026-07-05T05:10:36.691497+00:00"},{"alias_kind":"arxiv_version","alias_value":"2202.12459v3","created_at":"2026-07-05T05:10:36.691497+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2202.12459","created_at":"2026-07-05T05:10:36.691497+00:00"},{"alias_kind":"pith_short_12","alias_value":"XRDTBJ4R2X3Z","created_at":"2026-07-05T05:10:36.691497+00:00"},{"alias_kind":"pith_short_16","alias_value":"XRDTBJ4R2X3ZPOSQ","created_at":"2026-07-05T05:10:36.691497+00:00"},{"alias_kind":"pith_short_8","alias_value":"XRDTBJ4R","created_at":"2026-07-05T05:10:36.691497+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/XRDTBJ4R2X3ZPOSQ66FG5SFDKB","json":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB.json","graph_json":"https://pith.science/api/pith-number/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/graph.json","events_json":"https://pith.science/api/pith-number/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/events.json","paper":"https://pith.science/paper/XRDTBJ4R"},"agent_actions":{"view_html":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB","download_json":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB.json","view_paper":"https://pith.science/paper/XRDTBJ4R","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2202.12459&json=true","fetch_graph":"https://pith.science/api/pith-number/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/graph.json","fetch_events":"https://pith.science/api/pith-number/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/action/storage_attestation","attest_author":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/action/author_attestation","sign_citation":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/action/citation_signature","submit_replication":"https://pith.science/pith/XRDTBJ4R2X3ZPOSQ66FG5SFDKB/action/replication_record"}},"created_at":"2026-07-05T05:10:36.691497+00:00","updated_at":"2026-07-05T05:10:36.691497+00:00"}