{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:7PS4U2AJYMIMSVOYZUFP2CS2RD","short_pith_number":"pith:7PS4U2AJ","schema_version":"1.0","canonical_sha256":"fbe5ca6809c310c955d8cd0afd0a5a88fbd44c61a0759d71d1854297c20d079a","source":{"kind":"arxiv","id":"2402.16458","version":2},"attestation_state":"computed","paper":{"title":"ID-XCB: Data-independent Debiasing for Fair and Accurate Transformer-based Cyberbullying Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arkaitz Zubiaga, Peiling Yi","submitted_at":"2024-02-26T10:02:29Z","abstract_excerpt":"Swear words are a common proxy to collect datasets with cyberbullying incidents. Our focus is on measuring and mitigating biases derived from spurious associations between swear words and incidents occurring as a result of such data collection strategies. After demonstrating and quantifying these biases, we introduce ID-XCB, the first data-independent debiasing technique that combines adversarial training, bias constraints and debias fine-tuning approach aimed at alleviating model attention to bias-inducing words without impacting overall model performance. We explore ID-XCB on two popular ses"},"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":"2402.16458","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2024-02-26T10:02:29Z","cross_cats_sorted":[],"title_canon_sha256":"84f1bfa069d879ec1c657bbb5fe61cf42005d42d971e18e5a066818a0dc31d93","abstract_canon_sha256":"5266a5909406b35561f11cabd5e2e74c4bf5afbb2a79d5439776d23d992c1a3a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:49:37.749030Z","signature_b64":"uhIiUqUm7DS1RwXBqHbNhhPpc4MhnC9WjCA9fACzlr+oUB1QvDwjItNlhwgd6NcuzKqjoPZmdrlelRYaZ7oIBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fbe5ca6809c310c955d8cd0afd0a5a88fbd44c61a0759d71d1854297c20d079a","last_reissued_at":"2026-07-05T07:49:37.748572Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:49:37.748572Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ID-XCB: Data-independent Debiasing for Fair and Accurate Transformer-based Cyberbullying Detection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Arkaitz Zubiaga, Peiling Yi","submitted_at":"2024-02-26T10:02:29Z","abstract_excerpt":"Swear words are a common proxy to collect datasets with cyberbullying incidents. Our focus is on measuring and mitigating biases derived from spurious associations between swear words and incidents occurring as a result of such data collection strategies. After demonstrating and quantifying these biases, we introduce ID-XCB, the first data-independent debiasing technique that combines adversarial training, bias constraints and debias fine-tuning approach aimed at alleviating model attention to bias-inducing words without impacting overall model performance. We explore ID-XCB on two popular ses"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.16458","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/2402.16458/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":"2402.16458","created_at":"2026-07-05T07:49:37.748629+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.16458v2","created_at":"2026-07-05T07:49:37.748629+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.16458","created_at":"2026-07-05T07:49:37.748629+00:00"},{"alias_kind":"pith_short_12","alias_value":"7PS4U2AJYMIM","created_at":"2026-07-05T07:49:37.748629+00:00"},{"alias_kind":"pith_short_16","alias_value":"7PS4U2AJYMIMSVOY","created_at":"2026-07-05T07:49:37.748629+00:00"},{"alias_kind":"pith_short_8","alias_value":"7PS4U2AJ","created_at":"2026-07-05T07:49:37.748629+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2412.00609","citing_title":"Exploration and Evaluation of Bias in Cyberbullying Detection with Machine Learning","ref_index":4,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD","json":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD.json","graph_json":"https://pith.science/api/pith-number/7PS4U2AJYMIMSVOYZUFP2CS2RD/graph.json","events_json":"https://pith.science/api/pith-number/7PS4U2AJYMIMSVOYZUFP2CS2RD/events.json","paper":"https://pith.science/paper/7PS4U2AJ"},"agent_actions":{"view_html":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD","download_json":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD.json","view_paper":"https://pith.science/paper/7PS4U2AJ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.16458&json=true","fetch_graph":"https://pith.science/api/pith-number/7PS4U2AJYMIMSVOYZUFP2CS2RD/graph.json","fetch_events":"https://pith.science/api/pith-number/7PS4U2AJYMIMSVOYZUFP2CS2RD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD/action/storage_attestation","attest_author":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD/action/author_attestation","sign_citation":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD/action/citation_signature","submit_replication":"https://pith.science/pith/7PS4U2AJYMIMSVOYZUFP2CS2RD/action/replication_record"}},"created_at":"2026-07-05T07:49:37.748629+00:00","updated_at":"2026-07-05T07:49:37.748629+00:00"}