{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:MD4XU27DO2KC6QEM5WMB64JKFJ","short_pith_number":"pith:MD4XU27D","schema_version":"1.0","canonical_sha256":"60f97a6be376942f408ced981f712a2a6ce844f943effe5d122b2a0fe756cf48","source":{"kind":"arxiv","id":"2312.03379","version":1},"attestation_state":"computed","paper":{"title":"A Text-to-Text Model for Multilingual Offensive Language Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcos Zampieri, Tharindu Ranasinghe","submitted_at":"2023-12-06T09:37:27Z","abstract_excerpt":"The ubiquity of offensive content on social media is a growing cause for concern among companies and government organizations. Recently, transformer-based models such as BERT, XLNET, and XLM-R have achieved state-of-the-art performance in detecting various forms of offensive content (e.g. hate speech, cyberbullying, and cyberaggression). However, the majority of these models are limited in their capabilities due to their encoder-only architecture, which restricts the number and types of labels in downstream tasks. Addressing these limitations, this study presents the first pre-trained model wi"},"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":"2312.03379","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-12-06T09:37:27Z","cross_cats_sorted":[],"title_canon_sha256":"8bf6546419987a75aa948ae3860e256c475838af00107ecdf022a777be04f453","abstract_canon_sha256":"769eb6c1f9e239ffb9bee4aa80105ac239330d00afe4c4dd07daa049faa87b55"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T07:21:03.000871Z","signature_b64":"cJ04+afeweNhCMFWL+/6lsGZ2a3cSwPG+tO6fcFrMLDEwGPIrqZo2jPw4H8xHl/nO4ZC5bFZ7ffFOQys+QYfAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"60f97a6be376942f408ced981f712a2a6ce844f943effe5d122b2a0fe756cf48","last_reissued_at":"2026-07-05T07:21:03.000344Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T07:21:03.000344Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Text-to-Text Model for Multilingual Offensive Language Identification","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Marcos Zampieri, Tharindu Ranasinghe","submitted_at":"2023-12-06T09:37:27Z","abstract_excerpt":"The ubiquity of offensive content on social media is a growing cause for concern among companies and government organizations. Recently, transformer-based models such as BERT, XLNET, and XLM-R have achieved state-of-the-art performance in detecting various forms of offensive content (e.g. hate speech, cyberbullying, and cyberaggression). However, the majority of these models are limited in their capabilities due to their encoder-only architecture, which restricts the number and types of labels in downstream tasks. Addressing these limitations, this study presents the first pre-trained model wi"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2312.03379","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/2312.03379/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":"2312.03379","created_at":"2026-07-05T07:21:03.000402+00:00"},{"alias_kind":"arxiv_version","alias_value":"2312.03379v1","created_at":"2026-07-05T07:21:03.000402+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2312.03379","created_at":"2026-07-05T07:21:03.000402+00:00"},{"alias_kind":"pith_short_12","alias_value":"MD4XU27DO2KC","created_at":"2026-07-05T07:21:03.000402+00:00"},{"alias_kind":"pith_short_16","alias_value":"MD4XU27DO2KC6QEM","created_at":"2026-07-05T07:21:03.000402+00:00"},{"alias_kind":"pith_short_8","alias_value":"MD4XU27D","created_at":"2026-07-05T07:21:03.000402+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2508.06360","citing_title":"Cyberbullying Detection via Aggression-Enhanced Prompting","ref_index":21,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ","json":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ.json","graph_json":"https://pith.science/api/pith-number/MD4XU27DO2KC6QEM5WMB64JKFJ/graph.json","events_json":"https://pith.science/api/pith-number/MD4XU27DO2KC6QEM5WMB64JKFJ/events.json","paper":"https://pith.science/paper/MD4XU27D"},"agent_actions":{"view_html":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ","download_json":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ.json","view_paper":"https://pith.science/paper/MD4XU27D","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2312.03379&json=true","fetch_graph":"https://pith.science/api/pith-number/MD4XU27DO2KC6QEM5WMB64JKFJ/graph.json","fetch_events":"https://pith.science/api/pith-number/MD4XU27DO2KC6QEM5WMB64JKFJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ/action/storage_attestation","attest_author":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ/action/author_attestation","sign_citation":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ/action/citation_signature","submit_replication":"https://pith.science/pith/MD4XU27DO2KC6QEM5WMB64JKFJ/action/replication_record"}},"created_at":"2026-07-05T07:21:03.000402+00:00","updated_at":"2026-07-05T07:21:03.000402+00:00"}