{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:B2P463R2VJ2TCVRDU4NPBDAXUM","short_pith_number":"pith:B2P463R2","schema_version":"1.0","canonical_sha256":"0e9fcf6e3aaa75315623a71af08c17a331abc5669e0e0e66a169d3751c2298a7","source":{"kind":"arxiv","id":"2012.02954","version":1},"attestation_state":"computed","paper":{"title":"Enhanced Offensive Language Detection Through Data Augmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Guangxuan Xu, Ruibo Liu, Soroush Vosoughi","submitted_at":"2020-12-05T05:45:16Z","abstract_excerpt":"Detecting offensive language on social media is an important task. The ICWSM-2020 Data Challenge Task 2 is aimed at identifying offensive content using a crowd-sourced dataset containing 100k labelled tweets. The dataset, however, suffers from class imbalance, where certain labels are extremely rare compared with other classes (e.g, the hateful class is only 5% of the data). In this work, we present Dager (Data Augmenter), a generation-based data augmentation method, that improves the performance of classification on imbalanced and low-resource data such as the offensive language dataset. Dage"},"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":"2012.02954","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:45:16Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"88787164808625729c85b63f1c31fdce3f82aad1a9362e0b33b522ec07a376ab","abstract_canon_sha256":"21b2673e39f44b114728622371cfc19a9fbf68f40b2858c6a57845715e30e010"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:57:24.264199Z","signature_b64":"9YzrlUMLCKrs4i8jGIXKAHYWN3bWGtkgqAnotPdbh8E5SVnkeKx+xvSEAFyagcw/9DkwexXvzl+YLHoBnqSQBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0e9fcf6e3aaa75315623a71af08c17a331abc5669e0e0e66a169d3751c2298a7","last_reissued_at":"2026-07-05T01:57:24.263811Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:57:24.263811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Enhanced Offensive Language Detection Through Data Augmentation","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Guangxuan Xu, Ruibo Liu, Soroush Vosoughi","submitted_at":"2020-12-05T05:45:16Z","abstract_excerpt":"Detecting offensive language on social media is an important task. The ICWSM-2020 Data Challenge Task 2 is aimed at identifying offensive content using a crowd-sourced dataset containing 100k labelled tweets. The dataset, however, suffers from class imbalance, where certain labels are extremely rare compared with other classes (e.g, the hateful class is only 5% of the data). In this work, we present Dager (Data Augmenter), a generation-based data augmentation method, that improves the performance of classification on imbalanced and low-resource data such as the offensive language dataset. Dage"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02954","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/2012.02954/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":"2012.02954","created_at":"2026-07-05T01:57:24.263868+00:00"},{"alias_kind":"arxiv_version","alias_value":"2012.02954v1","created_at":"2026-07-05T01:57:24.263868+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02954","created_at":"2026-07-05T01:57:24.263868+00:00"},{"alias_kind":"pith_short_12","alias_value":"B2P463R2VJ2T","created_at":"2026-07-05T01:57:24.263868+00:00"},{"alias_kind":"pith_short_16","alias_value":"B2P463R2VJ2TCVRD","created_at":"2026-07-05T01:57:24.263868+00:00"},{"alias_kind":"pith_short_8","alias_value":"B2P463R2","created_at":"2026-07-05T01:57:24.263868+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/B2P463R2VJ2TCVRDU4NPBDAXUM","json":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM.json","graph_json":"https://pith.science/api/pith-number/B2P463R2VJ2TCVRDU4NPBDAXUM/graph.json","events_json":"https://pith.science/api/pith-number/B2P463R2VJ2TCVRDU4NPBDAXUM/events.json","paper":"https://pith.science/paper/B2P463R2"},"agent_actions":{"view_html":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM","download_json":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM.json","view_paper":"https://pith.science/paper/B2P463R2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2012.02954&json=true","fetch_graph":"https://pith.science/api/pith-number/B2P463R2VJ2TCVRDU4NPBDAXUM/graph.json","fetch_events":"https://pith.science/api/pith-number/B2P463R2VJ2TCVRDU4NPBDAXUM/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/action/timestamp_anchor","attest_storage":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/action/storage_attestation","attest_author":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/action/author_attestation","sign_citation":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/action/citation_signature","submit_replication":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/action/replication_record"}},"created_at":"2026-07-05T01:57:24.263868+00:00","updated_at":"2026-07-05T01:57:24.263868+00:00"}