{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:B2P463R2VJ2TCVRDU4NPBDAXUM","short_pith_number":"pith:B2P463R2","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"},"canonical_sha256":"0e9fcf6e3aaa75315623a71af08c17a331abc5669e0e0e66a169d3751c2298a7","source":{"kind":"arxiv","id":"2012.02954","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02954","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02954v1","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02954","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"B2P463R2VJ2T","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"B2P463R2VJ2TCVRD","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"B2P463R2","created_at":"2026-07-05T01:57:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:B2P463R2VJ2TCVRDU4NPBDAXUM","target":"record","payload":{"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"},"canonical_sha256":"0e9fcf6e3aaa75315623a71af08c17a331abc5669e0e0e66a169d3751c2298a7","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"},"source_kind":"arxiv","source_id":"2012.02954","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wjnjTIxHkQaMSKxpJ7BltwoRm8OrZHiO3/oJB43S0cRNuoAUc7Dmz7L3Wme4TnahWKyBTL8oYvaPp2gVHScLAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:12:46.133244Z"},"content_sha256":"e1caaf3aa7759592b69dcbb9e2c0246d6dc6907c8206f2b0da1546aace2868e7","schema_version":"1.0","event_id":"sha256:e1caaf3aa7759592b69dcbb9e2c0246d6dc6907c8206f2b0da1546aace2868e7"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:B2P463R2VJ2TCVRDU4NPBDAXUM","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T01:57:24Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wr0GvwXspDCWQ5uNyeD94ziV51wBAA2ZdOplyB8nyrFbZS1UlfvnKINhCrfRlgKNR1TPpJaQWPQQyniGiTS6Cg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-08T22:12:46.133621Z"},"content_sha256":"fabffbc28ed697568bf5f79a9d3b98a003a2d7cdb40e7f7ec75d980b572acd3b","schema_version":"1.0","event_id":"sha256:fabffbc28ed697568bf5f79a9d3b98a003a2d7cdb40e7f7ec75d980b572acd3b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/bundle.json","state_url":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-07-08T22:12:46Z","links":{"resolver":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM","bundle":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/bundle.json","state":"https://pith.science/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B2P463R2VJ2TCVRDU4NPBDAXUM/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:B2P463R2VJ2TCVRDU4NPBDAXUM","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"21b2673e39f44b114728622371cfc19a9fbf68f40b2858c6a57845715e30e010","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:45:16Z","title_canon_sha256":"88787164808625729c85b63f1c31fdce3f82aad1a9362e0b33b522ec07a376ab"},"schema_version":"1.0","source":{"id":"2012.02954","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.02954","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"arxiv_version","alias_value":"2012.02954v1","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.02954","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_12","alias_value":"B2P463R2VJ2T","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_16","alias_value":"B2P463R2VJ2TCVRD","created_at":"2026-07-05T01:57:24Z"},{"alias_kind":"pith_short_8","alias_value":"B2P463R2","created_at":"2026-07-05T01:57:24Z"}],"graph_snapshots":[{"event_id":"sha256:fabffbc28ed697568bf5f79a9d3b98a003a2d7cdb40e7f7ec75d980b572acd3b","target":"graph","created_at":"2026-07-05T01:57:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2012.02954/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Guangxuan Xu, Ruibo Liu, Soroush Vosoughi","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:45:16Z","title":"Enhanced Offensive Language Detection Through Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.02954","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e1caaf3aa7759592b69dcbb9e2c0246d6dc6907c8206f2b0da1546aace2868e7","target":"record","created_at":"2026-07-05T01:57:24Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"21b2673e39f44b114728622371cfc19a9fbf68f40b2858c6a57845715e30e010","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-05T05:45:16Z","title_canon_sha256":"88787164808625729c85b63f1c31fdce3f82aad1a9362e0b33b522ec07a376ab"},"schema_version":"1.0","source":{"id":"2012.02954","kind":"arxiv","version":1}},"canonical_sha256":"0e9fcf6e3aaa75315623a71af08c17a331abc5669e0e0e66a169d3751c2298a7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0e9fcf6e3aaa75315623a71af08c17a331abc5669e0e0e66a169d3751c2298a7","first_computed_at":"2026-07-05T01:57:24.263811Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T01:57:24.263811Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9YzrlUMLCKrs4i8jGIXKAHYWN3bWGtkgqAnotPdbh8E5SVnkeKx+xvSEAFyagcw/9DkwexXvzl+YLHoBnqSQBw==","signature_status":"signed_v1","signed_at":"2026-07-05T01:57:24.264199Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.02954","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e1caaf3aa7759592b69dcbb9e2c0246d6dc6907c8206f2b0da1546aace2868e7","sha256:fabffbc28ed697568bf5f79a9d3b98a003a2d7cdb40e7f7ec75d980b572acd3b"],"state_sha256":"206977912ee7ec070f7d427b484669461bed7595f8f5fc848609185d46e731dc"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vrwereIfHMdxwBORIj7dyt37BiuMykFzZSHHC6jTu7wOgvh35Dwgfk2UR+3k/zVetI76O107P7nZvO2mRUp3CQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-08T22:12:46.135911Z","bundle_sha256":"9526c02bef849d5a813f7227513ce907e33fe42ca34c81b0628c9c84bf0f78fc"}}