{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:NYMTRGISRU5NYZO3KTFQ5NTEJ3","short_pith_number":"pith:NYMTRGIS","schema_version":"1.0","canonical_sha256":"6e193899128d3adc65db54cb0eb6644ee2c2f7128c286ba14eb9d0610b40a476","source":{"kind":"arxiv","id":"2010.08670","version":1},"attestation_state":"computed","paper":{"title":"CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinghan Shen, Jiawei Han, Sandra Sajeev, Weizhu Chen, Yanru Qu, Yelong Shen","submitted_at":"2020-10-16T23:57:03Z","abstract_excerpt":"Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends to be more challenging. In this paper, we propose a novel data augmentation framework dubbed CoDA, which synthesizes diverse and informative augmented examples by integrating multiple transformations organically. Moreover, a contrastive regularization objective is introduced to capture the global relationship among all the data samples. A momentum encoder a"},"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":"2010.08670","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-16T23:57:03Z","cross_cats_sorted":[],"title_canon_sha256":"1286a0ea44714ab6c5317e74468a0dd35fe4e9e8ded12fb1ef50af3262bba7d1","abstract_canon_sha256":"ebcc5b591e6b7e6e99d649d60626c31bcebebe40b3e1fe6e5dd8beee4e7b5415"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:43:44.419770Z","signature_b64":"45cnYiJvSJloLut13DRYtD8RQdIpfPG4rzLZ3jtk6oaIlqxt87hn5QQnxIR6xCQqTVhuuxiGpASPSmleHFBYCA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6e193899128d3adc65db54cb0eb6644ee2c2f7128c286ba14eb9d0610b40a476","last_reissued_at":"2026-07-05T01:43:44.419426Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:43:44.419426Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"CoDA: Contrast-enhanced and Diversity-promoting Data Augmentation for Natural Language Understanding","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Dinghan Shen, Jiawei Han, Sandra Sajeev, Weizhu Chen, Yanru Qu, Yelong Shen","submitted_at":"2020-10-16T23:57:03Z","abstract_excerpt":"Data augmentation has been demonstrated as an effective strategy for improving model generalization and data efficiency. However, due to the discrete nature of natural language, designing label-preserving transformations for text data tends to be more challenging. In this paper, we propose a novel data augmentation framework dubbed CoDA, which synthesizes diverse and informative augmented examples by integrating multiple transformations organically. Moreover, a contrastive regularization objective is introduced to capture the global relationship among all the data samples. A momentum encoder a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.08670","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/2010.08670/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":"2010.08670","created_at":"2026-07-05T01:43:44.419488+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.08670v1","created_at":"2026-07-05T01:43:44.419488+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.08670","created_at":"2026-07-05T01:43:44.419488+00:00"},{"alias_kind":"pith_short_12","alias_value":"NYMTRGISRU5N","created_at":"2026-07-05T01:43:44.419488+00:00"},{"alias_kind":"pith_short_16","alias_value":"NYMTRGISRU5NYZO3","created_at":"2026-07-05T01:43:44.419488+00:00"},{"alias_kind":"pith_short_8","alias_value":"NYMTRGIS","created_at":"2026-07-05T01:43:44.419488+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/NYMTRGISRU5NYZO3KTFQ5NTEJ3","json":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3.json","graph_json":"https://pith.science/api/pith-number/NYMTRGISRU5NYZO3KTFQ5NTEJ3/graph.json","events_json":"https://pith.science/api/pith-number/NYMTRGISRU5NYZO3KTFQ5NTEJ3/events.json","paper":"https://pith.science/paper/NYMTRGIS"},"agent_actions":{"view_html":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3","download_json":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3.json","view_paper":"https://pith.science/paper/NYMTRGIS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.08670&json=true","fetch_graph":"https://pith.science/api/pith-number/NYMTRGISRU5NYZO3KTFQ5NTEJ3/graph.json","fetch_events":"https://pith.science/api/pith-number/NYMTRGISRU5NYZO3KTFQ5NTEJ3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3/action/storage_attestation","attest_author":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3/action/author_attestation","sign_citation":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3/action/citation_signature","submit_replication":"https://pith.science/pith/NYMTRGISRU5NYZO3KTFQ5NTEJ3/action/replication_record"}},"created_at":"2026-07-05T01:43:44.419488+00:00","updated_at":"2026-07-05T01:43:44.419488+00:00"}