{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:SWX5ZLX5WBPRDMH2GYGSJCOH7V","short_pith_number":"pith:SWX5ZLX5","schema_version":"1.0","canonical_sha256":"95afdcaefdb05f11b0fa360d2489c7fd601f1bb830c68979c24e7a973a479a81","source":{"kind":"arxiv","id":"2201.08702","version":1},"attestation_state":"computed","paper":{"title":"Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Qianben Chen, Richong Zhang, Yaowei Zheng, Yongyi Mao","submitted_at":"2022-01-21T13:59:45Z","abstract_excerpt":"Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in practice. In this work, we introduce a dual contrastive learning (DualCL) framework that simultaneously learns the features of input samples and the parameters of classifiers in the same space. Specifically, DualCL regards the parameters of the classifiers as augmented samples associating to different labels and then exploits the contrastive learning between the in"},"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":"2201.08702","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-01-21T13:59:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"2c0d0198fe652934f579e26316ff6de7f33e741b3a782d5a2058ac9dcc169516","abstract_canon_sha256":"8446cd8dad768937a796b7f266662f71cb91ba798c0eebc9c88c338c07d59bb0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:50:31.503600Z","signature_b64":"1fnZ/6ZPDc3gp36bG7oRFyagdGNSmHWoatIBuT6aCOtOgC6Xg+AzeunuGjUh7FKBelJgtOwp1F5Ko39rG/VWCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"95afdcaefdb05f11b0fa360d2489c7fd601f1bb830c68979c24e7a973a479a81","last_reissued_at":"2026-07-05T03:50:31.503236Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:50:31.503236Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Dual Contrastive Learning: Text Classification via Label-Aware Data Augmentation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Qianben Chen, Richong Zhang, Yaowei Zheng, Yongyi Mao","submitted_at":"2022-01-21T13:59:45Z","abstract_excerpt":"Contrastive learning has achieved remarkable success in representation learning via self-supervision in unsupervised settings. However, effectively adapting contrastive learning to supervised learning tasks remains as a challenge in practice. In this work, we introduce a dual contrastive learning (DualCL) framework that simultaneously learns the features of input samples and the parameters of classifiers in the same space. Specifically, DualCL regards the parameters of the classifiers as augmented samples associating to different labels and then exploits the contrastive learning between the in"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2201.08702","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/2201.08702/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":"2201.08702","created_at":"2026-07-05T03:50:31.503290+00:00"},{"alias_kind":"arxiv_version","alias_value":"2201.08702v1","created_at":"2026-07-05T03:50:31.503290+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2201.08702","created_at":"2026-07-05T03:50:31.503290+00:00"},{"alias_kind":"pith_short_12","alias_value":"SWX5ZLX5WBPR","created_at":"2026-07-05T03:50:31.503290+00:00"},{"alias_kind":"pith_short_16","alias_value":"SWX5ZLX5WBPRDMH2","created_at":"2026-07-05T03:50:31.503290+00:00"},{"alias_kind":"pith_short_8","alias_value":"SWX5ZLX5","created_at":"2026-07-05T03:50:31.503290+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2507.14182","citing_title":"From Bias to Behavior: Learning Bull-Bear Market Dynamics with Contrastive Modeling","ref_index":7,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V","json":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V.json","graph_json":"https://pith.science/api/pith-number/SWX5ZLX5WBPRDMH2GYGSJCOH7V/graph.json","events_json":"https://pith.science/api/pith-number/SWX5ZLX5WBPRDMH2GYGSJCOH7V/events.json","paper":"https://pith.science/paper/SWX5ZLX5"},"agent_actions":{"view_html":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V","download_json":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V.json","view_paper":"https://pith.science/paper/SWX5ZLX5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2201.08702&json=true","fetch_graph":"https://pith.science/api/pith-number/SWX5ZLX5WBPRDMH2GYGSJCOH7V/graph.json","fetch_events":"https://pith.science/api/pith-number/SWX5ZLX5WBPRDMH2GYGSJCOH7V/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V/action/storage_attestation","attest_author":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V/action/author_attestation","sign_citation":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V/action/citation_signature","submit_replication":"https://pith.science/pith/SWX5ZLX5WBPRDMH2GYGSJCOH7V/action/replication_record"}},"created_at":"2026-07-05T03:50:31.503290+00:00","updated_at":"2026-07-05T03:50:31.503290+00:00"}