{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:HDOMTRSPAB75DSO3JNR2EQ3CI5","short_pith_number":"pith:HDOMTRSP","schema_version":"1.0","canonical_sha256":"38dcc9c64f007fd1c9db4b63a24362474ce9d2210a7c3e82b5d8ef1a590bd4f6","source":{"kind":"arxiv","id":"2206.10265","version":2},"attestation_state":"computed","paper":{"title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Jiayi Zheng, Tao Shen, Xiubo Geng, Yufei Wang","submitted_at":"2022-06-21T11:34:02Z","abstract_excerpt":"This paper focuses on the data augmentation for low-resource NLP tasks where the training set is limited. The existing solutions either leverage task-independent heuristic rules (e.g., Synonym Replacement) or fine-tune general-purpose pre-trained language models (e.g., GPT2) using the limited training instances to produce new synthetic data. Consequently, they have trivial task-specific knowledge and are limited to yielding low-quality synthetic data. To combat this issue, we propose Knowledge Mixture Data Augmentation Model (KnowDA) which is an Seq2Seq language model pre-trained on a mixture "},"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":"2206.10265","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T11:34:02Z","cross_cats_sorted":[],"title_canon_sha256":"3ac3501f23c3d954283dc8b7a6091971560d2894920dc4176baf40892a1ad6ec","abstract_canon_sha256":"84e367a3116109a45082c8aa3552cf7a84ba0e181974127d10a1362163f8f11b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:36:17.000680Z","signature_b64":"8WdovqH/VUaZ2BDuhyeLJm6yUG3v4YLDEbCSRGwdZbvktSyn/PePI61jaLndqCcbqFQqJUBPdK+IjRQClrv5DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"38dcc9c64f007fd1c9db4b63a24362474ce9d2210a7c3e82b5d8ef1a590bd4f6","last_reissued_at":"2026-07-05T05:36:17.000163Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:36:17.000163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Jiayi Zheng, Tao Shen, Xiubo Geng, Yufei Wang","submitted_at":"2022-06-21T11:34:02Z","abstract_excerpt":"This paper focuses on the data augmentation for low-resource NLP tasks where the training set is limited. The existing solutions either leverage task-independent heuristic rules (e.g., Synonym Replacement) or fine-tune general-purpose pre-trained language models (e.g., GPT2) using the limited training instances to produce new synthetic data. Consequently, they have trivial task-specific knowledge and are limited to yielding low-quality synthetic data. To combat this issue, we propose Knowledge Mixture Data Augmentation Model (KnowDA) which is an Seq2Seq language model pre-trained on a mixture "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10265","kind":"arxiv","version":2},"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/2206.10265/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":"2206.10265","created_at":"2026-07-05T05:36:17.000225+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.10265v2","created_at":"2026-07-05T05:36:17.000225+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10265","created_at":"2026-07-05T05:36:17.000225+00:00"},{"alias_kind":"pith_short_12","alias_value":"HDOMTRSPAB75","created_at":"2026-07-05T05:36:17.000225+00:00"},{"alias_kind":"pith_short_16","alias_value":"HDOMTRSPAB75DSO3","created_at":"2026-07-05T05:36:17.000225+00:00"},{"alias_kind":"pith_short_8","alias_value":"HDOMTRSP","created_at":"2026-07-05T05:36:17.000225+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2304.12244","citing_title":"WizardLM: Empowering large pre-trained language models to follow complex instructions","ref_index":44,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5","json":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5.json","graph_json":"https://pith.science/api/pith-number/HDOMTRSPAB75DSO3JNR2EQ3CI5/graph.json","events_json":"https://pith.science/api/pith-number/HDOMTRSPAB75DSO3JNR2EQ3CI5/events.json","paper":"https://pith.science/paper/HDOMTRSP"},"agent_actions":{"view_html":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5","download_json":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5.json","view_paper":"https://pith.science/paper/HDOMTRSP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.10265&json=true","fetch_graph":"https://pith.science/api/pith-number/HDOMTRSPAB75DSO3JNR2EQ3CI5/graph.json","fetch_events":"https://pith.science/api/pith-number/HDOMTRSPAB75DSO3JNR2EQ3CI5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/action/storage_attestation","attest_author":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/action/author_attestation","sign_citation":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/action/citation_signature","submit_replication":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/action/replication_record"}},"created_at":"2026-07-05T05:36:17.000225+00:00","updated_at":"2026-07-05T05:36:17.000225+00:00"}