{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:HDOMTRSPAB75DSO3JNR2EQ3CI5","short_pith_number":"pith:HDOMTRSP","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"},"canonical_sha256":"38dcc9c64f007fd1c9db4b63a24362474ce9d2210a7c3e82b5d8ef1a590bd4f6","source":{"kind":"arxiv","id":"2206.10265","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10265","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10265v2","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10265","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"pith_short_12","alias_value":"HDOMTRSPAB75","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"pith_short_16","alias_value":"HDOMTRSPAB75DSO3","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"pith_short_8","alias_value":"HDOMTRSP","created_at":"2026-07-05T05:36:17Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:HDOMTRSPAB75DSO3JNR2EQ3CI5","target":"record","payload":{"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"},"canonical_sha256":"38dcc9c64f007fd1c9db4b63a24362474ce9d2210a7c3e82b5d8ef1a590bd4f6","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"},"source_kind":"arxiv","source_id":"2206.10265","source_version":2,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vDRrD3IF2eS/JlxxOQZxlChBf4UOZ8VVwK98BDtoGIyhFuF1YlWKMTMZ3HdqzVoiqljmca9+yhvmgvbE4UIqBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:45:40.228086Z"},"content_sha256":"2e4380da33bccbabf8243ac884ebe8b5ab10366af77f4e99b74c49a7f4dec666","schema_version":"1.0","event_id":"sha256:2e4380da33bccbabf8243ac884ebe8b5ab10366af77f4e99b74c49a7f4dec666"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:HDOMTRSPAB75DSO3JNR2EQ3CI5","target":"graph","payload":{"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T05:36:17Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"s94/7VoIRGLo/qXvVSEPO4Bzrh6wzcwxiiyCTj4MWvIareaSvNWjZTRrpGHvRyI6Bytdhd7AZ13uPhOKKgF4Dw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-06T14:45:40.228988Z"},"content_sha256":"394aea0e8c1979b609f4015dc1b49b210bae308d09772ed2fd1e1b812ce463ff","schema_version":"1.0","event_id":"sha256:394aea0e8c1979b609f4015dc1b49b210bae308d09772ed2fd1e1b812ce463ff"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/bundle.json","state_url":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/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":"2026-08-06T14:45:40Z","links":{"resolver":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5","bundle":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/bundle.json","state":"https://pith.science/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/state.json","well_known_bundle":"https://pith.science/.well-known/pith/HDOMTRSPAB75DSO3JNR2EQ3CI5/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:HDOMTRSPAB75DSO3JNR2EQ3CI5","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":"84e367a3116109a45082c8aa3552cf7a84ba0e181974127d10a1362163f8f11b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T11:34:02Z","title_canon_sha256":"3ac3501f23c3d954283dc8b7a6091971560d2894920dc4176baf40892a1ad6ec"},"schema_version":"1.0","source":{"id":"2206.10265","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.10265","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"arxiv_version","alias_value":"2206.10265v2","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.10265","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"pith_short_12","alias_value":"HDOMTRSPAB75","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"pith_short_16","alias_value":"HDOMTRSPAB75DSO3","created_at":"2026-07-05T05:36:17Z"},{"alias_kind":"pith_short_8","alias_value":"HDOMTRSP","created_at":"2026-07-05T05:36:17Z"}],"graph_snapshots":[{"event_id":"sha256:394aea0e8c1979b609f4015dc1b49b210bae308d09772ed2fd1e1b812ce463ff","target":"graph","created_at":"2026-07-05T05:36:17Z","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/2206.10265/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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 ","authors_text":"Can Xu, Chongyang Tao, Daxin Jiang, Jiayi Zheng, Tao Shen, Xiubo Geng, Yufei Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T11:34:02Z","title":"KnowDA: All-in-One Knowledge Mixture Model for Data Augmentation in Low-Resource NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.10265","kind":"arxiv","version":2},"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":"sha256:2e4380da33bccbabf8243ac884ebe8b5ab10366af77f4e99b74c49a7f4dec666","target":"record","created_at":"2026-07-05T05:36:17Z","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":"84e367a3116109a45082c8aa3552cf7a84ba0e181974127d10a1362163f8f11b","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-06-21T11:34:02Z","title_canon_sha256":"3ac3501f23c3d954283dc8b7a6091971560d2894920dc4176baf40892a1ad6ec"},"schema_version":"1.0","source":{"id":"2206.10265","kind":"arxiv","version":2}},"canonical_sha256":"38dcc9c64f007fd1c9db4b63a24362474ce9d2210a7c3e82b5d8ef1a590bd4f6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"38dcc9c64f007fd1c9db4b63a24362474ce9d2210a7c3e82b5d8ef1a590bd4f6","first_computed_at":"2026-07-05T05:36:17.000163Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:36:17.000163Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8WdovqH/VUaZ2BDuhyeLJm6yUG3v4YLDEbCSRGwdZbvktSyn/PePI61jaLndqCcbqFQqJUBPdK+IjRQClrv5DA==","signature_status":"signed_v1","signed_at":"2026-07-05T05:36:17.000680Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.10265","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2e4380da33bccbabf8243ac884ebe8b5ab10366af77f4e99b74c49a7f4dec666","sha256:394aea0e8c1979b609f4015dc1b49b210bae308d09772ed2fd1e1b812ce463ff"],"state_sha256":"39936457ba95ff03c49f0704b4ad4121c2029bd34d2e10375dcc29e11710af31"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"NNLaga9/rIyiY8EtOgxwFI8Avr0CVsuhRdy1Qq3gbllRzVUw4JibgII2E60avBycwsqeXvb9mo3P2WJNu7cXBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-06T14:45:40.237000Z","bundle_sha256":"d23ae63549d1c7e34c538930965789cf593e3e85a1cf75919f0c86d05c3bc8f1"}}