{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:PT3FZK2AVCHXU2DMFSZUIWA55F","short_pith_number":"pith:PT3FZK2A","canonical_record":{"source":{"id":"2110.01852","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-05T07:35:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cafdf04091b2ec62ed745e93afa75592cdb2c149b1747d22a8cd9234b8a41225","abstract_canon_sha256":"51ab8ebc71d28a9fc4f34281704f0f3143ce2151faf90037f83c3b85ac2c0546"},"schema_version":"1.0"},"canonical_sha256":"7cf65cab40a88f7a686c2cb344581de940ea96e924f8d8d8d235f732efbc8fb7","source":{"kind":"arxiv","id":"2110.01852","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01852","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01852v3","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01852","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"PT3FZK2AVCHX","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"PT3FZK2AVCHXU2DM","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"PT3FZK2A","created_at":"2026-07-05T04:34:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:PT3FZK2AVCHXU2DMFSZUIWA55F","target":"record","payload":{"canonical_record":{"source":{"id":"2110.01852","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-05T07:35:32Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"cafdf04091b2ec62ed745e93afa75592cdb2c149b1747d22a8cd9234b8a41225","abstract_canon_sha256":"51ab8ebc71d28a9fc4f34281704f0f3143ce2151faf90037f83c3b85ac2c0546"},"schema_version":"1.0"},"canonical_sha256":"7cf65cab40a88f7a686c2cb344581de940ea96e924f8d8d8d235f732efbc8fb7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:34:47.427828Z","signature_b64":"Bm3AHBbIUPVPxhcEVSpIq3F9aG9D7YPMhTUrGmShDr7tJs7q18UnSKxQugnijJM0+DFaL4Kv2fBzlp+/b6HiAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7cf65cab40a88f7a686c2cb344581de940ea96e924f8d8d8d235f732efbc8fb7","last_reissued_at":"2026-07-05T04:34:47.427248Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:34:47.427248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2110.01852","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JN+1oY7hKw/W5R1lxgX4vkeDECx2aYjzGd5CkJ4Ur9CS4A+kApWrOBH1El6DstRI6F821csLnPeOAY9REsjbCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:22:53.292197Z"},"content_sha256":"9e77987192f9cd577813c92e986b9ac96ae8c61ac31a3913aed9239a4993a0ef","schema_version":"1.0","event_id":"sha256:9e77987192f9cd577813c92e986b9ac96ae8c61ac31a3913aed9239a4993a0ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:PT3FZK2AVCHXU2DMFSZUIWA55F","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Augmentation Approaches in Natural Language Processing: A Survey","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Bohan Li, Wanxiang Che, Yutai Hou","submitted_at":"2021-10-05T07:35:32Z","abstract_excerpt":"As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in many tasks. One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data. In this survey, we frame DA methods into three categories based on the diversity of augmented data, including paraphrasing, noising, and sampling. Our paper sets out to analyze DA methods "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01852","kind":"arxiv","version":3},"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/2110.01852/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":"2026-07-05T04:34:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nWZuZgSqYGWXaDcjH9yKSoMg02hJ8EHLoMHgIYD0PZrJKrXIQ2CsYl0BwTr3qnne8xzdzNpTWunwa2LkMG1bCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-19T11:22:53.292696Z"},"content_sha256":"e1262c71bcddcdaaeb64ef85715103c2f2c1d0e9d25c6548178c9caafac31cf5","schema_version":"1.0","event_id":"sha256:e1262c71bcddcdaaeb64ef85715103c2f2c1d0e9d25c6548178c9caafac31cf5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PT3FZK2AVCHXU2DMFSZUIWA55F/bundle.json","state_url":"https://pith.science/pith/PT3FZK2AVCHXU2DMFSZUIWA55F/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PT3FZK2AVCHXU2DMFSZUIWA55F/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":"2026-08-19T11:22:53Z","links":{"resolver":"https://pith.science/pith/PT3FZK2AVCHXU2DMFSZUIWA55F","bundle":"https://pith.science/pith/PT3FZK2AVCHXU2DMFSZUIWA55F/bundle.json","state":"https://pith.science/pith/PT3FZK2AVCHXU2DMFSZUIWA55F/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PT3FZK2AVCHXU2DMFSZUIWA55F/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:PT3FZK2AVCHXU2DMFSZUIWA55F","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":"51ab8ebc71d28a9fc4f34281704f0f3143ce2151faf90037f83c3b85ac2c0546","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-05T07:35:32Z","title_canon_sha256":"cafdf04091b2ec62ed745e93afa75592cdb2c149b1747d22a8cd9234b8a41225"},"schema_version":"1.0","source":{"id":"2110.01852","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2110.01852","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"arxiv_version","alias_value":"2110.01852v3","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2110.01852","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_12","alias_value":"PT3FZK2AVCHX","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_16","alias_value":"PT3FZK2AVCHXU2DM","created_at":"2026-07-05T04:34:47Z"},{"alias_kind":"pith_short_8","alias_value":"PT3FZK2A","created_at":"2026-07-05T04:34:47Z"}],"graph_snapshots":[{"event_id":"sha256:e1262c71bcddcdaaeb64ef85715103c2f2c1d0e9d25c6548178c9caafac31cf5","target":"graph","created_at":"2026-07-05T04:34:47Z","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/2110.01852/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"As an effective strategy, data augmentation (DA) alleviates data scarcity scenarios where deep learning techniques may fail. It is widely applied in computer vision then introduced to natural language processing and achieves improvements in many tasks. One of the main focuses of the DA methods is to improve the diversity of training data, thereby helping the model to better generalize to unseen testing data. In this survey, we frame DA methods into three categories based on the diversity of augmented data, including paraphrasing, noising, and sampling. Our paper sets out to analyze DA methods ","authors_text":"Bohan Li, Wanxiang Che, Yutai Hou","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-05T07:35:32Z","title":"Data Augmentation Approaches in Natural Language Processing: A Survey"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2110.01852","kind":"arxiv","version":3},"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":"sha256:9e77987192f9cd577813c92e986b9ac96ae8c61ac31a3913aed9239a4993a0ef","target":"record","created_at":"2026-07-05T04:34:47Z","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":"51ab8ebc71d28a9fc4f34281704f0f3143ce2151faf90037f83c3b85ac2c0546","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2021-10-05T07:35:32Z","title_canon_sha256":"cafdf04091b2ec62ed745e93afa75592cdb2c149b1747d22a8cd9234b8a41225"},"schema_version":"1.0","source":{"id":"2110.01852","kind":"arxiv","version":3}},"canonical_sha256":"7cf65cab40a88f7a686c2cb344581de940ea96e924f8d8d8d235f732efbc8fb7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7cf65cab40a88f7a686c2cb344581de940ea96e924f8d8d8d235f732efbc8fb7","first_computed_at":"2026-07-05T04:34:47.427248Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:34:47.427248Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Bm3AHBbIUPVPxhcEVSpIq3F9aG9D7YPMhTUrGmShDr7tJs7q18UnSKxQugnijJM0+DFaL4Kv2fBzlp+/b6HiAQ==","signature_status":"signed_v1","signed_at":"2026-07-05T04:34:47.427828Z","signed_message":"canonical_sha256_bytes"},"source_id":"2110.01852","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:9e77987192f9cd577813c92e986b9ac96ae8c61ac31a3913aed9239a4993a0ef","sha256:e1262c71bcddcdaaeb64ef85715103c2f2c1d0e9d25c6548178c9caafac31cf5"],"state_sha256":"6c33681fde24094a5d58cccd1c48f315b2cb2521ac88991d8066d1313b19ab30"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UIeEtzMjaQqLz4r+FHlV/E9eNabMxcdT69ITANIQY1mYV0HMUdVs3rOH4ttC9QfIyuq2oUudEuwM+xGL/73hBw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-19T11:22:53.297740Z","bundle_sha256":"f07bfe45a6f2aa24fa558c116f99ec227cec477ca3537ec5af64d11ed18ab6cb"}}