{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:IM6CHVOUEO6F6HL5FLCBTQN75H","short_pith_number":"pith:IM6CHVOU","canonical_record":{"source":{"id":"2105.03075","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T06:03:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7986134240f436ad1e82f29cc3500cefca39b390ae62997774657e5d5741f49c","abstract_canon_sha256":"56a0ff982079e13b3149578dcc662d488295ada2a389c512acb6dcdc78d3e73d"},"schema_version":"1.0"},"canonical_sha256":"433c23d5d423bc5f1d7d2ac419c1bfe9ffea2f57f893f8942ada97d327a46e28","source":{"kind":"arxiv","id":"2105.03075","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03075","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03075v5","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03075","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"IM6CHVOUEO6F","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"IM6CHVOUEO6F6HL5","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"IM6CHVOU","created_at":"2026-07-05T03:36:54Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:IM6CHVOUEO6F6HL5FLCBTQN75H","target":"record","payload":{"canonical_record":{"source":{"id":"2105.03075","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T06:03:45Z","cross_cats_sorted":["cs.AI","cs.LG"],"title_canon_sha256":"7986134240f436ad1e82f29cc3500cefca39b390ae62997774657e5d5741f49c","abstract_canon_sha256":"56a0ff982079e13b3149578dcc662d488295ada2a389c512acb6dcdc78d3e73d"},"schema_version":"1.0"},"canonical_sha256":"433c23d5d423bc5f1d7d2ac419c1bfe9ffea2f57f893f8942ada97d327a46e28","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:36:54.250227Z","signature_b64":"oC0zGz7lu3hDNdeQhzsA45lN4D49RSXmUFpAY6AfOC/rg21tn3BBPOh2Mon9Bt7tTvIH3PBcUVUTnwyKtKBKDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"433c23d5d423bc5f1d7d2ac419c1bfe9ffea2f57f893f8942ada97d327a46e28","last_reissued_at":"2026-07-05T03:36:54.249713Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:36:54.249713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2105.03075","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T03:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Yw04405f0b+x1j0nwmKqwoFDpyZaYANRqCHfLp8r734/cOdv7TaUH5QYguyod3aeLfQjNpqyitsO7W5dFc8YCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:49.179888Z"},"content_sha256":"538cd26961656ccf62bf8b0ed942516948b43db7933d306874dc7e4ce588f9aa","schema_version":"1.0","event_id":"sha256:538cd26961656ccf62bf8b0ed942516948b43db7933d306874dc7e4ce588f9aa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:IM6CHVOUEO6F6HL5FLCBTQN75H","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Survey of Data Augmentation Approaches for NLP","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.LG"],"primary_cat":"cs.CL","authors_text":"Eduard Hovy, Jason Wei, Sarath Chandar, Soroush Vosoughi, Steven Y. Feng, Teruko Mitamura, Varun Gangal","submitted_at":"2021-05-07T06:03:45Z","abstract_excerpt":"Data augmentation has recently seen increased interest in NLP due to more work in low-resource domains, new tasks, and the popularity of large-scale neural networks that require large amounts of training data. Despite this recent upsurge, this area is still relatively underexplored, perhaps due to the challenges posed by the discrete nature of language data. In this paper, we present a comprehensive and unifying survey of data augmentation for NLP by summarizing the literature in a structured manner. We first introduce and motivate data augmentation for NLP, and then discuss major methodologic"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03075","kind":"arxiv","version":5},"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/2105.03075/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":"2026-07-05T03:36:54Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b1CZssB344S+/vN4/4QzVAY/23OJzhWVUHEl4A8jFt4pjZSEnSt/2s2X8nk/Lm8GfvD5V2DUG5c4opcE8BiDDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-08T11:49:49.180401Z"},"content_sha256":"21c5bd7f67cf6b3e64ff05dfd20863b728c06ddbbb54e26723ad607b11b55de0","schema_version":"1.0","event_id":"sha256:21c5bd7f67cf6b3e64ff05dfd20863b728c06ddbbb54e26723ad607b11b55de0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IM6CHVOUEO6F6HL5FLCBTQN75H/bundle.json","state_url":"https://pith.science/pith/IM6CHVOUEO6F6HL5FLCBTQN75H/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IM6CHVOUEO6F6HL5FLCBTQN75H/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":"2026-08-08T11:49:49Z","links":{"resolver":"https://pith.science/pith/IM6CHVOUEO6F6HL5FLCBTQN75H","bundle":"https://pith.science/pith/IM6CHVOUEO6F6HL5FLCBTQN75H/bundle.json","state":"https://pith.science/pith/IM6CHVOUEO6F6HL5FLCBTQN75H/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IM6CHVOUEO6F6HL5FLCBTQN75H/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:IM6CHVOUEO6F6HL5FLCBTQN75H","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":"56a0ff982079e13b3149578dcc662d488295ada2a389c512acb6dcdc78d3e73d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T06:03:45Z","title_canon_sha256":"7986134240f436ad1e82f29cc3500cefca39b390ae62997774657e5d5741f49c"},"schema_version":"1.0","source":{"id":"2105.03075","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2105.03075","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"arxiv_version","alias_value":"2105.03075v5","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2105.03075","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_12","alias_value":"IM6CHVOUEO6F","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_16","alias_value":"IM6CHVOUEO6F6HL5","created_at":"2026-07-05T03:36:54Z"},{"alias_kind":"pith_short_8","alias_value":"IM6CHVOU","created_at":"2026-07-05T03:36:54Z"}],"graph_snapshots":[{"event_id":"sha256:21c5bd7f67cf6b3e64ff05dfd20863b728c06ddbbb54e26723ad607b11b55de0","target":"graph","created_at":"2026-07-05T03:36:54Z","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/2105.03075/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation has recently seen increased interest in NLP due to more work in low-resource domains, new tasks, and the popularity of large-scale neural networks that require large amounts of training data. Despite this recent upsurge, this area is still relatively underexplored, perhaps due to the challenges posed by the discrete nature of language data. In this paper, we present a comprehensive and unifying survey of data augmentation for NLP by summarizing the literature in a structured manner. We first introduce and motivate data augmentation for NLP, and then discuss major methodologic","authors_text":"Eduard Hovy, Jason Wei, Sarath Chandar, Soroush Vosoughi, Steven Y. Feng, Teruko Mitamura, Varun Gangal","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T06:03:45Z","title":"A Survey of Data Augmentation Approaches for NLP"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2105.03075","kind":"arxiv","version":5},"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":"sha256:538cd26961656ccf62bf8b0ed942516948b43db7933d306874dc7e4ce588f9aa","target":"record","created_at":"2026-07-05T03:36:54Z","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":"56a0ff982079e13b3149578dcc662d488295ada2a389c512acb6dcdc78d3e73d","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2021-05-07T06:03:45Z","title_canon_sha256":"7986134240f436ad1e82f29cc3500cefca39b390ae62997774657e5d5741f49c"},"schema_version":"1.0","source":{"id":"2105.03075","kind":"arxiv","version":5}},"canonical_sha256":"433c23d5d423bc5f1d7d2ac419c1bfe9ffea2f57f893f8942ada97d327a46e28","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"433c23d5d423bc5f1d7d2ac419c1bfe9ffea2f57f893f8942ada97d327a46e28","first_computed_at":"2026-07-05T03:36:54.249713Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T03:36:54.249713Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"oC0zGz7lu3hDNdeQhzsA45lN4D49RSXmUFpAY6AfOC/rg21tn3BBPOh2Mon9Bt7tTvIH3PBcUVUTnwyKtKBKDQ==","signature_status":"signed_v1","signed_at":"2026-07-05T03:36:54.250227Z","signed_message":"canonical_sha256_bytes"},"source_id":"2105.03075","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:538cd26961656ccf62bf8b0ed942516948b43db7933d306874dc7e4ce588f9aa","sha256:21c5bd7f67cf6b3e64ff05dfd20863b728c06ddbbb54e26723ad607b11b55de0"],"state_sha256":"2302749d5b7d1886c636caf58d1b3cb358dc0d7b037904d45e6d7f69c5e7b260"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ffPE4EnEzbSI6tEc9AcFl1QnPpFPalQN2+/JIMliN5KzDJtcLLbpLdtyuNAb2m8ZyNK6kAC2GYQoA3xTNmw8Bg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-08T11:49:49.184623Z","bundle_sha256":"3a12a2526aa8f1452b0586472a5c5e93ff6e85057a6affea1e92cc09836e8ea0"}}