{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:F5NIT36WJDYOKSWEY7RKHUKQ7A","short_pith_number":"pith:F5NIT36W","canonical_record":{"source":{"id":"2003.02245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-04T18:35:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"582130dc7608dbfc6dde4539057de32aa3090b269e0d974bcd7812a5c6e54eba","abstract_canon_sha256":"c793304c7865876f107f1e0ead79bd43e6e773b42af622ad85c4420255be987e"},"schema_version":"1.0"},"canonical_sha256":"2f5a89efd648f0e54ac4c7e2a3d150f8287d2c48d551327bce4103bba161351f","source":{"kind":"arxiv","id":"2003.02245","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02245","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02245v2","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02245","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"F5NIT36WJDYO","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"F5NIT36WJDYOKSWE","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"F5NIT36W","created_at":"2026-07-05T02:10:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:F5NIT36WJDYOKSWEY7RKHUKQ7A","target":"record","payload":{"canonical_record":{"source":{"id":"2003.02245","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-04T18:35:19Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"582130dc7608dbfc6dde4539057de32aa3090b269e0d974bcd7812a5c6e54eba","abstract_canon_sha256":"c793304c7865876f107f1e0ead79bd43e6e773b42af622ad85c4420255be987e"},"schema_version":"1.0"},"canonical_sha256":"2f5a89efd648f0e54ac4c7e2a3d150f8287d2c48d551327bce4103bba161351f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:10:59.584339Z","signature_b64":"PhSpr1VtZEG+r8tizmwKHqQp8rdO1MSKIhymFt9S2J0S1UZCBC+wUct0bhH6SdAiREjtotuCh2hx+grrMF4bAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2f5a89efd648f0e54ac4c7e2a3d150f8287d2c48d551327bce4103bba161351f","last_reissued_at":"2026-07-05T02:10:59.583853Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:10:59.583853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2003.02245","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":"2026-07-05T02:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"mrwG0y5lsOyB71lNqdQ+K69XXjRu0XRzyT/DI81dH/dh7o/U5XgJlaqLy099n8fDYhkYrVwZL2jJeKVP3WCPBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:54:37.982725Z"},"content_sha256":"6a5f04155271335d4c037f947a2ced5c54a39123ba02071a8b70b75ed4b9a3db","schema_version":"1.0","event_id":"sha256:6a5f04155271335d4c037f947a2ced5c54a39123ba02071a8b70b75ed4b9a3db"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:F5NIT36WJDYOKSWEY7RKHUKQ7A","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Data Augmentation using Pre-trained Transformer Models","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Ashutosh Choudhary, Eunah Cho, Varun Kumar","submitted_at":"2020-03-04T18:35:19Z","abstract_excerpt":"Language model based pre-trained models such as BERT have provided significant gains across different NLP tasks. In this paper, we study different types of transformer based pre-trained models such as auto-regressive models (GPT-2), auto-encoder models (BERT), and seq2seq models (BART) for conditional data augmentation. We show that prepending the class labels to text sequences provides a simple yet effective way to condition the pre-trained models for data augmentation. Additionally, on three classification benchmarks, pre-trained Seq2Seq model outperforms other data augmentation methods in a"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02245","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/2003.02245/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":"2026-07-05T02:10:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"emljBaaSHg+CKFSivBCJL5Z7OUopahA2C5j6FDvG5TW4jwkbp/g/n6bAK2gUjk5fBR1VviH2cCVermbpfC1nAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T09:54:37.983279Z"},"content_sha256":"f1d0667284b5ca9a376162b55174d44f22f1f4d0f6ab1c3c7d176a32adfdbc1f","schema_version":"1.0","event_id":"sha256:f1d0667284b5ca9a376162b55174d44f22f1f4d0f6ab1c3c7d176a32adfdbc1f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/F5NIT36WJDYOKSWEY7RKHUKQ7A/bundle.json","state_url":"https://pith.science/pith/F5NIT36WJDYOKSWEY7RKHUKQ7A/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/F5NIT36WJDYOKSWEY7RKHUKQ7A/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":"2026-08-10T09:54:37Z","links":{"resolver":"https://pith.science/pith/F5NIT36WJDYOKSWEY7RKHUKQ7A","bundle":"https://pith.science/pith/F5NIT36WJDYOKSWEY7RKHUKQ7A/bundle.json","state":"https://pith.science/pith/F5NIT36WJDYOKSWEY7RKHUKQ7A/state.json","well_known_bundle":"https://pith.science/.well-known/pith/F5NIT36WJDYOKSWEY7RKHUKQ7A/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:F5NIT36WJDYOKSWEY7RKHUKQ7A","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":"c793304c7865876f107f1e0ead79bd43e6e773b42af622ad85c4420255be987e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-04T18:35:19Z","title_canon_sha256":"582130dc7608dbfc6dde4539057de32aa3090b269e0d974bcd7812a5c6e54eba"},"schema_version":"1.0","source":{"id":"2003.02245","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2003.02245","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"arxiv_version","alias_value":"2003.02245v2","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2003.02245","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"pith_short_12","alias_value":"F5NIT36WJDYO","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"pith_short_16","alias_value":"F5NIT36WJDYOKSWE","created_at":"2026-07-05T02:10:59Z"},{"alias_kind":"pith_short_8","alias_value":"F5NIT36W","created_at":"2026-07-05T02:10:59Z"}],"graph_snapshots":[{"event_id":"sha256:f1d0667284b5ca9a376162b55174d44f22f1f4d0f6ab1c3c7d176a32adfdbc1f","target":"graph","created_at":"2026-07-05T02:10:59Z","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/2003.02245/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Language model based pre-trained models such as BERT have provided significant gains across different NLP tasks. In this paper, we study different types of transformer based pre-trained models such as auto-regressive models (GPT-2), auto-encoder models (BERT), and seq2seq models (BART) for conditional data augmentation. We show that prepending the class labels to text sequences provides a simple yet effective way to condition the pre-trained models for data augmentation. Additionally, on three classification benchmarks, pre-trained Seq2Seq model outperforms other data augmentation methods in a","authors_text":"Ashutosh Choudhary, Eunah Cho, Varun Kumar","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-04T18:35:19Z","title":"Data Augmentation using Pre-trained Transformer Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2003.02245","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":"sha256:6a5f04155271335d4c037f947a2ced5c54a39123ba02071a8b70b75ed4b9a3db","target":"record","created_at":"2026-07-05T02:10:59Z","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":"c793304c7865876f107f1e0ead79bd43e6e773b42af622ad85c4420255be987e","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-03-04T18:35:19Z","title_canon_sha256":"582130dc7608dbfc6dde4539057de32aa3090b269e0d974bcd7812a5c6e54eba"},"schema_version":"1.0","source":{"id":"2003.02245","kind":"arxiv","version":2}},"canonical_sha256":"2f5a89efd648f0e54ac4c7e2a3d150f8287d2c48d551327bce4103bba161351f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"2f5a89efd648f0e54ac4c7e2a3d150f8287d2c48d551327bce4103bba161351f","first_computed_at":"2026-07-05T02:10:59.583853Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:10:59.583853Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"PhSpr1VtZEG+r8tizmwKHqQp8rdO1MSKIhymFt9S2J0S1UZCBC+wUct0bhH6SdAiREjtotuCh2hx+grrMF4bAA==","signature_status":"signed_v1","signed_at":"2026-07-05T02:10:59.584339Z","signed_message":"canonical_sha256_bytes"},"source_id":"2003.02245","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6a5f04155271335d4c037f947a2ced5c54a39123ba02071a8b70b75ed4b9a3db","sha256:f1d0667284b5ca9a376162b55174d44f22f1f4d0f6ab1c3c7d176a32adfdbc1f"],"state_sha256":"41ad345a33062b902b8f5a342d9d4f11d494996a7dfcd87d423fc485fb863c84"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b6d0OMkIB/6bD4g9MV3PJNQ6rWLIns3p/1PFF3Xmr1YKbhqBHnJarlF3R9HyKE2/CMGU0LUdsqJ37d+MrwMyCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T09:54:37.990059Z","bundle_sha256":"866e76578e2d8282292706ac1862533512a6f62cb05365bda0a42f433f5bdfb3"}}