{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:5YMKGESBJSJFAB43CWXEGI5SAI","short_pith_number":"pith:5YMKGESB","canonical_record":{"source":{"id":"2101.03236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T01:15:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6b5e9624e89474ec7b4bb24dc3c20fc9a65db1e13680daef8e9ddcdebbaa527b","abstract_canon_sha256":"c908887ffd0a8d4bafd49f4566a335ef1fb430f706baab6f2bba3ee62a70063c"},"schema_version":"1.0"},"canonical_sha256":"ee18a312414c9250079b15ae4323b20205fc1312d70df60de007aa1d52ba7d33","source":{"kind":"arxiv","id":"2101.03236","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.03236","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2101.03236v1","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03236","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"5YMKGESBJSJF","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"5YMKGESBJSJFAB43","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"5YMKGESB","created_at":"2026-07-05T02:05:47Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:5YMKGESBJSJFAB43CWXEGI5SAI","target":"record","payload":{"canonical_record":{"source":{"id":"2101.03236","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T01:15:57Z","cross_cats_sorted":["cs.LG"],"title_canon_sha256":"6b5e9624e89474ec7b4bb24dc3c20fc9a65db1e13680daef8e9ddcdebbaa527b","abstract_canon_sha256":"c908887ffd0a8d4bafd49f4566a335ef1fb430f706baab6f2bba3ee62a70063c"},"schema_version":"1.0"},"canonical_sha256":"ee18a312414c9250079b15ae4323b20205fc1312d70df60de007aa1d52ba7d33","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:05:47.497856Z","signature_b64":"vkOefPjQvYPwMtgcHeWVKKvTt6LTEnQbe3S5HJxJK4YdszFhzrp3ODiT/4K0T5/e1/FD9Sib1LAMvtNR4FqXCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ee18a312414c9250079b15ae4323b20205fc1312d70df60de007aa1d52ba7d33","last_reissued_at":"2026-07-05T02:05:47.497437Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:05:47.497437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2101.03236","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tpOLoTEMBxN+WlBNRjWqf/QOIru2242dPOIyz2BxUVdX3P6u+WuUEPTrDhM1xSjbLEoU/r//WOX2YrPdE38ABg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T09:30:00.403984Z"},"content_sha256":"2536b6faa8a04eaddede93876741ecea0fcaf5b4fc6bdecedab4bf7886a03f70","schema_version":"1.0","event_id":"sha256:2536b6faa8a04eaddede93876741ecea0fcaf5b4fc6bdecedab4bf7886a03f70"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:5YMKGESBJSJFAB43CWXEGI5SAI","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SDA: Improving Text Generation with Self Data Augmentation","license":"http://creativecommons.org/publicdomain/zero/1.0/","headline":"","cross_cats":["cs.LG"],"primary_cat":"cs.CL","authors_text":"Changyou Chen, Chunyuan Li, Ping Yu, Ruiyi Zhang, Yang Zhao, Yizhe Zhang","submitted_at":"2021-01-02T01:15:57Z","abstract_excerpt":"Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of natural languages. In this paper, we propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, which are only applied to specific models, our method is more general and could be easily adapted to any M"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03236","kind":"arxiv","version":1},"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/2101.03236/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":"2026-07-05T02:05:47Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"PcXMBNcHPpk6DUqzAJ1/HRBUoEV1T4g4u/UwZudJR0IGJXei07qz2JIsm5RuGat0iS5xfTfo+kUAio0tVO1YAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-07-14T09:30:00.404373Z"},"content_sha256":"c8b0d0987fad813b6575691d8e4478c026a445a15395fc8ab3f528b3e4d233b0","schema_version":"1.0","event_id":"sha256:c8b0d0987fad813b6575691d8e4478c026a445a15395fc8ab3f528b3e4d233b0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5YMKGESBJSJFAB43CWXEGI5SAI/bundle.json","state_url":"https://pith.science/pith/5YMKGESBJSJFAB43CWXEGI5SAI/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5YMKGESBJSJFAB43CWXEGI5SAI/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":"2026-07-14T09:30:00Z","links":{"resolver":"https://pith.science/pith/5YMKGESBJSJFAB43CWXEGI5SAI","bundle":"https://pith.science/pith/5YMKGESBJSJFAB43CWXEGI5SAI/bundle.json","state":"https://pith.science/pith/5YMKGESBJSJFAB43CWXEGI5SAI/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5YMKGESBJSJFAB43CWXEGI5SAI/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:5YMKGESBJSJFAB43CWXEGI5SAI","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":"c908887ffd0a8d4bafd49f4566a335ef1fb430f706baab6f2bba3ee62a70063c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T01:15:57Z","title_canon_sha256":"6b5e9624e89474ec7b4bb24dc3c20fc9a65db1e13680daef8e9ddcdebbaa527b"},"schema_version":"1.0","source":{"id":"2101.03236","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2101.03236","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"arxiv_version","alias_value":"2101.03236v1","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2101.03236","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"pith_short_12","alias_value":"5YMKGESBJSJF","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"pith_short_16","alias_value":"5YMKGESBJSJFAB43","created_at":"2026-07-05T02:05:47Z"},{"alias_kind":"pith_short_8","alias_value":"5YMKGESB","created_at":"2026-07-05T02:05:47Z"}],"graph_snapshots":[{"event_id":"sha256:c8b0d0987fad813b6575691d8e4478c026a445a15395fc8ab3f528b3e4d233b0","target":"graph","created_at":"2026-07-05T02:05:47Z","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/2101.03236/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Data augmentation has been widely used to improve deep neural networks in many research fields, such as computer vision. However, less work has been done in the context of text, partially due to its discrete nature and the complexity of natural languages. In this paper, we propose to improve the standard maximum likelihood estimation (MLE) paradigm by incorporating a self-imitation-learning phase for automatic data augmentation. Unlike most existing sentence-level augmentation strategies, which are only applied to specific models, our method is more general and could be easily adapted to any M","authors_text":"Changyou Chen, Chunyuan Li, Ping Yu, Ruiyi Zhang, Yang Zhao, Yizhe Zhang","cross_cats":["cs.LG"],"headline":"","license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T01:15:57Z","title":"SDA: Improving Text Generation with Self Data Augmentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2101.03236","kind":"arxiv","version":1},"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":"sha256:2536b6faa8a04eaddede93876741ecea0fcaf5b4fc6bdecedab4bf7886a03f70","target":"record","created_at":"2026-07-05T02:05:47Z","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":"c908887ffd0a8d4bafd49f4566a335ef1fb430f706baab6f2bba3ee62a70063c","cross_cats_sorted":["cs.LG"],"license":"http://creativecommons.org/publicdomain/zero/1.0/","primary_cat":"cs.CL","submitted_at":"2021-01-02T01:15:57Z","title_canon_sha256":"6b5e9624e89474ec7b4bb24dc3c20fc9a65db1e13680daef8e9ddcdebbaa527b"},"schema_version":"1.0","source":{"id":"2101.03236","kind":"arxiv","version":1}},"canonical_sha256":"ee18a312414c9250079b15ae4323b20205fc1312d70df60de007aa1d52ba7d33","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ee18a312414c9250079b15ae4323b20205fc1312d70df60de007aa1d52ba7d33","first_computed_at":"2026-07-05T02:05:47.497437Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:05:47.497437Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"vkOefPjQvYPwMtgcHeWVKKvTt6LTEnQbe3S5HJxJK4YdszFhzrp3ODiT/4K0T5/e1/FD9Sib1LAMvtNR4FqXCQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:05:47.497856Z","signed_message":"canonical_sha256_bytes"},"source_id":"2101.03236","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:2536b6faa8a04eaddede93876741ecea0fcaf5b4fc6bdecedab4bf7886a03f70","sha256:c8b0d0987fad813b6575691d8e4478c026a445a15395fc8ab3f528b3e4d233b0"],"state_sha256":"fa8c1e74d9becfb38e9698360b21444716d428fd790588039700040a2e606a07"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"3nHBWh3RctaTMQrec+3fA7nGHBTb50o3Crnm6ozgsNb8Kuwo3CUsrCFS7epvy4aisanSSrD0yK+caKJEQ8BMBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-07-14T09:30:00.407085Z","bundle_sha256":"2cf0627139cc9276691cd6f592f4fc600c913e3680310d04890aed46ca2cc45a"}}