{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2019:OCGGOOLS3LMFURDIZOF2XQTOX3","short_pith_number":"pith:OCGGOOLS","canonical_record":{"source":{"id":"1905.10523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-25T05:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"cbec86f89dacb476775615ffcc6be9f2ed453a640aa431b511a46a684891c919","abstract_canon_sha256":"7bdb15ac540744ecea9a6771708dfacdf5d0557d7df2258f71072e1399b2d915"},"schema_version":"1.0"},"canonical_sha256":"708c673972dad85a4468cb8babc26ebefaa79cb2bd836c55ac119d3353c9b67a","source":{"kind":"arxiv","id":"1905.10523","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10523","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10523v1","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10523","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"OCGGOOLS3LMF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OCGGOOLS3LMFURDI","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OCGGOOLS","created_at":"2026-05-18T12:33:24Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2019:OCGGOOLS3LMFURDIZOF2XQTOX3","target":"record","payload":{"canonical_record":{"source":{"id":"1905.10523","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-25T05:28:03Z","cross_cats_sorted":[],"title_canon_sha256":"cbec86f89dacb476775615ffcc6be9f2ed453a640aa431b511a46a684891c919","abstract_canon_sha256":"7bdb15ac540744ecea9a6771708dfacdf5d0557d7df2258f71072e1399b2d915"},"schema_version":"1.0"},"canonical_sha256":"708c673972dad85a4468cb8babc26ebefaa79cb2bd836c55ac119d3353c9b67a","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:45:08.238244Z","signature_b64":"/Ujmk7rJJE80UVeWNAij7ujIYZE1AImg74srUcesOTPK9KfOMP9B/nfuG4+GB3jU6jOS2drdpc25U2NDjf+aAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"708c673972dad85a4468cb8babc26ebefaa79cb2bd836c55ac119d3353c9b67a","last_reissued_at":"2026-05-17T23:45:08.237534Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:45:08.237534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1905.10523","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":"2026-05-17T23:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zigaXqrrZXf01tAyjASp3z6GYb5RQuL1UqDpjjK64WXfdH7mdUEiSyIgFX6RCIkSbEBihr56jXih+URnVQ0bBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:43:47.169585Z"},"content_sha256":"6d79adf964897e47a43394e8cc457b0c15ed12f6bf4d2072b70cf9334161a8e5","schema_version":"1.0","event_id":"sha256:6d79adf964897e47a43394e8cc457b0c15ed12f6bf4d2072b70cf9334161a8e5"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2019:OCGGOOLS3LMFURDIZOF2XQTOX3","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Soft Contextual Data Augmentation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fei Gao, Jinhua Zhu, Lijun Wu, Tao Qin, Tie-Yan Liu, Wengang Zhou, Xueqi Cheng, Yingce Xia","submitted_at":"2019-05-25T05:28:03Z","abstract_excerpt":"While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for neural machine translation. Different from previous augmentation methods that randomly drop, swap or replace words with other words in a sentence, we softly augment a randomly chosen word in a sentence by its contextual mixture of multiple related words. More accurately, we replace the one-hot representation of a word by a distribution (provided by a langua"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10523","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":""},"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":"2026-05-17T23:45:08Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"zETe3BZ1Ji//WelLCvviYfEo/83MoqHYtmk+NvrVt1KrK1c2mpQvQUWm0z49WtJzMAOT7cttTnGAWpS/lSnDAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-27T13:43:47.170251Z"},"content_sha256":"b004bfbfb917611bae1e55fbd934ac44cff3798e584dd855e7e54a3053199c90","schema_version":"1.0","event_id":"sha256:b004bfbfb917611bae1e55fbd934ac44cff3798e584dd855e7e54a3053199c90"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OCGGOOLS3LMFURDIZOF2XQTOX3/bundle.json","state_url":"https://pith.science/pith/OCGGOOLS3LMFURDIZOF2XQTOX3/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OCGGOOLS3LMFURDIZOF2XQTOX3/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":"2026-05-27T13:43:47Z","links":{"resolver":"https://pith.science/pith/OCGGOOLS3LMFURDIZOF2XQTOX3","bundle":"https://pith.science/pith/OCGGOOLS3LMFURDIZOF2XQTOX3/bundle.json","state":"https://pith.science/pith/OCGGOOLS3LMFURDIZOF2XQTOX3/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OCGGOOLS3LMFURDIZOF2XQTOX3/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2019:OCGGOOLS3LMFURDIZOF2XQTOX3","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":"7bdb15ac540744ecea9a6771708dfacdf5d0557d7df2258f71072e1399b2d915","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-25T05:28:03Z","title_canon_sha256":"cbec86f89dacb476775615ffcc6be9f2ed453a640aa431b511a46a684891c919"},"schema_version":"1.0","source":{"id":"1905.10523","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1905.10523","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"arxiv_version","alias_value":"1905.10523v1","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1905.10523","created_at":"2026-05-17T23:45:08Z"},{"alias_kind":"pith_short_12","alias_value":"OCGGOOLS3LMF","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_16","alias_value":"OCGGOOLS3LMFURDI","created_at":"2026-05-18T12:33:24Z"},{"alias_kind":"pith_short_8","alias_value":"OCGGOOLS","created_at":"2026-05-18T12:33:24Z"}],"graph_snapshots":[{"event_id":"sha256:b004bfbfb917611bae1e55fbd934ac44cff3798e584dd855e7e54a3053199c90","target":"graph","created_at":"2026-05-17T23:45:08Z","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"},"paper":{"abstract_excerpt":"While data augmentation is an important trick to boost the accuracy of deep learning methods in computer vision tasks, its study in natural language tasks is still very limited. In this paper, we present a novel data augmentation method for neural machine translation. Different from previous augmentation methods that randomly drop, swap or replace words with other words in a sentence, we softly augment a randomly chosen word in a sentence by its contextual mixture of multiple related words. More accurately, we replace the one-hot representation of a word by a distribution (provided by a langua","authors_text":"Fei Gao, Jinhua Zhu, Lijun Wu, Tao Qin, Tie-Yan Liu, Wengang Zhou, Xueqi Cheng, Yingce Xia","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-25T05:28:03Z","title":"Soft Contextual Data Augmentation for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1905.10523","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":"sha256:6d79adf964897e47a43394e8cc457b0c15ed12f6bf4d2072b70cf9334161a8e5","target":"record","created_at":"2026-05-17T23:45:08Z","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":"7bdb15ac540744ecea9a6771708dfacdf5d0557d7df2258f71072e1399b2d915","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2019-05-25T05:28:03Z","title_canon_sha256":"cbec86f89dacb476775615ffcc6be9f2ed453a640aa431b511a46a684891c919"},"schema_version":"1.0","source":{"id":"1905.10523","kind":"arxiv","version":1}},"canonical_sha256":"708c673972dad85a4468cb8babc26ebefaa79cb2bd836c55ac119d3353c9b67a","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"708c673972dad85a4468cb8babc26ebefaa79cb2bd836c55ac119d3353c9b67a","first_computed_at":"2026-05-17T23:45:08.237534Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:45:08.237534Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/Ujmk7rJJE80UVeWNAij7ujIYZE1AImg74srUcesOTPK9KfOMP9B/nfuG4+GB3jU6jOS2drdpc25U2NDjf+aAQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:45:08.238244Z","signed_message":"canonical_sha256_bytes"},"source_id":"1905.10523","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6d79adf964897e47a43394e8cc457b0c15ed12f6bf4d2072b70cf9334161a8e5","sha256:b004bfbfb917611bae1e55fbd934ac44cff3798e584dd855e7e54a3053199c90"],"state_sha256":"0a727a864f62cedece5afdb88baf0a8416e2b4ee1d2675c114e8a04e79cee3a4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"DtZ4XxhQ5wemLRwIKTn9UvoR3TCaBrBn4Uvs6tu338CsmqtKkVbfBHM0Ms3hEy396w6EGBnbZX6kvHAMn2QvBA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-27T13:43:47.173346Z","bundle_sha256":"5f7ef9e57a7fcd482a13574a6a26a7592d404e419f83618620c38dbe1be6e87d"}}