{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:ABBSNBBEFV7N6OY7Y4MLRZUDQD","short_pith_number":"pith:ABBSNBBE","canonical_record":{"source":{"id":"1808.07512","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-22T18:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"000c7186b667d3acbceca645f0f99be806ff6a18a87b38defece417582ffe7df","abstract_canon_sha256":"dd6a605be6892953836cac77cad63f9037418955cbdd47424e0d9116ad4c542a"},"schema_version":"1.0"},"canonical_sha256":"00432684242d7edf3b1fc718b8e68380fab5c77e51b939b7d11b6cd529ff4d65","source":{"kind":"arxiv","id":"1808.07512","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07512","created_at":"2026-05-18T00:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07512v2","created_at":"2026-05-18T00:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07512","created_at":"2026-05-18T00:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"ABBSNBBEFV7N","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ABBSNBBEFV7N6OY7","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ABBSNBBE","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:ABBSNBBEFV7N6OY7Y4MLRZUDQD","target":"record","payload":{"canonical_record":{"source":{"id":"1808.07512","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-22T18:26:43Z","cross_cats_sorted":[],"title_canon_sha256":"000c7186b667d3acbceca645f0f99be806ff6a18a87b38defece417582ffe7df","abstract_canon_sha256":"dd6a605be6892953836cac77cad63f9037418955cbdd47424e0d9116ad4c542a"},"schema_version":"1.0"},"canonical_sha256":"00432684242d7edf3b1fc718b8e68380fab5c77e51b939b7d11b6cd529ff4d65","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:05.195142Z","signature_b64":"3BftBU1u4Qt/VzcmTwes6fAttP/meT0G+CsU6HxDYT+Gz8KyMgIBFNHkNwBrKsrijV5BkqszHfNVC307xRadBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"00432684242d7edf3b1fc718b8e68380fab5c77e51b939b7d11b6cd529ff4d65","last_reissued_at":"2026-05-18T00:07:05.194420Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:05.194420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.07512","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":"2026-05-18T00:07:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9MwKT3dUTnfHqfFUZaV9T1Ed3VbYPOKoL/kFLm6tFA0K72D91Nttr7qqEtwQas3KNipFJCcXVay1bZOvdQwBAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:54:41.762216Z"},"content_sha256":"4daacac05802e5907ce7b3acd27dfe56b6850838824f6b9873d9f6970c593f87","schema_version":"1.0","event_id":"sha256:4daacac05802e5907ce7b3acd27dfe56b6850838824f6b9873d9f6970c593f87"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:ABBSNBBEFV7N6OY7Y4MLRZUDQD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Hieu Pham, Xinyi Wang, Zihang Dai","submitted_at":"2018-08-22T18:26:43Z","abstract_excerpt":"In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07512","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":""},"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":"2026-05-18T00:07:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"CTOcw19cL29k6R2RHvx/4iUwcy0ugcqd2KAKE54okFRER+MIbPWQdAQm2uaonGtuJ9tUeegBWGmd33WZkFC3CA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T11:54:41.762585Z"},"content_sha256":"52b9e823da3deb97324dc02c7ca5babfc59545a1ca243bcde90437f49513989e","schema_version":"1.0","event_id":"sha256:52b9e823da3deb97324dc02c7ca5babfc59545a1ca243bcde90437f49513989e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/bundle.json","state_url":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/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":"2026-05-26T11:54:41Z","links":{"resolver":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD","bundle":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/bundle.json","state":"https://pith.science/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ABBSNBBEFV7N6OY7Y4MLRZUDQD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:ABBSNBBEFV7N6OY7Y4MLRZUDQD","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":"dd6a605be6892953836cac77cad63f9037418955cbdd47424e0d9116ad4c542a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-22T18:26:43Z","title_canon_sha256":"000c7186b667d3acbceca645f0f99be806ff6a18a87b38defece417582ffe7df"},"schema_version":"1.0","source":{"id":"1808.07512","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.07512","created_at":"2026-05-18T00:07:05Z"},{"alias_kind":"arxiv_version","alias_value":"1808.07512v2","created_at":"2026-05-18T00:07:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.07512","created_at":"2026-05-18T00:07:05Z"},{"alias_kind":"pith_short_12","alias_value":"ABBSNBBEFV7N","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"ABBSNBBEFV7N6OY7","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"ABBSNBBE","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:52b9e823da3deb97324dc02c7ca5babfc59545a1ca243bcde90437f49513989e","target":"graph","created_at":"2026-05-18T00:07:05Z","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":"In this work, we examine methods for data augmentation for text-based tasks such as neural machine translation (NMT). We formulate the design of a data augmentation policy with desirable properties as an optimization problem, and derive a generic analytic solution. This solution not only subsumes some existing augmentation schemes, but also leads to an extremely simple data augmentation strategy for NMT: randomly replacing words in both the source sentence and the target sentence with other random words from their corresponding vocabularies. We name this method SwitchOut. Experiments on three ","authors_text":"Graham Neubig, Hieu Pham, Xinyi Wang, Zihang Dai","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-22T18:26:43Z","title":"SwitchOut: an Efficient Data Augmentation Algorithm for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.07512","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":"sha256:4daacac05802e5907ce7b3acd27dfe56b6850838824f6b9873d9f6970c593f87","target":"record","created_at":"2026-05-18T00:07:05Z","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":"dd6a605be6892953836cac77cad63f9037418955cbdd47424e0d9116ad4c542a","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-22T18:26:43Z","title_canon_sha256":"000c7186b667d3acbceca645f0f99be806ff6a18a87b38defece417582ffe7df"},"schema_version":"1.0","source":{"id":"1808.07512","kind":"arxiv","version":2}},"canonical_sha256":"00432684242d7edf3b1fc718b8e68380fab5c77e51b939b7d11b6cd529ff4d65","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"00432684242d7edf3b1fc718b8e68380fab5c77e51b939b7d11b6cd529ff4d65","first_computed_at":"2026-05-18T00:07:05.194420Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:05.194420Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3BftBU1u4Qt/VzcmTwes6fAttP/meT0G+CsU6HxDYT+Gz8KyMgIBFNHkNwBrKsrijV5BkqszHfNVC307xRadBw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:05.195142Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.07512","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4daacac05802e5907ce7b3acd27dfe56b6850838824f6b9873d9f6970c593f87","sha256:52b9e823da3deb97324dc02c7ca5babfc59545a1ca243bcde90437f49513989e"],"state_sha256":"85bc9ffa9964b20751cf0d97f3499a21482f443ebb7eaeda8e26b3c12d648ac4"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Y+pqyCX4r5W7TZPJNHuhy89Yihx9my76luc02JWWYAA+5iC4DI1dTTS44sPRBQqqPN3rpvdHXDtE6z9PftR7Ag==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T11:54:41.764796Z","bundle_sha256":"cc276e5d9981c54ba65eb3626d51f2f48ae7bb9722a7b572fbb8c3a3bb4788e9"}}