{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:25NKHBGVPCBOICZ6ELB34E3HZ7","short_pith_number":"pith:25NKHBGV","canonical_record":{"source":{"id":"1804.06189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T12:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"4d2c1b3d35616fd0c157df0b1556053c135d8ae70ddf2adadff5b504a74b32f1","abstract_canon_sha256":"e532a7a58a0c8dc4347309c9b3be20b6faf2a2d4030ec350d3adc6c980ebdcfa"},"schema_version":"1.0"},"canonical_sha256":"d75aa384d57882e40b3e22c3be1367cfe166f9fc4ea6555a7e4d93068532f14d","source":{"kind":"arxiv","id":"1804.06189","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06189","created_at":"2026-05-18T00:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06189v1","created_at":"2026-05-18T00:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06189","created_at":"2026-05-18T00:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"25NKHBGVPCBO","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"25NKHBGVPCBOICZ6","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"25NKHBGV","created_at":"2026-05-18T12:31:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:25NKHBGVPCBOICZ6ELB34E3HZ7","target":"record","payload":{"canonical_record":{"source":{"id":"1804.06189","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T12:16:25Z","cross_cats_sorted":[],"title_canon_sha256":"4d2c1b3d35616fd0c157df0b1556053c135d8ae70ddf2adadff5b504a74b32f1","abstract_canon_sha256":"e532a7a58a0c8dc4347309c9b3be20b6faf2a2d4030ec350d3adc6c980ebdcfa"},"schema_version":"1.0"},"canonical_sha256":"d75aa384d57882e40b3e22c3be1367cfe166f9fc4ea6555a7e4d93068532f14d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:21.426184Z","signature_b64":"U7QP77chSshk2Se/15s4Hxin2iaB7GBwgnibWn780ELYrKGi6rlmikbcedQtlKKHGTLR3l/U8b5/lEPmD66hCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d75aa384d57882e40b3e22c3be1367cfe166f9fc4ea6555a7e4d93068532f14d","last_reissued_at":"2026-05-18T00:18:21.425532Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:21.425532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.06189","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":"2026-05-18T00:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"p27bXedmDtKgLAGuu2/I+06MF/IKB1UqK3yDsS9cpcqzZzYbrgb1uhlDlbMafJoRcEAaCEVheYzPBJmXrdnmDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:23:21.975272Z"},"content_sha256":"accad7caf7bf94e2d20c054d48e1df3c9d2258a2da1f66ccea974c63c6065bb6","schema_version":"1.0","event_id":"sha256:accad7caf7bf94e2d20c054d48e1df3c9d2258a2da1f66ccea974c63c6065bb6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:25NKHBGVPCBOICZ6ELB34E3HZ7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Investigating Backtranslation in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alberto Poncelas, Andy Way, Dimitar Shterionov, Gideon Maillette de Buy Wenniger, Peyman Passban","submitted_at":"2018-04-17T12:16:25Z","abstract_excerpt":"A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT has been shown in many studies to outperform SMT, but mostly when large parallel corpora are available; in cases where data is limited, SMT can still outperform NMT.\n  Recently researchers have shown that back-translating monolingual data can be used to create synthetic parallel corpora, which in turn can be used in combination with authentic parallel data "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06189","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":"2026-05-18T00:18:21Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nLudN/WCU0SrWDcGWWlPD16muzojetxbsdi9L38nxHi8ILo5f7SNhWpdzqCnKD+D6KYCbPaJTdtLTGKHANGRDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-02T01:23:21.975628Z"},"content_sha256":"a736d180e4da809b34c4b006cf5347a02b668669558780139be11d02c633f6b3","schema_version":"1.0","event_id":"sha256:a736d180e4da809b34c4b006cf5347a02b668669558780139be11d02c633f6b3"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/25NKHBGVPCBOICZ6ELB34E3HZ7/bundle.json","state_url":"https://pith.science/pith/25NKHBGVPCBOICZ6ELB34E3HZ7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/25NKHBGVPCBOICZ6ELB34E3HZ7/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":"2026-06-02T01:23:21Z","links":{"resolver":"https://pith.science/pith/25NKHBGVPCBOICZ6ELB34E3HZ7","bundle":"https://pith.science/pith/25NKHBGVPCBOICZ6ELB34E3HZ7/bundle.json","state":"https://pith.science/pith/25NKHBGVPCBOICZ6ELB34E3HZ7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/25NKHBGVPCBOICZ6ELB34E3HZ7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:25NKHBGVPCBOICZ6ELB34E3HZ7","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":"e532a7a58a0c8dc4347309c9b3be20b6faf2a2d4030ec350d3adc6c980ebdcfa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T12:16:25Z","title_canon_sha256":"4d2c1b3d35616fd0c157df0b1556053c135d8ae70ddf2adadff5b504a74b32f1"},"schema_version":"1.0","source":{"id":"1804.06189","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06189","created_at":"2026-05-18T00:18:21Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06189v1","created_at":"2026-05-18T00:18:21Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06189","created_at":"2026-05-18T00:18:21Z"},{"alias_kind":"pith_short_12","alias_value":"25NKHBGVPCBO","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_16","alias_value":"25NKHBGVPCBOICZ6","created_at":"2026-05-18T12:31:59Z"},{"alias_kind":"pith_short_8","alias_value":"25NKHBGV","created_at":"2026-05-18T12:31:59Z"}],"graph_snapshots":[{"event_id":"sha256:a736d180e4da809b34c4b006cf5347a02b668669558780139be11d02c633f6b3","target":"graph","created_at":"2026-05-18T00:18:21Z","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":"A prerequisite for training corpus-based machine translation (MT) systems -- either Statistical MT (SMT) or Neural MT (NMT) -- is the availability of high-quality parallel data. This is arguably more important today than ever before, as NMT has been shown in many studies to outperform SMT, but mostly when large parallel corpora are available; in cases where data is limited, SMT can still outperform NMT.\n  Recently researchers have shown that back-translating monolingual data can be used to create synthetic parallel corpora, which in turn can be used in combination with authentic parallel data ","authors_text":"Alberto Poncelas, Andy Way, Dimitar Shterionov, Gideon Maillette de Buy Wenniger, Peyman Passban","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T12:16:25Z","title":"Investigating Backtranslation in Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06189","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:accad7caf7bf94e2d20c054d48e1df3c9d2258a2da1f66ccea974c63c6065bb6","target":"record","created_at":"2026-05-18T00:18:21Z","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":"e532a7a58a0c8dc4347309c9b3be20b6faf2a2d4030ec350d3adc6c980ebdcfa","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T12:16:25Z","title_canon_sha256":"4d2c1b3d35616fd0c157df0b1556053c135d8ae70ddf2adadff5b504a74b32f1"},"schema_version":"1.0","source":{"id":"1804.06189","kind":"arxiv","version":1}},"canonical_sha256":"d75aa384d57882e40b3e22c3be1367cfe166f9fc4ea6555a7e4d93068532f14d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d75aa384d57882e40b3e22c3be1367cfe166f9fc4ea6555a7e4d93068532f14d","first_computed_at":"2026-05-18T00:18:21.425532Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:21.425532Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"U7QP77chSshk2Se/15s4Hxin2iaB7GBwgnibWn780ELYrKGi6rlmikbcedQtlKKHGTLR3l/U8b5/lEPmD66hCQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:21.426184Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.06189","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:accad7caf7bf94e2d20c054d48e1df3c9d2258a2da1f66ccea974c63c6065bb6","sha256:a736d180e4da809b34c4b006cf5347a02b668669558780139be11d02c633f6b3"],"state_sha256":"4e574b03f0bca32afcb0289f9d9c2e01d9dc678a151923f55ffad6f36175baf9"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"qd8CxDKtMqNsQIKx0ErECBD8Z1lvZaJQKlTg3tDixK60BDAKzicJxqYCZm2R+wEqj6REwrQ/jb4Z/iyIYCUdDg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-02T01:23:21.977548Z","bundle_sha256":"17282a3a38622ea1cf9293b4d786f0c5c4004277c53acdda60095037c1189d4c"}}