{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:6IGZQFP2IHMIKWPDRO3GY2JTT7","short_pith_number":"pith:6IGZQFP2","canonical_record":{"source":{"id":"1808.09006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:27:01Z","cross_cats_sorted":[],"title_canon_sha256":"924ecc4457f75fd0b1cfb886ea9fd871882eff0aa0c2fbc0d5a38c6ffd2d1654","abstract_canon_sha256":"7aed345fd452a8b26e20055fc9ccdd54c71410fa3c8f0ee88f4119cbac909cb5"},"schema_version":"1.0"},"canonical_sha256":"f20d9815fa41d88559e38bb66c69339ff5cc7e9d965d5b4aae514a6510c68952","source":{"kind":"arxiv","id":"1808.09006","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09006","created_at":"2026-05-18T00:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09006v2","created_at":"2026-05-18T00:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09006","created_at":"2026-05-18T00:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"6IGZQFP2IHMI","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6IGZQFP2IHMIKWPD","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6IGZQFP2","created_at":"2026-05-18T12:32:08Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:6IGZQFP2IHMIKWPDRO3GY2JTT7","target":"record","payload":{"canonical_record":{"source":{"id":"1808.09006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:27:01Z","cross_cats_sorted":[],"title_canon_sha256":"924ecc4457f75fd0b1cfb886ea9fd871882eff0aa0c2fbc0d5a38c6ffd2d1654","abstract_canon_sha256":"7aed345fd452a8b26e20055fc9ccdd54c71410fa3c8f0ee88f4119cbac909cb5"},"schema_version":"1.0"},"canonical_sha256":"f20d9815fa41d88559e38bb66c69339ff5cc7e9d965d5b4aae514a6510c68952","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:05:13.702349Z","signature_b64":"w8SH9OVWRVwxQIshMM24U0A5weHvH8xYnNvAkUJtLygDwuzgS3k1DBE8LVLobaBz08/7NR4JYgD2WFZ+PKdKAA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"f20d9815fa41d88559e38bb66c69339ff5cc7e9d965d5b4aae514a6510c68952","last_reissued_at":"2026-05-18T00:05:13.701675Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:05:13.701675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.09006","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":"2026-05-18T00:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"diVTba6FU76dtqb6cEl5kkDvUUZHTabhb7KHIDZRIdwiVlJofLywjDUg4uCxzK4JafD+o02YGRhEh+KqOwB2Dg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:35:35.121210Z"},"content_sha256":"8e4c9f363bc596475dc3325c2f8fe4a52f839a0895020d33af8fcf7fa544f478","schema_version":"1.0","event_id":"sha256:8e4c9f363bc596475dc3325c2f8fe4a52f839a0895020d33af8fcf7fa544f478"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:6IGZQFP2IHMIKWPDRO3GY2JTT7","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Christof Monz, Marzieh Fadaee","submitted_at":"2018-08-27T19:27:01Z","abstract_excerpt":"Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from monolingual data using a reverse translation model. While back-translation has been shown to be very effective in many cases, it is not entirely clear why. In this work, we explore different aspects of back-translation, and show that words with high prediction loss during training benefit most from the addition of synthetic data. We introduce several variations of"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09006","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":"2026-05-18T00:05:13Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QFeZqbEZlFSNppZgOZUtW/Lzhk9f52B5cb5OZ8+Ubr9o88I/CN7fvjBsZpVYvd1rBTwhgrexgwqxNmgzljR9Cw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T03:35:35.121864Z"},"content_sha256":"432c60dcea3f06d406dafad3200c7cc026541be6fc9e2716d8682f2c7341a36f","schema_version":"1.0","event_id":"sha256:432c60dcea3f06d406dafad3200c7cc026541be6fc9e2716d8682f2c7341a36f"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/6IGZQFP2IHMIKWPDRO3GY2JTT7/bundle.json","state_url":"https://pith.science/pith/6IGZQFP2IHMIKWPDRO3GY2JTT7/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/6IGZQFP2IHMIKWPDRO3GY2JTT7/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":"2026-05-26T03:35:35Z","links":{"resolver":"https://pith.science/pith/6IGZQFP2IHMIKWPDRO3GY2JTT7","bundle":"https://pith.science/pith/6IGZQFP2IHMIKWPDRO3GY2JTT7/bundle.json","state":"https://pith.science/pith/6IGZQFP2IHMIKWPDRO3GY2JTT7/state.json","well_known_bundle":"https://pith.science/.well-known/pith/6IGZQFP2IHMIKWPDRO3GY2JTT7/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:6IGZQFP2IHMIKWPDRO3GY2JTT7","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":"7aed345fd452a8b26e20055fc9ccdd54c71410fa3c8f0ee88f4119cbac909cb5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:27:01Z","title_canon_sha256":"924ecc4457f75fd0b1cfb886ea9fd871882eff0aa0c2fbc0d5a38c6ffd2d1654"},"schema_version":"1.0","source":{"id":"1808.09006","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.09006","created_at":"2026-05-18T00:05:13Z"},{"alias_kind":"arxiv_version","alias_value":"1808.09006v2","created_at":"2026-05-18T00:05:13Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.09006","created_at":"2026-05-18T00:05:13Z"},{"alias_kind":"pith_short_12","alias_value":"6IGZQFP2IHMI","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_16","alias_value":"6IGZQFP2IHMIKWPD","created_at":"2026-05-18T12:32:08Z"},{"alias_kind":"pith_short_8","alias_value":"6IGZQFP2","created_at":"2026-05-18T12:32:08Z"}],"graph_snapshots":[{"event_id":"sha256:432c60dcea3f06d406dafad3200c7cc026541be6fc9e2716d8682f2c7341a36f","target":"graph","created_at":"2026-05-18T00:05:13Z","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":"Neural Machine Translation has achieved state-of-the-art performance for several language pairs using a combination of parallel and synthetic data. Synthetic data is often generated by back-translating sentences randomly sampled from monolingual data using a reverse translation model. While back-translation has been shown to be very effective in many cases, it is not entirely clear why. In this work, we explore different aspects of back-translation, and show that words with high prediction loss during training benefit most from the addition of synthetic data. We introduce several variations of","authors_text":"Christof Monz, Marzieh Fadaee","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:27:01Z","title":"Back-Translation Sampling by Targeting Difficult Words in Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.09006","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":"sha256:8e4c9f363bc596475dc3325c2f8fe4a52f839a0895020d33af8fcf7fa544f478","target":"record","created_at":"2026-05-18T00:05:13Z","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":"7aed345fd452a8b26e20055fc9ccdd54c71410fa3c8f0ee88f4119cbac909cb5","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-27T19:27:01Z","title_canon_sha256":"924ecc4457f75fd0b1cfb886ea9fd871882eff0aa0c2fbc0d5a38c6ffd2d1654"},"schema_version":"1.0","source":{"id":"1808.09006","kind":"arxiv","version":2}},"canonical_sha256":"f20d9815fa41d88559e38bb66c69339ff5cc7e9d965d5b4aae514a6510c68952","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f20d9815fa41d88559e38bb66c69339ff5cc7e9d965d5b4aae514a6510c68952","first_computed_at":"2026-05-18T00:05:13.701675Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:05:13.701675Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"w8SH9OVWRVwxQIshMM24U0A5weHvH8xYnNvAkUJtLygDwuzgS3k1DBE8LVLobaBz08/7NR4JYgD2WFZ+PKdKAA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:05:13.702349Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.09006","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:8e4c9f363bc596475dc3325c2f8fe4a52f839a0895020d33af8fcf7fa544f478","sha256:432c60dcea3f06d406dafad3200c7cc026541be6fc9e2716d8682f2c7341a36f"],"state_sha256":"e22a4a65f3ab3d29b89df639fbe6373c04fe525c492b50a5a00b9649c8bbd78e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FR1z0ybRzDd2nzxzEHjb2gOll2U2RhlouKJzVyjvx8tY1w3GQkn4hdQGowzme1GkcIfVLbwBAx9ASyhs1aIFDA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T03:35:35.125394Z","bundle_sha256":"f49631be99ca1774bfa2e4a70ccc6d6e4e05de8725dab1378e56fe9205a1f6be"}}