{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:IMB6CTUGE232XSODFEBVOJLZEQ","short_pith_number":"pith:IMB6CTUG","canonical_record":{"source":{"id":"1604.02201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-08T00:16:35Z","cross_cats_sorted":[],"title_canon_sha256":"5c27510fb659f24b98659e765b6e76f2f1e40a948f2741192809cb4cd809b3c9","abstract_canon_sha256":"e9cc69d08b93f8c7f3e3cfa903f45876b132f9feee29181f1bcdca3cf5d5eab9"},"schema_version":"1.0"},"canonical_sha256":"4303e14e8626b7abc9c32903572579240c1cc1a2e9b1370eb3e7676464eeaa40","source":{"kind":"arxiv","id":"1604.02201","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.02201","created_at":"2026-05-18T01:17:28Z"},{"alias_kind":"arxiv_version","alias_value":"1604.02201v1","created_at":"2026-05-18T01:17:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02201","created_at":"2026-05-18T01:17:28Z"},{"alias_kind":"pith_short_12","alias_value":"IMB6CTUGE232","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IMB6CTUGE232XSOD","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IMB6CTUG","created_at":"2026-05-18T12:30:22Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:IMB6CTUGE232XSODFEBVOJLZEQ","target":"record","payload":{"canonical_record":{"source":{"id":"1604.02201","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-08T00:16:35Z","cross_cats_sorted":[],"title_canon_sha256":"5c27510fb659f24b98659e765b6e76f2f1e40a948f2741192809cb4cd809b3c9","abstract_canon_sha256":"e9cc69d08b93f8c7f3e3cfa903f45876b132f9feee29181f1bcdca3cf5d5eab9"},"schema_version":"1.0"},"canonical_sha256":"4303e14e8626b7abc9c32903572579240c1cc1a2e9b1370eb3e7676464eeaa40","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:17:28.235768Z","signature_b64":"s3jUeRgU5V5vqADWD7yN5FbsHorHRkdH8GZUl/su3eEpGj36JYz1zbwWOKvIkWYwu4CHuiAyrJMg/3n9tbI+BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4303e14e8626b7abc9c32903572579240c1cc1a2e9b1370eb3e7676464eeaa40","last_reissued_at":"2026-05-18T01:17:28.235108Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:17:28.235108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1604.02201","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":"2026-05-18T01:17:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"tGWsJ6Vq1yNU8tFxtR1ltHPXUwBS277ab8Pwr7hifj1ZudD80JPiBL00OH1LyydAihMToYJTWwPYSxt/QNy4AA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T17:19:52.105071Z"},"content_sha256":"e9fe19fab98019d104805408f62c65edf873d7addaca31163cabd4a5e1e9b6c6","schema_version":"1.0","event_id":"sha256:e9fe19fab98019d104805408f62c65edf873d7addaca31163cabd4a5e1e9b6c6"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:IMB6CTUGE232XSODFEBVOJLZEQ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Transfer Learning for Low-Resource Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Barret Zoph, Deniz Yuret, Jonathan May, Kevin Knight","submitted_at":"2016-04-08T00:16:35Z","abstract_excerpt":"The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves Bleu scores across a range of low-resource languages. Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training. Using our transfer learning method we improve baseline NMT models by an average of 5.6 Bleu on four l"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02201","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":"2026-05-18T01:17:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ce22rRHApYhO23X9NV+xA3NldzvojA3Ac5j7xLWwgLrQTmPQ6yUY2rm6nMuVlQB4HSyMZ59pxE6d/AY61kSWBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-20T17:19:52.105616Z"},"content_sha256":"090f24e97f72d2c6ec170976e7397a1d811493d647637e3323a7e7751cdf407a","schema_version":"1.0","event_id":"sha256:090f24e97f72d2c6ec170976e7397a1d811493d647637e3323a7e7751cdf407a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/bundle.json","state_url":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IMB6CTUGE232XSODFEBVOJLZEQ/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":"2026-05-20T17:19:52Z","links":{"resolver":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ","bundle":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/bundle.json","state":"https://pith.science/pith/IMB6CTUGE232XSODFEBVOJLZEQ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IMB6CTUGE232XSODFEBVOJLZEQ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:IMB6CTUGE232XSODFEBVOJLZEQ","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":"e9cc69d08b93f8c7f3e3cfa903f45876b132f9feee29181f1bcdca3cf5d5eab9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-08T00:16:35Z","title_canon_sha256":"5c27510fb659f24b98659e765b6e76f2f1e40a948f2741192809cb4cd809b3c9"},"schema_version":"1.0","source":{"id":"1604.02201","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1604.02201","created_at":"2026-05-18T01:17:28Z"},{"alias_kind":"arxiv_version","alias_value":"1604.02201v1","created_at":"2026-05-18T01:17:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1604.02201","created_at":"2026-05-18T01:17:28Z"},{"alias_kind":"pith_short_12","alias_value":"IMB6CTUGE232","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_16","alias_value":"IMB6CTUGE232XSOD","created_at":"2026-05-18T12:30:22Z"},{"alias_kind":"pith_short_8","alias_value":"IMB6CTUG","created_at":"2026-05-18T12:30:22Z"}],"graph_snapshots":[{"event_id":"sha256:090f24e97f72d2c6ec170976e7397a1d811493d647637e3323a7e7751cdf407a","target":"graph","created_at":"2026-05-18T01:17:28Z","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":"The encoder-decoder framework for neural machine translation (NMT) has been shown effective in large data scenarios, but is much less effective for low-resource languages. We present a transfer learning method that significantly improves Bleu scores across a range of low-resource languages. Our key idea is to first train a high-resource language pair (the parent model), then transfer some of the learned parameters to the low-resource pair (the child model) to initialize and constrain training. Using our transfer learning method we improve baseline NMT models by an average of 5.6 Bleu on four l","authors_text":"Barret Zoph, Deniz Yuret, Jonathan May, Kevin Knight","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-08T00:16:35Z","title":"Transfer Learning for Low-Resource Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1604.02201","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:e9fe19fab98019d104805408f62c65edf873d7addaca31163cabd4a5e1e9b6c6","target":"record","created_at":"2026-05-18T01:17:28Z","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":"e9cc69d08b93f8c7f3e3cfa903f45876b132f9feee29181f1bcdca3cf5d5eab9","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-04-08T00:16:35Z","title_canon_sha256":"5c27510fb659f24b98659e765b6e76f2f1e40a948f2741192809cb4cd809b3c9"},"schema_version":"1.0","source":{"id":"1604.02201","kind":"arxiv","version":1}},"canonical_sha256":"4303e14e8626b7abc9c32903572579240c1cc1a2e9b1370eb3e7676464eeaa40","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4303e14e8626b7abc9c32903572579240c1cc1a2e9b1370eb3e7676464eeaa40","first_computed_at":"2026-05-18T01:17:28.235108Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:17:28.235108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s3jUeRgU5V5vqADWD7yN5FbsHorHRkdH8GZUl/su3eEpGj36JYz1zbwWOKvIkWYwu4CHuiAyrJMg/3n9tbI+BQ==","signature_status":"signed_v1","signed_at":"2026-05-18T01:17:28.235768Z","signed_message":"canonical_sha256_bytes"},"source_id":"1604.02201","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e9fe19fab98019d104805408f62c65edf873d7addaca31163cabd4a5e1e9b6c6","sha256:090f24e97f72d2c6ec170976e7397a1d811493d647637e3323a7e7751cdf407a"],"state_sha256":"50ac6b9b01b5cb459577809d4372a33457a67ab555c9f1521546b58a88bb6e6f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"75jnwrIvgJB6RDk+TIoSdFITHA+E20yJr/LssVAfSRzFspXQBQslypOpLZ97kCn7HtL2gkgOHsp6oMW7pMT/DQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-20T17:19:52.107957Z","bundle_sha256":"a0b77e483027a7cd4b0ab6c7f91e7ba4711184b2d20ddf7103817f899b220469"}}