{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:ZTX6ALZAQLYLCYAU42DXXWPHTL","short_pith_number":"pith:ZTX6ALZA","canonical_record":{"source":{"id":"1609.04621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-09-15T13:15:01Z","cross_cats_sorted":[],"title_canon_sha256":"2a27bc3fc85053aed6be09a016a9edc323afeb9f5200a4dffdc5ab48f296d050","abstract_canon_sha256":"99038e2ad62f64758089de8ba163175f6e02e7d027329da36a6b66efee620363"},"schema_version":"1.0"},"canonical_sha256":"ccefe02f2082f0b16014e6877bd9e79ae103100db424d19ae1b22b04884d8469","source":{"kind":"arxiv","id":"1609.04621","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.04621","created_at":"2026-05-18T00:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"1609.04621v1","created_at":"2026-05-18T00:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.04621","created_at":"2026-05-18T00:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZTX6ALZAQLYL","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZTX6ALZAQLYLCYAU","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZTX6ALZA","created_at":"2026-05-18T12:30:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:ZTX6ALZAQLYLCYAU42DXXWPHTL","target":"record","payload":{"canonical_record":{"source":{"id":"1609.04621","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-09-15T13:15:01Z","cross_cats_sorted":[],"title_canon_sha256":"2a27bc3fc85053aed6be09a016a9edc323afeb9f5200a4dffdc5ab48f296d050","abstract_canon_sha256":"99038e2ad62f64758089de8ba163175f6e02e7d027329da36a6b66efee620363"},"schema_version":"1.0"},"canonical_sha256":"ccefe02f2082f0b16014e6877bd9e79ae103100db424d19ae1b22b04884d8469","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:28:41.274695Z","signature_b64":"s0DEpmw+MHwI79cAEOi33Ds7n2jK2mYZlzoW91VcS3yyCjhYyyYYodqCeuSX0nG2Q7gzLVrKMFZZ4y0qrajxBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ccefe02f2082f0b16014e6877bd9e79ae103100db424d19ae1b22b04884d8469","last_reissued_at":"2026-05-18T00:28:41.273937Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:28:41.273937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1609.04621","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":"2026-05-18T00:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"AXz2AwiKHcJQl5NUpAkP362folZ9vnS/ckL+jAlqqJ9+RG5LNqp6kq48GM+24clbl8llyrK4rGdMgYyiPWWqDQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:21:30.513003Z"},"content_sha256":"ddd1ec447d54b4b9cacfffef4da8ae1b8104b101456a30cbf04b6923d0164981","schema_version":"1.0","event_id":"sha256:ddd1ec447d54b4b9cacfffef4da8ae1b8104b101456a30cbf04b6923d0164981"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:ZTX6ALZAQLYLCYAU42DXXWPHTL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Factored Neural Machine Translation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Fethi Bougares, Lo\\\"ic Barrault, Mercedes Garc\\'ia-Mart\\'inez","submitted_at":"2016-09-15T13:15:01Z","abstract_excerpt":"We present a new approach for neural machine translation (NMT) using the morphological and grammatical decomposition of the words (factors) in the output side of the neural network. This architecture addresses two main problems occurring in MT, namely dealing with a large target language vocabulary and the out of vocabulary (OOV) words. By the means of factors, we are able to handle larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size). In addition, we can produce new words that are not in the vocabulary. We use a morphological analyser to"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.04621","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":"2026-05-18T00:28:41Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ci62sY0KWPDTckYMc5IRxa4LCTsuOcKVSLqFFx8mhqdgwdCr1LvBh6wczKL6Yw66Gs4jhgZRYkp0Cs1RiAAQCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-26T17:21:30.513475Z"},"content_sha256":"c13e6d16dfe11e3a2e0af58cab4a5146ed5efecd774647898c5486f94d6ac467","schema_version":"1.0","event_id":"sha256:c13e6d16dfe11e3a2e0af58cab4a5146ed5efecd774647898c5486f94d6ac467"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZTX6ALZAQLYLCYAU42DXXWPHTL/bundle.json","state_url":"https://pith.science/pith/ZTX6ALZAQLYLCYAU42DXXWPHTL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZTX6ALZAQLYLCYAU42DXXWPHTL/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":"2026-05-26T17:21:30Z","links":{"resolver":"https://pith.science/pith/ZTX6ALZAQLYLCYAU42DXXWPHTL","bundle":"https://pith.science/pith/ZTX6ALZAQLYLCYAU42DXXWPHTL/bundle.json","state":"https://pith.science/pith/ZTX6ALZAQLYLCYAU42DXXWPHTL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZTX6ALZAQLYLCYAU42DXXWPHTL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:ZTX6ALZAQLYLCYAU42DXXWPHTL","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":"99038e2ad62f64758089de8ba163175f6e02e7d027329da36a6b66efee620363","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-09-15T13:15:01Z","title_canon_sha256":"2a27bc3fc85053aed6be09a016a9edc323afeb9f5200a4dffdc5ab48f296d050"},"schema_version":"1.0","source":{"id":"1609.04621","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1609.04621","created_at":"2026-05-18T00:28:41Z"},{"alias_kind":"arxiv_version","alias_value":"1609.04621v1","created_at":"2026-05-18T00:28:41Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1609.04621","created_at":"2026-05-18T00:28:41Z"},{"alias_kind":"pith_short_12","alias_value":"ZTX6ALZAQLYL","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_16","alias_value":"ZTX6ALZAQLYLCYAU","created_at":"2026-05-18T12:30:55Z"},{"alias_kind":"pith_short_8","alias_value":"ZTX6ALZA","created_at":"2026-05-18T12:30:55Z"}],"graph_snapshots":[{"event_id":"sha256:c13e6d16dfe11e3a2e0af58cab4a5146ed5efecd774647898c5486f94d6ac467","target":"graph","created_at":"2026-05-18T00:28:41Z","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":"We present a new approach for neural machine translation (NMT) using the morphological and grammatical decomposition of the words (factors) in the output side of the neural network. This architecture addresses two main problems occurring in MT, namely dealing with a large target language vocabulary and the out of vocabulary (OOV) words. By the means of factors, we are able to handle larger vocabulary and reduce the training time (for systems with equivalent target language vocabulary size). In addition, we can produce new words that are not in the vocabulary. We use a morphological analyser to","authors_text":"Fethi Bougares, Lo\\\"ic Barrault, Mercedes Garc\\'ia-Mart\\'inez","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-09-15T13:15:01Z","title":"Factored Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1609.04621","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:ddd1ec447d54b4b9cacfffef4da8ae1b8104b101456a30cbf04b6923d0164981","target":"record","created_at":"2026-05-18T00:28:41Z","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":"99038e2ad62f64758089de8ba163175f6e02e7d027329da36a6b66efee620363","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2016-09-15T13:15:01Z","title_canon_sha256":"2a27bc3fc85053aed6be09a016a9edc323afeb9f5200a4dffdc5ab48f296d050"},"schema_version":"1.0","source":{"id":"1609.04621","kind":"arxiv","version":1}},"canonical_sha256":"ccefe02f2082f0b16014e6877bd9e79ae103100db424d19ae1b22b04884d8469","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"ccefe02f2082f0b16014e6877bd9e79ae103100db424d19ae1b22b04884d8469","first_computed_at":"2026-05-18T00:28:41.273937Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:28:41.273937Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"s0DEpmw+MHwI79cAEOi33Ds7n2jK2mYZlzoW91VcS3yyCjhYyyYYodqCeuSX0nG2Q7gzLVrKMFZZ4y0qrajxBg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:28:41.274695Z","signed_message":"canonical_sha256_bytes"},"source_id":"1609.04621","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:ddd1ec447d54b4b9cacfffef4da8ae1b8104b101456a30cbf04b6923d0164981","sha256:c13e6d16dfe11e3a2e0af58cab4a5146ed5efecd774647898c5486f94d6ac467"],"state_sha256":"c8d7b6447517211c4acd6b5a6c50eac493db72b8ecb2c80f539f7a04d6b80015"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xvZ55Tc0wnS2PP6PrPltNo4dJ6Gh4E/+SSqjEOdNbT2R/eyc6PJLpGFRxwXaaLgwbQsnE2P1xf6cs5Ro1dMJCA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-26T17:21:30.516088Z","bundle_sha256":"36b0d7de719846499e020f5a8e7c5cd8c54d67a649a59bdbf35893b9e3536299"}}