{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:BKVCJ2RW35IREGG3AUH5SHQ43Y","short_pith_number":"pith:BKVCJ2RW","canonical_record":{"source":{"id":"1606.02006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-07T02:40:42Z","cross_cats_sorted":[],"title_canon_sha256":"5ded1d8b7ae5490937aa7990709bd4a8b52543de82caed3d5ea58a9481b2792e","abstract_canon_sha256":"3309e6260a680b75477f6a457169a84ef9adc8f67b6c89609c5809ff99bec900"},"schema_version":"1.0"},"canonical_sha256":"0aaa24ea36df511218db050fd91e1cde34f9237598ac5f87da77e194b95ba1cb","source":{"kind":"arxiv","id":"1606.02006","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02006","created_at":"2026-05-18T01:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02006v2","created_at":"2026-05-18T01:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02006","created_at":"2026-05-18T01:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"BKVCJ2RW35IR","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BKVCJ2RW35IREGG3","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BKVCJ2RW","created_at":"2026-05-18T12:30:07Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:BKVCJ2RW35IREGG3AUH5SHQ43Y","target":"record","payload":{"canonical_record":{"source":{"id":"1606.02006","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-07T02:40:42Z","cross_cats_sorted":[],"title_canon_sha256":"5ded1d8b7ae5490937aa7990709bd4a8b52543de82caed3d5ea58a9481b2792e","abstract_canon_sha256":"3309e6260a680b75477f6a457169a84ef9adc8f67b6c89609c5809ff99bec900"},"schema_version":"1.0"},"canonical_sha256":"0aaa24ea36df511218db050fd91e1cde34f9237598ac5f87da77e194b95ba1cb","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:03:11.731380Z","signature_b64":"BLEoSsstOUgxknwaF9XUo2AkcxRL0QGrsCcQNUiGjBGez+3O7QBne3HeUwntGqxSvGToB+knwLNrMAeNqbQMDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0aaa24ea36df511218db050fd91e1cde34f9237598ac5f87da77e194b95ba1cb","last_reissued_at":"2026-05-18T01:03:11.730797Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:03:11.730797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1606.02006","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":"2026-05-18T01:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"754IKn6drQFGED6v0NzsblAFzm/JnMbpi3BU/cgTteWQ1FTBJb3KOBe6qVDjMhzrisA/fxRvEo9v/vLbZ+tmBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:16:02.151115Z"},"content_sha256":"5271a9314268357ebca40cb320bccded09da535202f5ec18e390c9e7b4f9f69c","schema_version":"1.0","event_id":"sha256:5271a9314268357ebca40cb320bccded09da535202f5ec18e390c9e7b4f9f69c"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:BKVCJ2RW35IREGG3AUH5SHQ43Y","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Incorporating Discrete Translation Lexicons into Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Graham Neubig, Philip Arthur, Satoshi Nakamura","submitted_at":"2016-06-07T02:40:42Z","abstract_excerpt":"Neural machine translation (NMT) often makes mistakes in translating low-frequency content words that are essential to understanding the meaning of the sentence. We propose a method to alleviate this problem by augmenting NMT systems with discrete translation lexicons that efficiently encode translations of these low-frequency words. We describe a method to calculate the lexicon probability of the next word in the translation candidate by using the attention vector of the NMT model to select which source word lexical probabilities the model should focus on. We test two methods to combine this "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02006","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":"2026-05-18T01:03:11Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"ssJFzjmucINWiVG/H0Ua0/3TtNM8+Ja2aPZjna2cEZ897wfQcczUagIc+RYbaSSiOK+4Z8SZZ/3R+pnp78wGDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T19:16:02.151706Z"},"content_sha256":"d345f05ad3c7e843f6dfee65dc2f90fb820a180a90dde010e99e70f586d8400b","schema_version":"1.0","event_id":"sha256:d345f05ad3c7e843f6dfee65dc2f90fb820a180a90dde010e99e70f586d8400b"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/BKVCJ2RW35IREGG3AUH5SHQ43Y/bundle.json","state_url":"https://pith.science/pith/BKVCJ2RW35IREGG3AUH5SHQ43Y/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/BKVCJ2RW35IREGG3AUH5SHQ43Y/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":"2026-06-04T19:16:02Z","links":{"resolver":"https://pith.science/pith/BKVCJ2RW35IREGG3AUH5SHQ43Y","bundle":"https://pith.science/pith/BKVCJ2RW35IREGG3AUH5SHQ43Y/bundle.json","state":"https://pith.science/pith/BKVCJ2RW35IREGG3AUH5SHQ43Y/state.json","well_known_bundle":"https://pith.science/.well-known/pith/BKVCJ2RW35IREGG3AUH5SHQ43Y/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:BKVCJ2RW35IREGG3AUH5SHQ43Y","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":"3309e6260a680b75477f6a457169a84ef9adc8f67b6c89609c5809ff99bec900","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-07T02:40:42Z","title_canon_sha256":"5ded1d8b7ae5490937aa7990709bd4a8b52543de82caed3d5ea58a9481b2792e"},"schema_version":"1.0","source":{"id":"1606.02006","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02006","created_at":"2026-05-18T01:03:11Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02006v2","created_at":"2026-05-18T01:03:11Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02006","created_at":"2026-05-18T01:03:11Z"},{"alias_kind":"pith_short_12","alias_value":"BKVCJ2RW35IR","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_16","alias_value":"BKVCJ2RW35IREGG3","created_at":"2026-05-18T12:30:07Z"},{"alias_kind":"pith_short_8","alias_value":"BKVCJ2RW","created_at":"2026-05-18T12:30:07Z"}],"graph_snapshots":[{"event_id":"sha256:d345f05ad3c7e843f6dfee65dc2f90fb820a180a90dde010e99e70f586d8400b","target":"graph","created_at":"2026-05-18T01:03:11Z","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 (NMT) often makes mistakes in translating low-frequency content words that are essential to understanding the meaning of the sentence. We propose a method to alleviate this problem by augmenting NMT systems with discrete translation lexicons that efficiently encode translations of these low-frequency words. We describe a method to calculate the lexicon probability of the next word in the translation candidate by using the attention vector of the NMT model to select which source word lexical probabilities the model should focus on. We test two methods to combine this ","authors_text":"Graham Neubig, Philip Arthur, Satoshi Nakamura","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-07T02:40:42Z","title":"Incorporating Discrete Translation Lexicons into Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02006","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":"sha256:5271a9314268357ebca40cb320bccded09da535202f5ec18e390c9e7b4f9f69c","target":"record","created_at":"2026-05-18T01:03:11Z","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":"3309e6260a680b75477f6a457169a84ef9adc8f67b6c89609c5809ff99bec900","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-07T02:40:42Z","title_canon_sha256":"5ded1d8b7ae5490937aa7990709bd4a8b52543de82caed3d5ea58a9481b2792e"},"schema_version":"1.0","source":{"id":"1606.02006","kind":"arxiv","version":2}},"canonical_sha256":"0aaa24ea36df511218db050fd91e1cde34f9237598ac5f87da77e194b95ba1cb","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0aaa24ea36df511218db050fd91e1cde34f9237598ac5f87da77e194b95ba1cb","first_computed_at":"2026-05-18T01:03:11.730797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:03:11.730797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BLEoSsstOUgxknwaF9XUo2AkcxRL0QGrsCcQNUiGjBGez+3O7QBne3HeUwntGqxSvGToB+knwLNrMAeNqbQMDA==","signature_status":"signed_v1","signed_at":"2026-05-18T01:03:11.731380Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.02006","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:5271a9314268357ebca40cb320bccded09da535202f5ec18e390c9e7b4f9f69c","sha256:d345f05ad3c7e843f6dfee65dc2f90fb820a180a90dde010e99e70f586d8400b"],"state_sha256":"e44c9eab9fbdd08f3ca314b32f076059fb5ae03ba3d3bb60b0031fe67b08723f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UU7x5mf8jT//bAJ1UKmJPi5wZFyRRR0zR80bvhFZbXWEQdrsbnXsl0nnMExWvC6Haz4OwtfbQgGIym5FTjOCBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T19:16:02.154446Z","bundle_sha256":"79bf7c7f118ac946414b274a58ad01d7efb3cc8e6c9523aa38c4fccd8fa13463"}}