{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:2W47LBDLACTHSLBWFI2WE3SEOL","short_pith_number":"pith:2W47LBDL","canonical_record":{"source":{"id":"1605.03209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-10T20:50:56Z","cross_cats_sorted":[],"title_canon_sha256":"b94138f784ea928e3b92410c7818675154a1a1a6556742ebca935b940be6d885","abstract_canon_sha256":"b9e18c308f3122c32d8f647b73318c6bebb5fcdb4c7f20988b84b21b26830c80"},"schema_version":"1.0"},"canonical_sha256":"d5b9f5846b00a6792c362a35626e4472f69801cabfe52d34fff547d72c7dc6b0","source":{"kind":"arxiv","id":"1605.03209","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.03209","created_at":"2026-05-18T01:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"1605.03209v1","created_at":"2026-05-18T01:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03209","created_at":"2026-05-18T01:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"2W47LBDLACTH","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"2W47LBDLACTHSLBW","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"2W47LBDL","created_at":"2026-05-18T12:29:55Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:2W47LBDLACTHSLBWFI2WE3SEOL","target":"record","payload":{"canonical_record":{"source":{"id":"1605.03209","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-10T20:50:56Z","cross_cats_sorted":[],"title_canon_sha256":"b94138f784ea928e3b92410c7818675154a1a1a6556742ebca935b940be6d885","abstract_canon_sha256":"b9e18c308f3122c32d8f647b73318c6bebb5fcdb4c7f20988b84b21b26830c80"},"schema_version":"1.0"},"canonical_sha256":"d5b9f5846b00a6792c362a35626e4472f69801cabfe52d34fff547d72c7dc6b0","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:10:14.392850Z","signature_b64":"jQVHxu4LAhoMKs/47/HJuvmi+w5QZ6moIYLoRtByTtwKtUYA6BN6yCHObEBAKUbo06+6TzXEJ655sl8VXw13Bg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d5b9f5846b00a6792c362a35626e4472f69801cabfe52d34fff547d72c7dc6b0","last_reissued_at":"2026-05-18T01:10:14.392256Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:10:14.392256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1605.03209","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":"2026-05-18T01:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"P9Z4hNcCCTHkGytcFGViTsuylhlUzpEjs3elEOz3pkXvCLcLz9hbf/sZ1Sw5lAgXi2D67sSf8mQ8Lkav+8HRAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:09:03.864784Z"},"content_sha256":"46f003290ccedf899b02005effe91e6682e9c54214cef06df444525e4bef1e3f","schema_version":"1.0","event_id":"sha256:46f003290ccedf899b02005effe91e6682e9c54214cef06df444525e4bef1e3f"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:2W47LBDLACTHSLBWFI2WE3SEOL","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Vocabulary Manipulation for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Abe Ittycheriah, Haitao Mi, Zhiguo Wang","submitted_at":"2016-05-10T20:50:56Z","abstract_excerpt":"In order to capture rich language phenomena, neural machine translation models have to use a large vocabulary size, which requires high computing time and large memory usage. In this paper, we alleviate this issue by introducing a sentence-level or batch-level vocabulary, which is only a very small sub-set of the full output vocabulary. For each sentence or batch, we only predict the target words in its sentence-level or batch-level vocabulary. Thus, we reduce both the computing time and the memory usage. Our method simply takes into account the translation options of each word or phrase in th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03209","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":"2026-05-18T01:10:14Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gWleJJ6Ffil6hxLjf3K+1o7/5ryD0WFiw2KrZSRldubDGNcRmQo0RTiB1UBKAoSU2cZvDH6iTiLgbS3wH2RrAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T04:09:03.865154Z"},"content_sha256":"fc0e9b9875bb7a7c49b65957bc2de447a4a641723b68f9dbb90030adb47193b2","schema_version":"1.0","event_id":"sha256:fc0e9b9875bb7a7c49b65957bc2de447a4a641723b68f9dbb90030adb47193b2"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/2W47LBDLACTHSLBWFI2WE3SEOL/bundle.json","state_url":"https://pith.science/pith/2W47LBDLACTHSLBWFI2WE3SEOL/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/2W47LBDLACTHSLBWFI2WE3SEOL/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":"2026-05-24T04:09:03Z","links":{"resolver":"https://pith.science/pith/2W47LBDLACTHSLBWFI2WE3SEOL","bundle":"https://pith.science/pith/2W47LBDLACTHSLBWFI2WE3SEOL/bundle.json","state":"https://pith.science/pith/2W47LBDLACTHSLBWFI2WE3SEOL/state.json","well_known_bundle":"https://pith.science/.well-known/pith/2W47LBDLACTHSLBWFI2WE3SEOL/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:2W47LBDLACTHSLBWFI2WE3SEOL","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":"b9e18c308f3122c32d8f647b73318c6bebb5fcdb4c7f20988b84b21b26830c80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-10T20:50:56Z","title_canon_sha256":"b94138f784ea928e3b92410c7818675154a1a1a6556742ebca935b940be6d885"},"schema_version":"1.0","source":{"id":"1605.03209","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1605.03209","created_at":"2026-05-18T01:10:14Z"},{"alias_kind":"arxiv_version","alias_value":"1605.03209v1","created_at":"2026-05-18T01:10:14Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1605.03209","created_at":"2026-05-18T01:10:14Z"},{"alias_kind":"pith_short_12","alias_value":"2W47LBDLACTH","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_16","alias_value":"2W47LBDLACTHSLBW","created_at":"2026-05-18T12:29:55Z"},{"alias_kind":"pith_short_8","alias_value":"2W47LBDL","created_at":"2026-05-18T12:29:55Z"}],"graph_snapshots":[{"event_id":"sha256:fc0e9b9875bb7a7c49b65957bc2de447a4a641723b68f9dbb90030adb47193b2","target":"graph","created_at":"2026-05-18T01:10:14Z","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":"In order to capture rich language phenomena, neural machine translation models have to use a large vocabulary size, which requires high computing time and large memory usage. In this paper, we alleviate this issue by introducing a sentence-level or batch-level vocabulary, which is only a very small sub-set of the full output vocabulary. For each sentence or batch, we only predict the target words in its sentence-level or batch-level vocabulary. Thus, we reduce both the computing time and the memory usage. Our method simply takes into account the translation options of each word or phrase in th","authors_text":"Abe Ittycheriah, Haitao Mi, Zhiguo Wang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-10T20:50:56Z","title":"Vocabulary Manipulation for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1605.03209","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":"sha256:46f003290ccedf899b02005effe91e6682e9c54214cef06df444525e4bef1e3f","target":"record","created_at":"2026-05-18T01:10:14Z","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":"b9e18c308f3122c32d8f647b73318c6bebb5fcdb4c7f20988b84b21b26830c80","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-05-10T20:50:56Z","title_canon_sha256":"b94138f784ea928e3b92410c7818675154a1a1a6556742ebca935b940be6d885"},"schema_version":"1.0","source":{"id":"1605.03209","kind":"arxiv","version":1}},"canonical_sha256":"d5b9f5846b00a6792c362a35626e4472f69801cabfe52d34fff547d72c7dc6b0","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d5b9f5846b00a6792c362a35626e4472f69801cabfe52d34fff547d72c7dc6b0","first_computed_at":"2026-05-18T01:10:14.392256Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:10:14.392256Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"jQVHxu4LAhoMKs/47/HJuvmi+w5QZ6moIYLoRtByTtwKtUYA6BN6yCHObEBAKUbo06+6TzXEJ655sl8VXw13Bg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:10:14.392850Z","signed_message":"canonical_sha256_bytes"},"source_id":"1605.03209","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:46f003290ccedf899b02005effe91e6682e9c54214cef06df444525e4bef1e3f","sha256:fc0e9b9875bb7a7c49b65957bc2de447a4a641723b68f9dbb90030adb47193b2"],"state_sha256":"8e8a2160784d132952fae65fa96fb8f11772aaa5b45002ca1f75d64819b8e531"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4AeOQTY9uQw+eurIyf9wnYL8Yk4PzmBR1U+/TGPzN7/KSLavtTtjNfm+DEJvT1VH5sUMWc25UgVvShuUGh0TAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T04:09:03.868273Z","bundle_sha256":"1c5ed70974055f6f111afa03b1a32dae8bbf53bbbc1153bcc0f617b9b3eadd59"}}