{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:A6ZOGDGVPF7XVLUGI5WSQUSSTK","short_pith_number":"pith:A6ZOGDGV","canonical_record":{"source":{"id":"1807.11219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-30T08:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"ee64957d0bf91daf85778b8bb5b668e815e422afb5c5993e2dc07b7d56e73b99","abstract_canon_sha256":"7d946167e46124661715f0b0016bc04562b00104e29bb3905d5b6a6c944004bc"},"schema_version":"1.0"},"canonical_sha256":"07b2e30cd5797f7aae86476d2852529aa0e362cc0b93c9760c108b20217b232d","source":{"kind":"arxiv","id":"1807.11219","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11219","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11219v1","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11219","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"A6ZOGDGVPF7X","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A6ZOGDGVPF7XVLUG","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A6ZOGDGV","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:A6ZOGDGVPF7XVLUGI5WSQUSSTK","target":"record","payload":{"canonical_record":{"source":{"id":"1807.11219","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-30T08:11:52Z","cross_cats_sorted":[],"title_canon_sha256":"ee64957d0bf91daf85778b8bb5b668e815e422afb5c5993e2dc07b7d56e73b99","abstract_canon_sha256":"7d946167e46124661715f0b0016bc04562b00104e29bb3905d5b6a6c944004bc"},"schema_version":"1.0"},"canonical_sha256":"07b2e30cd5797f7aae86476d2852529aa0e362cc0b93c9760c108b20217b232d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:09:32.584406Z","signature_b64":"BqAGj3NwgFsKAIl1uGEkNjg0Mw7JYr31NYcWc6g522cJKLpLnX8CYEDjccNywr9s9QaRT/KMvoDWA0lClVZsBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"07b2e30cd5797f7aae86476d2852529aa0e362cc0b93c9760c108b20217b232d","last_reissued_at":"2026-05-18T00:09:32.583575Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:09:32.583575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1807.11219","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":"2026-05-18T00:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"2H69QGx1Wgp3J42PeA1sEweUS64/Q7yHNrt97t4eszdDFvqDRzr83Q4GRUe2a3fOlYS6vi2of0UPfX422XwnAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T16:42:05.782495Z"},"content_sha256":"03b2b091f4125550e31f55d9be206fb93edfe772304a431975a0c9bfed0712ba","schema_version":"1.0","event_id":"sha256:03b2b091f4125550e31f55d9be206fb93edfe772304a431975a0c9bfed0712ba"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:A6ZOGDGVPF7XVLUGI5WSQUSSTK","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Training Neural Machine Translation using Word Embedding-based Loss","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Katsuhito Sudoh, Katsuki Chousa, Satoshi Nakamura","submitted_at":"2018-07-30T08:11:52Z","abstract_excerpt":"In neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may cause a significant decrease in translation quality. This trade-off is derived from a softmax-based loss function that handles in-dictionary words independently, in which word similarity is not considered. In this paper, we propose a novel NMT loss function that includes word similarity in forms of distances in a word embedding space. The proposed loss function encourages an NMT decoder to generate words close to thei"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11219","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":"2026-05-18T00:09:32Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0yvlUmBN/SoXndjufML/jaIVhjiMdPepuQP9d1hl7T9xQdIPMd3ebHFd0sADiX8VBPc7htXXRM1J3dlp3lp3Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T16:42:05.783169Z"},"content_sha256":"dc950dc82bb6dbaec3e9178de28c9cd3e221f93a3de1c2fd4f3557bcbcd15ce5","schema_version":"1.0","event_id":"sha256:dc950dc82bb6dbaec3e9178de28c9cd3e221f93a3de1c2fd4f3557bcbcd15ce5"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/A6ZOGDGVPF7XVLUGI5WSQUSSTK/bundle.json","state_url":"https://pith.science/pith/A6ZOGDGVPF7XVLUGI5WSQUSSTK/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/A6ZOGDGVPF7XVLUGI5WSQUSSTK/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":"2026-05-24T16:42:05Z","links":{"resolver":"https://pith.science/pith/A6ZOGDGVPF7XVLUGI5WSQUSSTK","bundle":"https://pith.science/pith/A6ZOGDGVPF7XVLUGI5WSQUSSTK/bundle.json","state":"https://pith.science/pith/A6ZOGDGVPF7XVLUGI5WSQUSSTK/state.json","well_known_bundle":"https://pith.science/.well-known/pith/A6ZOGDGVPF7XVLUGI5WSQUSSTK/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:A6ZOGDGVPF7XVLUGI5WSQUSSTK","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":"7d946167e46124661715f0b0016bc04562b00104e29bb3905d5b6a6c944004bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-30T08:11:52Z","title_canon_sha256":"ee64957d0bf91daf85778b8bb5b668e815e422afb5c5993e2dc07b7d56e73b99"},"schema_version":"1.0","source":{"id":"1807.11219","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1807.11219","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"arxiv_version","alias_value":"1807.11219v1","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1807.11219","created_at":"2026-05-18T00:09:32Z"},{"alias_kind":"pith_short_12","alias_value":"A6ZOGDGVPF7X","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"A6ZOGDGVPF7XVLUG","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"A6ZOGDGV","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:dc950dc82bb6dbaec3e9178de28c9cd3e221f93a3de1c2fd4f3557bcbcd15ce5","target":"graph","created_at":"2026-05-18T00:09:32Z","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 neural machine translation (NMT), the computational cost at the output layer increases with the size of the target-side vocabulary. Using a limited-size vocabulary instead may cause a significant decrease in translation quality. This trade-off is derived from a softmax-based loss function that handles in-dictionary words independently, in which word similarity is not considered. In this paper, we propose a novel NMT loss function that includes word similarity in forms of distances in a word embedding space. The proposed loss function encourages an NMT decoder to generate words close to thei","authors_text":"Katsuhito Sudoh, Katsuki Chousa, Satoshi Nakamura","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-30T08:11:52Z","title":"Training Neural Machine Translation using Word Embedding-based Loss"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1807.11219","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":"sha256:03b2b091f4125550e31f55d9be206fb93edfe772304a431975a0c9bfed0712ba","target":"record","created_at":"2026-05-18T00:09:32Z","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":"7d946167e46124661715f0b0016bc04562b00104e29bb3905d5b6a6c944004bc","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-07-30T08:11:52Z","title_canon_sha256":"ee64957d0bf91daf85778b8bb5b668e815e422afb5c5993e2dc07b7d56e73b99"},"schema_version":"1.0","source":{"id":"1807.11219","kind":"arxiv","version":1}},"canonical_sha256":"07b2e30cd5797f7aae86476d2852529aa0e362cc0b93c9760c108b20217b232d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"07b2e30cd5797f7aae86476d2852529aa0e362cc0b93c9760c108b20217b232d","first_computed_at":"2026-05-18T00:09:32.583575Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:09:32.583575Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BqAGj3NwgFsKAIl1uGEkNjg0Mw7JYr31NYcWc6g522cJKLpLnX8CYEDjccNywr9s9QaRT/KMvoDWA0lClVZsBA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:09:32.584406Z","signed_message":"canonical_sha256_bytes"},"source_id":"1807.11219","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:03b2b091f4125550e31f55d9be206fb93edfe772304a431975a0c9bfed0712ba","sha256:dc950dc82bb6dbaec3e9178de28c9cd3e221f93a3de1c2fd4f3557bcbcd15ce5"],"state_sha256":"5fa68a6526bcfb84b36994b38c12fe66078176172ac71f5035dd583165da0364"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"wrmx2YiCrIUBihq5UB5LQSegor7udBdtb9xdxexWm9YTnhQE3IbH/QRNdHF1N1g23USD7IhzB1oIEWf10LWlCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T16:42:05.786148Z","bundle_sha256":"667dfdee7cfe4369f9dd40710bc478160129cb645bc132735d3e01c9dd7135a7"}}