{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:MLZ73T5TOOCZDHFWXTM2OZJGDH","short_pith_number":"pith:MLZ73T5T","canonical_record":{"source":{"id":"1707.06012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T10:47:22Z","cross_cats_sorted":[],"title_canon_sha256":"233a6daac3bcdb9af3f5cf261821a8d909c99b1242a816a03eaaf6af7677873d","abstract_canon_sha256":"be07247d68fb89c95eaead7f628052825f338ff0842374313a6883457a51f564"},"schema_version":"1.0"},"canonical_sha256":"62f3fdcfb37385919cb6bcd9a7652619cae4a295f40862f5d702bc315929ae84","source":{"kind":"arxiv","id":"1707.06012","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06012","created_at":"2026-05-18T00:36:02Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06012v2","created_at":"2026-05-18T00:36:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06012","created_at":"2026-05-18T00:36:02Z"},{"alias_kind":"pith_short_12","alias_value":"MLZ73T5TOOCZ","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MLZ73T5TOOCZDHFW","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MLZ73T5T","created_at":"2026-05-18T12:31:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:MLZ73T5TOOCZDHFWXTM2OZJGDH","target":"record","payload":{"canonical_record":{"source":{"id":"1707.06012","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T10:47:22Z","cross_cats_sorted":[],"title_canon_sha256":"233a6daac3bcdb9af3f5cf261821a8d909c99b1242a816a03eaaf6af7677873d","abstract_canon_sha256":"be07247d68fb89c95eaead7f628052825f338ff0842374313a6883457a51f564"},"schema_version":"1.0"},"canonical_sha256":"62f3fdcfb37385919cb6bcd9a7652619cae4a295f40862f5d702bc315929ae84","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:36:02.940723Z","signature_b64":"WEg3T8W06pWTBIwizVM8T056Jn8WUFfaA7v4bkGBGUenfZwyTByIrgXEb+FfC1NCqgpGphQIBP8bjSqVlX6ADg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62f3fdcfb37385919cb6bcd9a7652619cae4a295f40862f5d702bc315929ae84","last_reissued_at":"2026-05-18T00:36:02.940345Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:36:02.940345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1707.06012","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":"2026-05-18T00:36:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/e0ZkFQvoN+Jv/uem+g8xTn715MZ1bpi6PwmTzVM2zyn5JhrnKkyCpMrvij9luY9xay6wSjWp0RTCQYik8rwDA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:06:30.406060Z"},"content_sha256":"57a70d2504db4e94a9e4aac557e842369b2b4adfb840ab2a9288cbd5cbdae485","schema_version":"1.0","event_id":"sha256:57a70d2504db4e94a9e4aac557e842369b2b4adfb840ab2a9288cbd5cbdae485"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:MLZ73T5TOOCZDHFWXTM2OZJGDH","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Target-Side Inflection in Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ale\\v{s} Tamchyna, Alexander Fraser, Marion Weller-Di Marco","submitted_at":"2017-07-19T10:47:22Z","abstract_excerpt":"NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization over the rich vocabulary in morphologically rich languages with strong inflectional phenomena. We introduce a simple approach to overcome this problem by training a system to produce the lemma of a word and its morphologically rich POS tag, which is then followed by a deterministic generation step. We apply this strategy for English-Czech and English-German tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06012","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":"2026-05-18T00:36:02Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"akoNAbSdEaaVApH2ll74OK+5YqSh8BqXdqlRR+zphjYXMw30om9S0LS7tz1KAQxC1TdQqxGZD+qcNLVb/9IcCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T05:06:30.406737Z"},"content_sha256":"760b9ad56690f2e3376573c2b9a2972b13e935cbb10a1bd0ca984cfaa7c45aa0","schema_version":"1.0","event_id":"sha256:760b9ad56690f2e3376573c2b9a2972b13e935cbb10a1bd0ca984cfaa7c45aa0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/MLZ73T5TOOCZDHFWXTM2OZJGDH/bundle.json","state_url":"https://pith.science/pith/MLZ73T5TOOCZDHFWXTM2OZJGDH/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/MLZ73T5TOOCZDHFWXTM2OZJGDH/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":"2026-06-04T05:06:30Z","links":{"resolver":"https://pith.science/pith/MLZ73T5TOOCZDHFWXTM2OZJGDH","bundle":"https://pith.science/pith/MLZ73T5TOOCZDHFWXTM2OZJGDH/bundle.json","state":"https://pith.science/pith/MLZ73T5TOOCZDHFWXTM2OZJGDH/state.json","well_known_bundle":"https://pith.science/.well-known/pith/MLZ73T5TOOCZDHFWXTM2OZJGDH/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:MLZ73T5TOOCZDHFWXTM2OZJGDH","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":"be07247d68fb89c95eaead7f628052825f338ff0842374313a6883457a51f564","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T10:47:22Z","title_canon_sha256":"233a6daac3bcdb9af3f5cf261821a8d909c99b1242a816a03eaaf6af7677873d"},"schema_version":"1.0","source":{"id":"1707.06012","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.06012","created_at":"2026-05-18T00:36:02Z"},{"alias_kind":"arxiv_version","alias_value":"1707.06012v2","created_at":"2026-05-18T00:36:02Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.06012","created_at":"2026-05-18T00:36:02Z"},{"alias_kind":"pith_short_12","alias_value":"MLZ73T5TOOCZ","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_16","alias_value":"MLZ73T5TOOCZDHFW","created_at":"2026-05-18T12:31:31Z"},{"alias_kind":"pith_short_8","alias_value":"MLZ73T5T","created_at":"2026-05-18T12:31:31Z"}],"graph_snapshots":[{"event_id":"sha256:760b9ad56690f2e3376573c2b9a2972b13e935cbb10a1bd0ca984cfaa7c45aa0","target":"graph","created_at":"2026-05-18T00:36:02Z","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":"NMT systems have problems with large vocabulary sizes. Byte-pair encoding (BPE) is a popular approach to solving this problem, but while BPE allows the system to generate any target-side word, it does not enable effective generalization over the rich vocabulary in morphologically rich languages with strong inflectional phenomena. We introduce a simple approach to overcome this problem by training a system to produce the lemma of a word and its morphologically rich POS tag, which is then followed by a deterministic generation step. We apply this strategy for English-Czech and English-German tra","authors_text":"Ale\\v{s} Tamchyna, Alexander Fraser, Marion Weller-Di Marco","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T10:47:22Z","title":"Modeling Target-Side Inflection in Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.06012","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":"sha256:57a70d2504db4e94a9e4aac557e842369b2b4adfb840ab2a9288cbd5cbdae485","target":"record","created_at":"2026-05-18T00:36:02Z","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":"be07247d68fb89c95eaead7f628052825f338ff0842374313a6883457a51f564","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-19T10:47:22Z","title_canon_sha256":"233a6daac3bcdb9af3f5cf261821a8d909c99b1242a816a03eaaf6af7677873d"},"schema_version":"1.0","source":{"id":"1707.06012","kind":"arxiv","version":2}},"canonical_sha256":"62f3fdcfb37385919cb6bcd9a7652619cae4a295f40862f5d702bc315929ae84","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"62f3fdcfb37385919cb6bcd9a7652619cae4a295f40862f5d702bc315929ae84","first_computed_at":"2026-05-18T00:36:02.940345Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:36:02.940345Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"WEg3T8W06pWTBIwizVM8T056Jn8WUFfaA7v4bkGBGUenfZwyTByIrgXEb+FfC1NCqgpGphQIBP8bjSqVlX6ADg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:36:02.940723Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.06012","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:57a70d2504db4e94a9e4aac557e842369b2b4adfb840ab2a9288cbd5cbdae485","sha256:760b9ad56690f2e3376573c2b9a2972b13e935cbb10a1bd0ca984cfaa7c45aa0"],"state_sha256":"5ee0fcc9092b756ef3548dd938a113a34c5c7ec85783ae146765c11fe2b1588e"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LcpJ5qHpeV20+QAWOHOvy9D9f3InKnIxxT008hvc2zyUUEs00ftdLG4I8R5dU6eYjr/II3yCbBaTQ++p14GhBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T05:06:30.410688Z","bundle_sha256":"681489b85f331b33e835d1ef83a05e29cf35b93d23527ec929ca64d04be46f9f"}}