{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2016:OMUDQHD2JCCBWI2NJVFYM3J5OF","short_pith_number":"pith:OMUDQHD2","canonical_record":{"source":{"id":"1608.04738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-16T07:44:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"03dc9814ac64c60c93176711de92ff907453ee26f1669a4a21129cce4678e351","abstract_canon_sha256":"f0a4830aea38ec21812081cfdb0d555e38c65882c8972ac7efdcd425267cc0f5"},"schema_version":"1.0"},"canonical_sha256":"7328381c7a48841b234d4d4b866d3d715760bf7f315d850f53c680f46cccae22","source":{"kind":"arxiv","id":"1608.04738","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04738","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04738v2","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04738","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"OMUDQHD2JCCB","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OMUDQHD2JCCBWI2N","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OMUDQHD2","created_at":"2026-05-18T12:30:36Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2016:OMUDQHD2JCCBWI2NJVFYM3J5OF","target":"record","payload":{"canonical_record":{"source":{"id":"1608.04738","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-16T07:44:02Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"03dc9814ac64c60c93176711de92ff907453ee26f1669a4a21129cce4678e351","abstract_canon_sha256":"f0a4830aea38ec21812081cfdb0d555e38c65882c8972ac7efdcd425267cc0f5"},"schema_version":"1.0"},"canonical_sha256":"7328381c7a48841b234d4d4b866d3d715760bf7f315d850f53c680f46cccae22","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T01:08:28.426929Z","signature_b64":"M1xN5mfDsU/HlymtICbmnG9iIew+BvQIdqOGnzSEAVE2TP2UY1cguSBBISomF+ro3JEPRa1BPkyrKVORTEegBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7328381c7a48841b234d4d4b866d3d715760bf7f315d850f53c680f46cccae22","last_reissued_at":"2026-05-18T01:08:28.426508Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T01:08:28.426508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1608.04738","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":"2026-05-18T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"RC23VlfFDyjGAxUgoMIhl22Dl87ll/NzhV/mIhoGd2eUDE+blQuXBV0ZbxqVfqGg/Ezd5sm/o60cOhDT02xDCg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:26:56.696161Z"},"content_sha256":"d835742fdf0710b54aadea17b0446eb8eed0a594c145c436072453fd8ba61eac","schema_version":"1.0","event_id":"sha256:d835742fdf0710b54aadea17b0446eb8eed0a594c145c436072453fd8ba61eac"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2016:OMUDQHD2JCCBWI2NJVFYM3J5OF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"An Efficient Character-Level Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.CL","authors_text":"Shenjian Zhao, Zhihua Zhang","submitted_at":"2016-08-16T07:44:02Z","abstract_excerpt":"Neural machine translation aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to the existing state-of-the-art phrase-based systems on the task of English-to-French translation. However, the use of large vocabulary becomes the bottleneck in both training and improving the performance. In this paper, we propose an efficient architecture to train a deep character-level neural machine translation by introducing a decimator and an interpola"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04738","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":"2026-05-18T01:08:28Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"UBw9TH2N24EmfDXejbbbbvREsdfaH9BIUBvbYwsIKX1fsp849YnCrODGLBD4B0CCl4JUOFAg6AH4WHK6i8qFBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T01:26:56.696525Z"},"content_sha256":"32cc4a96b931cef9de44dc399290af3beaf1eba5c4e2c3e125c46d3e26871cb0","schema_version":"1.0","event_id":"sha256:32cc4a96b931cef9de44dc399290af3beaf1eba5c4e2c3e125c46d3e26871cb0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OMUDQHD2JCCBWI2NJVFYM3J5OF/bundle.json","state_url":"https://pith.science/pith/OMUDQHD2JCCBWI2NJVFYM3J5OF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OMUDQHD2JCCBWI2NJVFYM3J5OF/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":"2026-06-03T01:26:56Z","links":{"resolver":"https://pith.science/pith/OMUDQHD2JCCBWI2NJVFYM3J5OF","bundle":"https://pith.science/pith/OMUDQHD2JCCBWI2NJVFYM3J5OF/bundle.json","state":"https://pith.science/pith/OMUDQHD2JCCBWI2NJVFYM3J5OF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OMUDQHD2JCCBWI2NJVFYM3J5OF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:OMUDQHD2JCCBWI2NJVFYM3J5OF","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":"f0a4830aea38ec21812081cfdb0d555e38c65882c8972ac7efdcd425267cc0f5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-16T07:44:02Z","title_canon_sha256":"03dc9814ac64c60c93176711de92ff907453ee26f1669a4a21129cce4678e351"},"schema_version":"1.0","source":{"id":"1608.04738","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1608.04738","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"arxiv_version","alias_value":"1608.04738v2","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1608.04738","created_at":"2026-05-18T01:08:28Z"},{"alias_kind":"pith_short_12","alias_value":"OMUDQHD2JCCB","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_16","alias_value":"OMUDQHD2JCCBWI2N","created_at":"2026-05-18T12:30:36Z"},{"alias_kind":"pith_short_8","alias_value":"OMUDQHD2","created_at":"2026-05-18T12:30:36Z"}],"graph_snapshots":[{"event_id":"sha256:32cc4a96b931cef9de44dc399290af3beaf1eba5c4e2c3e125c46d3e26871cb0","target":"graph","created_at":"2026-05-18T01:08:28Z","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 aims at building a single large neural network that can be trained to maximize translation performance. The encoder-decoder architecture with an attention mechanism achieves a translation performance comparable to the existing state-of-the-art phrase-based systems on the task of English-to-French translation. However, the use of large vocabulary becomes the bottleneck in both training and improving the performance. In this paper, we propose an efficient architecture to train a deep character-level neural machine translation by introducing a decimator and an interpola","authors_text":"Shenjian Zhao, Zhihua Zhang","cross_cats":["stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-16T07:44:02Z","title":"An Efficient Character-Level Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1608.04738","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:d835742fdf0710b54aadea17b0446eb8eed0a594c145c436072453fd8ba61eac","target":"record","created_at":"2026-05-18T01:08:28Z","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":"f0a4830aea38ec21812081cfdb0d555e38c65882c8972ac7efdcd425267cc0f5","cross_cats_sorted":["stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-08-16T07:44:02Z","title_canon_sha256":"03dc9814ac64c60c93176711de92ff907453ee26f1669a4a21129cce4678e351"},"schema_version":"1.0","source":{"id":"1608.04738","kind":"arxiv","version":2}},"canonical_sha256":"7328381c7a48841b234d4d4b866d3d715760bf7f315d850f53c680f46cccae22","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7328381c7a48841b234d4d4b866d3d715760bf7f315d850f53c680f46cccae22","first_computed_at":"2026-05-18T01:08:28.426508Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:08:28.426508Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"M1xN5mfDsU/HlymtICbmnG9iIew+BvQIdqOGnzSEAVE2TP2UY1cguSBBISomF+ro3JEPRa1BPkyrKVORTEegBw==","signature_status":"signed_v1","signed_at":"2026-05-18T01:08:28.426929Z","signed_message":"canonical_sha256_bytes"},"source_id":"1608.04738","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:d835742fdf0710b54aadea17b0446eb8eed0a594c145c436072453fd8ba61eac","sha256:32cc4a96b931cef9de44dc399290af3beaf1eba5c4e2c3e125c46d3e26871cb0"],"state_sha256":"50efb3bb87c8ac57456f19d399ded37be663fa46758ab601bf9a297f4c4390c0"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"/bRx/+MOs3z5T1ypLfaOdje/M9s+bOU6Lz+VzytHdLUaTAYOBosWBgtJ+hDbMB9HsnwRkiJOO3ppNhl+GZj8AA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T01:26:56.698458Z","bundle_sha256":"3ca418bdf0a8506060c95ceb96ad2b5b39e2495e717169383e942fb25d0a2046"}}