{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:QUZ4RONJ4DMA7W6OWLWTJCY6RR","short_pith_number":"pith:QUZ4RONJ","canonical_record":{"source":{"id":"1804.06506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T23:54:26Z","cross_cats_sorted":[],"title_canon_sha256":"f4a2a22ed8db7d378192815467f1ef97b8481ddc1b32bfc86093cb4a38e3e00f","abstract_canon_sha256":"12629964858ce35bd775d1b8fb5c06a6efadf43a65b961b7c09ae803b2535976"},"schema_version":"1.0"},"canonical_sha256":"8533c8b9a9e0d80fdbceb2ed348b1e8c5a8dc374bdfd9a7bcaf16e63a89b810d","source":{"kind":"arxiv","id":"1804.06506","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06506","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06506v1","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06506","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"QUZ4RONJ4DMA","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QUZ4RONJ4DMA7W6O","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QUZ4RONJ","created_at":"2026-05-18T12:32:46Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:QUZ4RONJ4DMA7W6OWLWTJCY6RR","target":"record","payload":{"canonical_record":{"source":{"id":"1804.06506","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T23:54:26Z","cross_cats_sorted":[],"title_canon_sha256":"f4a2a22ed8db7d378192815467f1ef97b8481ddc1b32bfc86093cb4a38e3e00f","abstract_canon_sha256":"12629964858ce35bd775d1b8fb5c06a6efadf43a65b961b7c09ae803b2535976"},"schema_version":"1.0"},"canonical_sha256":"8533c8b9a9e0d80fdbceb2ed348b1e8c5a8dc374bdfd9a7bcaf16e63a89b810d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:18:06.458499Z","signature_b64":"7yVrlwJj/mJ8AyWmLK+MJMF1k6nWnNyNG/ADFYv0K6mS7RX/QdpclBrxwzKkzrDRvuWYlw9FznHdxEulW+yWBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8533c8b9a9e0d80fdbceb2ed348b1e8c5a8dc374bdfd9a7bcaf16e63a89b810d","last_reissued_at":"2026-05-18T00:18:06.457912Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:18:06.457912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1804.06506","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":"2026-05-18T00:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"gWShF/cFluhGJ0cO44Nv4CevQN7u7mpJvTPjK6nBYCT4locm057c2PRtOqVmAgFMDoA5MHsAxUnu53yTCzp/Bw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:37:16.396373Z"},"content_sha256":"cbd63b23c088c072cbbde8e4cc8eb23fd2be9a55238b303f2674211c5a008764","schema_version":"1.0","event_id":"sha256:cbd63b23c088c072cbbde8e4cc8eb23fd2be9a55238b303f2674211c5a008764"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:QUZ4RONJ4DMA7W6OWLWTJCY6RR","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Andy Way, Peyman Passban, Qun Liu","submitted_at":"2018-04-17T23:54:26Z","abstract_excerpt":"Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large vocabulary and high out-of-vocabulary (OOV) word rate of MRLs. Therefore, it is not suitable to exploit existing word-based models to translate this set of languages. In this paper, we propose an extension to the state-of-the-art model of Chung et al. (2016), which works at the character level and boosts the decoder with target"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06506","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":"2026-05-18T00:18:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"nyV/PwOVs8cQEVOHgV/N8hTHP4zGPwZMEKth0gEosVzmFJhyu/1bzUFwkBtDA8epVByaDo2RtAULFJTass2VCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-04T15:37:16.396726Z"},"content_sha256":"3f5090c71a9aee5fa74f0630c3484bafda09b4e7bfbcbd38993acfb4d4107b3a","schema_version":"1.0","event_id":"sha256:3f5090c71a9aee5fa74f0630c3484bafda09b4e7bfbcbd38993acfb4d4107b3a"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QUZ4RONJ4DMA7W6OWLWTJCY6RR/bundle.json","state_url":"https://pith.science/pith/QUZ4RONJ4DMA7W6OWLWTJCY6RR/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QUZ4RONJ4DMA7W6OWLWTJCY6RR/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":"2026-06-04T15:37:16Z","links":{"resolver":"https://pith.science/pith/QUZ4RONJ4DMA7W6OWLWTJCY6RR","bundle":"https://pith.science/pith/QUZ4RONJ4DMA7W6OWLWTJCY6RR/bundle.json","state":"https://pith.science/pith/QUZ4RONJ4DMA7W6OWLWTJCY6RR/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QUZ4RONJ4DMA7W6OWLWTJCY6RR/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:QUZ4RONJ4DMA7W6OWLWTJCY6RR","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":"12629964858ce35bd775d1b8fb5c06a6efadf43a65b961b7c09ae803b2535976","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T23:54:26Z","title_canon_sha256":"f4a2a22ed8db7d378192815467f1ef97b8481ddc1b32bfc86093cb4a38e3e00f"},"schema_version":"1.0","source":{"id":"1804.06506","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1804.06506","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"arxiv_version","alias_value":"1804.06506v1","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1804.06506","created_at":"2026-05-18T00:18:06Z"},{"alias_kind":"pith_short_12","alias_value":"QUZ4RONJ4DMA","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_16","alias_value":"QUZ4RONJ4DMA7W6O","created_at":"2026-05-18T12:32:46Z"},{"alias_kind":"pith_short_8","alias_value":"QUZ4RONJ","created_at":"2026-05-18T12:32:46Z"}],"graph_snapshots":[{"event_id":"sha256:3f5090c71a9aee5fa74f0630c3484bafda09b4e7bfbcbd38993acfb4d4107b3a","target":"graph","created_at":"2026-05-18T00:18:06Z","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":"Recently, neural machine translation (NMT) has emerged as a powerful alternative to conventional statistical approaches. However, its performance drops considerably in the presence of morphologically rich languages (MRLs). Neural engines usually fail to tackle the large vocabulary and high out-of-vocabulary (OOV) word rate of MRLs. Therefore, it is not suitable to exploit existing word-based models to translate this set of languages. In this paper, we propose an extension to the state-of-the-art model of Chung et al. (2016), which works at the character level and boosts the decoder with target","authors_text":"Andy Way, Peyman Passban, Qun Liu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T23:54:26Z","title":"Improving Character-based Decoding Using Target-Side Morphological Information for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1804.06506","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:cbd63b23c088c072cbbde8e4cc8eb23fd2be9a55238b303f2674211c5a008764","target":"record","created_at":"2026-05-18T00:18:06Z","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":"12629964858ce35bd775d1b8fb5c06a6efadf43a65b961b7c09ae803b2535976","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-04-17T23:54:26Z","title_canon_sha256":"f4a2a22ed8db7d378192815467f1ef97b8481ddc1b32bfc86093cb4a38e3e00f"},"schema_version":"1.0","source":{"id":"1804.06506","kind":"arxiv","version":1}},"canonical_sha256":"8533c8b9a9e0d80fdbceb2ed348b1e8c5a8dc374bdfd9a7bcaf16e63a89b810d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8533c8b9a9e0d80fdbceb2ed348b1e8c5a8dc374bdfd9a7bcaf16e63a89b810d","first_computed_at":"2026-05-18T00:18:06.457912Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:18:06.457912Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"7yVrlwJj/mJ8AyWmLK+MJMF1k6nWnNyNG/ADFYv0K6mS7RX/QdpclBrxwzKkzrDRvuWYlw9FznHdxEulW+yWBQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:18:06.458499Z","signed_message":"canonical_sha256_bytes"},"source_id":"1804.06506","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:cbd63b23c088c072cbbde8e4cc8eb23fd2be9a55238b303f2674211c5a008764","sha256:3f5090c71a9aee5fa74f0630c3484bafda09b4e7bfbcbd38993acfb4d4107b3a"],"state_sha256":"b1737df1dd2e133b5d13b6b826edf5a8c5c727e6c6c376159b0726e84f2e387c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"O5qjI1yNZ2EZK0kIxXJfsiNqnIr4QtsELDMFNr5G1xnXOJ0DsANdNjcgW62DEJ5yUJfeqAxag7HkPzq9mMIeDw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-04T15:37:16.398716Z","bundle_sha256":"fbcd43c078ca07800da39bed723521b8578e37d6b6099ecabdb79049291555e4"}}