{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:NMKOBYECUXFVZF3TUNES55CKO6","short_pith_number":"pith:NMKOBYEC","canonical_record":{"source":{"id":"1705.01452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T14:39:56Z","cross_cats_sorted":[],"title_canon_sha256":"1f7bfff5d4905f13a4d48bd45f4526550eceacd92f3ba87db4348847135a1410","abstract_canon_sha256":"71555a4a75992d55f2dd2d2cfecc060ba59fddd6bcebe48043b1dc18bb99cf4c"},"schema_version":"1.0"},"canonical_sha256":"6b14e0e082a5cb5c9773a3492ef44a77a1c27d5e79cbe860242c5aaa9a57f4ca","source":{"kind":"arxiv","id":"1705.01452","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01452","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01452v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01452","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"NMKOBYECUXFV","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NMKOBYECUXFVZF3T","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NMKOBYEC","created_at":"2026-05-18T12:31:34Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:NMKOBYECUXFVZF3TUNES55CKO6","target":"record","payload":{"canonical_record":{"source":{"id":"1705.01452","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T14:39:56Z","cross_cats_sorted":[],"title_canon_sha256":"1f7bfff5d4905f13a4d48bd45f4526550eceacd92f3ba87db4348847135a1410","abstract_canon_sha256":"71555a4a75992d55f2dd2d2cfecc060ba59fddd6bcebe48043b1dc18bb99cf4c"},"schema_version":"1.0"},"canonical_sha256":"6b14e0e082a5cb5c9773a3492ef44a77a1c27d5e79cbe860242c5aaa9a57f4ca","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:45:05.161167Z","signature_b64":"R9VmJS2jbQ8lFT/+KkN1TVp7UaM6V95PJe6QszkmjdBBsEUB+OwvmMmW/JL+J41w+NLM+ymXBkNDPuHs1H20DA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6b14e0e082a5cb5c9773a3492ef44a77a1c27d5e79cbe860242c5aaa9a57f4ca","last_reissued_at":"2026-05-18T00:45:05.160749Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:45:05.160749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1705.01452","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"vr79EPtw5Bkb/TRWzSOBmGeWdjXKM1fy6cMB7LLjBudy30p2pc2eczEuYS7WIn1pKSPERpmVGeXRhuHKYtAcBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:45:44.160723Z"},"content_sha256":"708bd78dab64ef1d2b2f957258388124a1a5da06b760f8e7d62ae23d8ac2b786","schema_version":"1.0","event_id":"sha256:708bd78dab64ef1d2b2f957258388124a1a5da06b760f8e7d62ae23d8ac2b786"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:NMKOBYECUXFVZF3TUNES55CKO6","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Chunk-Based Bi-Scale Decoder for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Hang Li, Hao Zhou, Jiajun Chen, Shujian Huang, Xiaohua Liu, Zhaopeng Tu","submitted_at":"2017-05-03T14:39:56Z","abstract_excerpt":"In typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we propose a new type of decoder for NMT, which splits the decode state into two parts and updates them in two different time-scales. Specifically, we first predict a chunk time-scale state for phrasal modeling, on top of which multiple word time-scale states are generated. In this way, the target sentence is translated hierarchically from chunks to words, with information in different granularities being leveraged. Exper"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01452","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":"2026-05-18T00:45:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"1x3JClHddmHZfwjNIpNUcm3E0MKhxi+U0a1pdRanFcelo0imT08hQHERtSYpAQC+9Ltz/Mv3k0fFgb+fQO3zAw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-05T13:45:44.163819Z"},"content_sha256":"cfccf75a4830a2113e4fa59563ce0be91f2c5b338cdf9591e972c702c3d2f60e","schema_version":"1.0","event_id":"sha256:cfccf75a4830a2113e4fa59563ce0be91f2c5b338cdf9591e972c702c3d2f60e"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/NMKOBYECUXFVZF3TUNES55CKO6/bundle.json","state_url":"https://pith.science/pith/NMKOBYECUXFVZF3TUNES55CKO6/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/NMKOBYECUXFVZF3TUNES55CKO6/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":"2026-08-05T13:45:44Z","links":{"resolver":"https://pith.science/pith/NMKOBYECUXFVZF3TUNES55CKO6","bundle":"https://pith.science/pith/NMKOBYECUXFVZF3TUNES55CKO6/bundle.json","state":"https://pith.science/pith/NMKOBYECUXFVZF3TUNES55CKO6/state.json","well_known_bundle":"https://pith.science/.well-known/pith/NMKOBYECUXFVZF3TUNES55CKO6/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:NMKOBYECUXFVZF3TUNES55CKO6","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":"71555a4a75992d55f2dd2d2cfecc060ba59fddd6bcebe48043b1dc18bb99cf4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T14:39:56Z","title_canon_sha256":"1f7bfff5d4905f13a4d48bd45f4526550eceacd92f3ba87db4348847135a1410"},"schema_version":"1.0","source":{"id":"1705.01452","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1705.01452","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"arxiv_version","alias_value":"1705.01452v1","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1705.01452","created_at":"2026-05-18T00:45:05Z"},{"alias_kind":"pith_short_12","alias_value":"NMKOBYECUXFV","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_16","alias_value":"NMKOBYECUXFVZF3T","created_at":"2026-05-18T12:31:34Z"},{"alias_kind":"pith_short_8","alias_value":"NMKOBYEC","created_at":"2026-05-18T12:31:34Z"}],"graph_snapshots":[{"event_id":"sha256:cfccf75a4830a2113e4fa59563ce0be91f2c5b338cdf9591e972c702c3d2f60e","target":"graph","created_at":"2026-05-18T00:45:05Z","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 typical neural machine translation~(NMT), the decoder generates a sentence word by word, packing all linguistic granularities in the same time-scale of RNN. In this paper, we propose a new type of decoder for NMT, which splits the decode state into two parts and updates them in two different time-scales. Specifically, we first predict a chunk time-scale state for phrasal modeling, on top of which multiple word time-scale states are generated. In this way, the target sentence is translated hierarchically from chunks to words, with information in different granularities being leveraged. Exper","authors_text":"Hang Li, Hao Zhou, Jiajun Chen, Shujian Huang, Xiaohua Liu, Zhaopeng Tu","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T14:39:56Z","title":"Chunk-Based Bi-Scale Decoder for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1705.01452","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":"sha256:708bd78dab64ef1d2b2f957258388124a1a5da06b760f8e7d62ae23d8ac2b786","target":"record","created_at":"2026-05-18T00:45:05Z","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":"71555a4a75992d55f2dd2d2cfecc060ba59fddd6bcebe48043b1dc18bb99cf4c","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-05-03T14:39:56Z","title_canon_sha256":"1f7bfff5d4905f13a4d48bd45f4526550eceacd92f3ba87db4348847135a1410"},"schema_version":"1.0","source":{"id":"1705.01452","kind":"arxiv","version":1}},"canonical_sha256":"6b14e0e082a5cb5c9773a3492ef44a77a1c27d5e79cbe860242c5aaa9a57f4ca","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"6b14e0e082a5cb5c9773a3492ef44a77a1c27d5e79cbe860242c5aaa9a57f4ca","first_computed_at":"2026-05-18T00:45:05.160749Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:45:05.160749Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"R9VmJS2jbQ8lFT/+KkN1TVp7UaM6V95PJe6QszkmjdBBsEUB+OwvmMmW/JL+J41w+NLM+ymXBkNDPuHs1H20DA==","signature_status":"signed_v1","signed_at":"2026-05-18T00:45:05.161167Z","signed_message":"canonical_sha256_bytes"},"source_id":"1705.01452","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:708bd78dab64ef1d2b2f957258388124a1a5da06b760f8e7d62ae23d8ac2b786","sha256:cfccf75a4830a2113e4fa59563ce0be91f2c5b338cdf9591e972c702c3d2f60e"],"state_sha256":"8f9816b0eeb9c01da88e543f2e4c67ec4806640f3556004115fc000e2160e593"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"FqFMq+4le4I44+4gzP+r0uXXM08Oq3+TUTrcZ3mnb9xp5IXA+LBR1qbQlptkzCHuKW31n7Mr291agyf5Y+XLAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-05T13:45:44.177162Z","bundle_sha256":"b91e362f347d5a9a07bc2515a001a9f2586ddb271659a3a7fd8638b638dbf62f"}}