{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:7Z5DHUE4QOWNJHUYFK75RLWGVJ","short_pith_number":"pith:7Z5DHUE4","canonical_record":{"source":{"id":"1811.05683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T08:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"80663258ee3293660da16eddc2497043a2a8c78fa5747936a1087c9876799fc8","abstract_canon_sha256":"f42a99f84d847f2c23fb8c08f5cc9e9a92de5c3881bdcb0ac39fb0e3a8180f77"},"schema_version":"1.0"},"canonical_sha256":"fe7a33d09c83acd49e982abfd8aec6aa73b8c8537d99cb498167e4e2c5af9bb5","source":{"kind":"arxiv","id":"1811.05683","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05683","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05683v1","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05683","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"7Z5DHUE4QOWN","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"7Z5DHUE4QOWNJHUY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"7Z5DHUE4","created_at":"2026-05-18T12:32:13Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:7Z5DHUE4QOWNJHUYFK75RLWGVJ","target":"record","payload":{"canonical_record":{"source":{"id":"1811.05683","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T08:22:27Z","cross_cats_sorted":[],"title_canon_sha256":"80663258ee3293660da16eddc2497043a2a8c78fa5747936a1087c9876799fc8","abstract_canon_sha256":"f42a99f84d847f2c23fb8c08f5cc9e9a92de5c3881bdcb0ac39fb0e3a8180f77"},"schema_version":"1.0"},"canonical_sha256":"fe7a33d09c83acd49e982abfd8aec6aa73b8c8537d99cb498167e4e2c5af9bb5","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:00:42.356575Z","signature_b64":"BVnno7uZj1GUaDeuYXXi3f+rMmOa/DNZg4C1tpBTiEEF9sDrkfSF4/wk+DC1yj24Ez5RltejFAgC6D0w4dfiDQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"fe7a33d09c83acd49e982abfd8aec6aa73b8c8537d99cb498167e4e2c5af9bb5","last_reissued_at":"2026-05-18T00:00:42.355893Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:00:42.355893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1811.05683","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":"2026-05-18T00:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"rFVtgBdW7vHKuXrHgKHlOFod0512HqW//w5UCNKbmmeLngTCotuxG4fWNKdhYxc5wt+vg9Q12G15ojP1ee8KCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:12:07.121889Z"},"content_sha256":"093bad26ab35e38813a0e7cdcf88c54880548485cc3a40b1e213c8462ee56799","schema_version":"1.0","event_id":"sha256:093bad26ab35e38813a0e7cdcf88c54880548485cc3a40b1e213c8462ee56799"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:7Z5DHUE4QOWNJHUYFK75RLWGVJ","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Modeling Coherence for Discourse Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"HaiFeng Wang, Hao Xiong, Hua Wu, Zhongjun He","submitted_at":"2018-11-14T08:22:27Z","abstract_excerpt":"Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which affects the coherence of the text. In this paper, we propose to use discourse context and reward to refine the translation quality from the discourse perspective. In particular, we generate the translation of individual sentences at first. Next, we deliberate the preliminary produced translations, and train the model to learn the policy that produces discourse co"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05683","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":"2026-05-18T00:00:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Gkoa5HjMv246CQeOPPYcYwFAISY+6w6pLUIicnCFpNM2RB2XsOVeBVWj2z/4woLnBR5iOTsdiHw2/2t2F2ayDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-03T22:12:07.122224Z"},"content_sha256":"9bca21054c0936b9118788821d9876900e501b386ab084ee3824eb0ac9f528e0","schema_version":"1.0","event_id":"sha256:9bca21054c0936b9118788821d9876900e501b386ab084ee3824eb0ac9f528e0"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/7Z5DHUE4QOWNJHUYFK75RLWGVJ/bundle.json","state_url":"https://pith.science/pith/7Z5DHUE4QOWNJHUYFK75RLWGVJ/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/7Z5DHUE4QOWNJHUYFK75RLWGVJ/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":"2026-06-03T22:12:07Z","links":{"resolver":"https://pith.science/pith/7Z5DHUE4QOWNJHUYFK75RLWGVJ","bundle":"https://pith.science/pith/7Z5DHUE4QOWNJHUYFK75RLWGVJ/bundle.json","state":"https://pith.science/pith/7Z5DHUE4QOWNJHUYFK75RLWGVJ/state.json","well_known_bundle":"https://pith.science/.well-known/pith/7Z5DHUE4QOWNJHUYFK75RLWGVJ/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:7Z5DHUE4QOWNJHUYFK75RLWGVJ","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":"f42a99f84d847f2c23fb8c08f5cc9e9a92de5c3881bdcb0ac39fb0e3a8180f77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T08:22:27Z","title_canon_sha256":"80663258ee3293660da16eddc2497043a2a8c78fa5747936a1087c9876799fc8"},"schema_version":"1.0","source":{"id":"1811.05683","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1811.05683","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"arxiv_version","alias_value":"1811.05683v1","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1811.05683","created_at":"2026-05-18T00:00:42Z"},{"alias_kind":"pith_short_12","alias_value":"7Z5DHUE4QOWN","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_16","alias_value":"7Z5DHUE4QOWNJHUY","created_at":"2026-05-18T12:32:13Z"},{"alias_kind":"pith_short_8","alias_value":"7Z5DHUE4","created_at":"2026-05-18T12:32:13Z"}],"graph_snapshots":[{"event_id":"sha256:9bca21054c0936b9118788821d9876900e501b386ab084ee3824eb0ac9f528e0","target":"graph","created_at":"2026-05-18T00:00:42Z","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":"Discourse coherence plays an important role in the translation of one text. However, the previous reported models most focus on improving performance over individual sentence while ignoring cross-sentence links and dependencies, which affects the coherence of the text. In this paper, we propose to use discourse context and reward to refine the translation quality from the discourse perspective. In particular, we generate the translation of individual sentences at first. Next, we deliberate the preliminary produced translations, and train the model to learn the policy that produces discourse co","authors_text":"HaiFeng Wang, Hao Xiong, Hua Wu, Zhongjun He","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T08:22:27Z","title":"Modeling Coherence for Discourse Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1811.05683","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":"sha256:093bad26ab35e38813a0e7cdcf88c54880548485cc3a40b1e213c8462ee56799","target":"record","created_at":"2026-05-18T00:00:42Z","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":"f42a99f84d847f2c23fb8c08f5cc9e9a92de5c3881bdcb0ac39fb0e3a8180f77","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-11-14T08:22:27Z","title_canon_sha256":"80663258ee3293660da16eddc2497043a2a8c78fa5747936a1087c9876799fc8"},"schema_version":"1.0","source":{"id":"1811.05683","kind":"arxiv","version":1}},"canonical_sha256":"fe7a33d09c83acd49e982abfd8aec6aa73b8c8537d99cb498167e4e2c5af9bb5","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"fe7a33d09c83acd49e982abfd8aec6aa73b8c8537d99cb498167e4e2c5af9bb5","first_computed_at":"2026-05-18T00:00:42.355893Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:00:42.355893Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"BVnno7uZj1GUaDeuYXXi3f+rMmOa/DNZg4C1tpBTiEEF9sDrkfSF4/wk+DC1yj24Ez5RltejFAgC6D0w4dfiDQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:00:42.356575Z","signed_message":"canonical_sha256_bytes"},"source_id":"1811.05683","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:093bad26ab35e38813a0e7cdcf88c54880548485cc3a40b1e213c8462ee56799","sha256:9bca21054c0936b9118788821d9876900e501b386ab084ee3824eb0ac9f528e0"],"state_sha256":"7d28593a2f6c29a4430d8cf19ab8f07f34fa8668dbda85a7753c2d3407d2b3f2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Uj4o9VSgT4E9rdpWueMxZU4FkLkcLThQHyOG0T+O+4Q4Rc4CMgs/Bte7JE4wvqwesHvndaGMKJvZvFlQYgleAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-03T22:12:07.124061Z","bundle_sha256":"351a810c4fdd2bc8d41d7605cf8ac0562a307c39a9b2f62d9a641cabd156f82e"}}