{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:IXH5HBM63ASHMTRGQ4GOM7DLAT","short_pith_number":"pith:IXH5HBM6","canonical_record":{"source":{"id":"1808.04064","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-13T05:03:42Z","cross_cats_sorted":[],"title_canon_sha256":"530789b636a1ea580f0a5a291bf235373547f3dd75e88eb2ef1aae3c965b21e8","abstract_canon_sha256":"ebe3b8a9d8dd76c496ec1ff15ed4a730d2aa1c23c4ec93b43ae168c4350d5dcf"},"schema_version":"1.0"},"canonical_sha256":"45cfd3859ed824764e26870ce67c6b04e7489aec7cbac5d0eea1cdb298da686d","source":{"kind":"arxiv","id":"1808.04064","version":2},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04064","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04064v2","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04064","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"IXH5HBM63ASH","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IXH5HBM63ASHMTRG","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IXH5HBM6","created_at":"2026-05-18T12:32:31Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:IXH5HBM63ASHMTRGQ4GOM7DLAT","target":"record","payload":{"canonical_record":{"source":{"id":"1808.04064","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-13T05:03:42Z","cross_cats_sorted":[],"title_canon_sha256":"530789b636a1ea580f0a5a291bf235373547f3dd75e88eb2ef1aae3c965b21e8","abstract_canon_sha256":"ebe3b8a9d8dd76c496ec1ff15ed4a730d2aa1c23c4ec93b43ae168c4350d5dcf"},"schema_version":"1.0"},"canonical_sha256":"45cfd3859ed824764e26870ce67c6b04e7489aec7cbac5d0eea1cdb298da686d","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:01:01.724939Z","signature_b64":"xr7Ewrm6M5JrFenDNteK5eORwBKDjkGN/EZ9ov66Pi5PPAHwOWPLn5Jyf/0J18Lzfbi62+gmjQG8HDZw+EkDAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"45cfd3859ed824764e26870ce67c6b04e7489aec7cbac5d0eea1cdb298da686d","last_reissued_at":"2026-05-18T00:01:01.724370Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:01:01.724370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.04064","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":"2026-05-18T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"xEOHtdbqGN4Ia2oBqsk7mj663UfeYRCFY987bbb3emLCNiUHlH3oj87U46EQXXjclXnCt/ylc50wOEXAiNH1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:59:07.101507Z"},"content_sha256":"3ae9906e31bf5767f315f9f28731fd19f1a1bed7878c3823206e5f0b254a33bd","schema_version":"1.0","event_id":"sha256:3ae9906e31bf5767f315f9f28731fd19f1a1bed7878c3823206e5f0b254a33bd"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:IXH5HBM63ASHMTRGQ4GOM7DLAT","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Regularizing Neural Machine Translation by Target-bidirectional Agreement","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Ming Zhou, Mu Li, Shuangzhi Wu, Shujie Liu, Tong Xu, Zhirui Zhang","submitted_at":"2018-08-13T05:03:42Z","abstract_excerpt":"Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation process are fed as inputs to the model and can be quickly amplified, harming subsequent sequence generation. To address this issue, we propose a novel model regularization method for NMT training, which aims to improve the agreement between translations generated by left-to-right (L2R) and right-to-left (R2L) NMT decoders. This goal is achieved by introducing two "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04064","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":"2026-05-18T00:01:01Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"4HuYDMjWTVAbnhLchoK8EvDT5MeFL7bca2bOeeV2B8k7xYT+DWHyYci5Fhw73RwVOGneUfpZnNV96kEBZxtABQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T20:59:07.102221Z"},"content_sha256":"0bee862e215b4c60de81d8996ad5bfac27425f3f84de4282ed7ec425236ccffb","schema_version":"1.0","event_id":"sha256:0bee862e215b4c60de81d8996ad5bfac27425f3f84de4282ed7ec425236ccffb"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/IXH5HBM63ASHMTRGQ4GOM7DLAT/bundle.json","state_url":"https://pith.science/pith/IXH5HBM63ASHMTRGQ4GOM7DLAT/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/IXH5HBM63ASHMTRGQ4GOM7DLAT/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":"2026-05-25T20:59:07Z","links":{"resolver":"https://pith.science/pith/IXH5HBM63ASHMTRGQ4GOM7DLAT","bundle":"https://pith.science/pith/IXH5HBM63ASHMTRGQ4GOM7DLAT/bundle.json","state":"https://pith.science/pith/IXH5HBM63ASHMTRGQ4GOM7DLAT/state.json","well_known_bundle":"https://pith.science/.well-known/pith/IXH5HBM63ASHMTRGQ4GOM7DLAT/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:IXH5HBM63ASHMTRGQ4GOM7DLAT","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":"ebe3b8a9d8dd76c496ec1ff15ed4a730d2aa1c23c4ec93b43ae168c4350d5dcf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-13T05:03:42Z","title_canon_sha256":"530789b636a1ea580f0a5a291bf235373547f3dd75e88eb2ef1aae3c965b21e8"},"schema_version":"1.0","source":{"id":"1808.04064","kind":"arxiv","version":2}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.04064","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"arxiv_version","alias_value":"1808.04064v2","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.04064","created_at":"2026-05-18T00:01:01Z"},{"alias_kind":"pith_short_12","alias_value":"IXH5HBM63ASH","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_16","alias_value":"IXH5HBM63ASHMTRG","created_at":"2026-05-18T12:32:31Z"},{"alias_kind":"pith_short_8","alias_value":"IXH5HBM6","created_at":"2026-05-18T12:32:31Z"}],"graph_snapshots":[{"event_id":"sha256:0bee862e215b4c60de81d8996ad5bfac27425f3f84de4282ed7ec425236ccffb","target":"graph","created_at":"2026-05-18T00:01:01Z","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":"Although Neural Machine Translation (NMT) has achieved remarkable progress in the past several years, most NMT systems still suffer from a fundamental shortcoming as in other sequence generation tasks: errors made early in generation process are fed as inputs to the model and can be quickly amplified, harming subsequent sequence generation. To address this issue, we propose a novel model regularization method for NMT training, which aims to improve the agreement between translations generated by left-to-right (L2R) and right-to-left (R2L) NMT decoders. This goal is achieved by introducing two ","authors_text":"Ming Zhou, Mu Li, Shuangzhi Wu, Shujie Liu, Tong Xu, Zhirui Zhang","cross_cats":[],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-13T05:03:42Z","title":"Regularizing Neural Machine Translation by Target-bidirectional Agreement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.04064","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":"sha256:3ae9906e31bf5767f315f9f28731fd19f1a1bed7878c3823206e5f0b254a33bd","target":"record","created_at":"2026-05-18T00:01:01Z","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":"ebe3b8a9d8dd76c496ec1ff15ed4a730d2aa1c23c4ec93b43ae168c4350d5dcf","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2018-08-13T05:03:42Z","title_canon_sha256":"530789b636a1ea580f0a5a291bf235373547f3dd75e88eb2ef1aae3c965b21e8"},"schema_version":"1.0","source":{"id":"1808.04064","kind":"arxiv","version":2}},"canonical_sha256":"45cfd3859ed824764e26870ce67c6b04e7489aec7cbac5d0eea1cdb298da686d","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"45cfd3859ed824764e26870ce67c6b04e7489aec7cbac5d0eea1cdb298da686d","first_computed_at":"2026-05-18T00:01:01.724370Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:01:01.724370Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"xr7Ewrm6M5JrFenDNteK5eORwBKDjkGN/EZ9ov66Pi5PPAHwOWPLn5Jyf/0J18Lzfbi62+gmjQG8HDZw+EkDAQ==","signature_status":"signed_v1","signed_at":"2026-05-18T00:01:01.724939Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.04064","source_kind":"arxiv","source_version":2}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:3ae9906e31bf5767f315f9f28731fd19f1a1bed7878c3823206e5f0b254a33bd","sha256:0bee862e215b4c60de81d8996ad5bfac27425f3f84de4282ed7ec425236ccffb"],"state_sha256":"59dc6b51fa6f82349be5147c2fbc489ac83c90764ce38cad10ec903ba609fe58"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"bB6PM/Qwj8BJMV/pX/R6FE57ZPxRmk5QXiIXkWvRDzHKloHs2Sbvx6dU8qXWwlLO5O2XEW5peCkZQUkchljkAg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T20:59:07.129470Z","bundle_sha256":"e4c0430a3b49d38ed97c4b7d3db6c034bcba76f0cc4f0634d61c1d2d9325f3a7"}}