{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2017:H65ZO2UQJNGBTLCBOSDMBXUQ2N","short_pith_number":"pith:H65ZO2UQ","canonical_record":{"source":{"id":"1706.08198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-06-26T00:55:04Z","cross_cats_sorted":[],"title_canon_sha256":"c791f9a6359c7c914386af7ebda205e4c97ccc992971ef51ab94cfff9497ee3a","abstract_canon_sha256":"29f8ade650d2546eaf9d3fbdc11e5b41b54f2f378c83abea5007f63f233a94e1"},"schema_version":"1.0"},"canonical_sha256":"3fbb976a904b4c19ac417486c0de90d358c90e541506ec225bf7556d5284481f","source":{"kind":"arxiv","id":"1706.08198","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.08198","created_at":"2026-05-18T00:41:43Z"},{"alias_kind":"arxiv_version","alias_value":"1706.08198v1","created_at":"2026-05-18T00:41:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08198","created_at":"2026-05-18T00:41:43Z"},{"alias_kind":"pith_short_12","alias_value":"H65ZO2UQJNGB","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H65ZO2UQJNGBTLCB","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H65ZO2UQ","created_at":"2026-05-18T12:31:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2017:H65ZO2UQJNGBTLCBOSDMBXUQ2N","target":"record","payload":{"canonical_record":{"source":{"id":"1706.08198","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-06-26T00:55:04Z","cross_cats_sorted":[],"title_canon_sha256":"c791f9a6359c7c914386af7ebda205e4c97ccc992971ef51ab94cfff9497ee3a","abstract_canon_sha256":"29f8ade650d2546eaf9d3fbdc11e5b41b54f2f378c83abea5007f63f233a94e1"},"schema_version":"1.0"},"canonical_sha256":"3fbb976a904b4c19ac417486c0de90d358c90e541506ec225bf7556d5284481f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:41:43.248512Z","signature_b64":"+EYF/6hOroZd1h+FceGO1aMo18u7i3VcylgkoB7HuHVLyWvaw5bAiNZNyek2BywQdiO9vT/1cKK1Jio3HtLiAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3fbb976a904b4c19ac417486c0de90d358c90e541506ec225bf7556d5284481f","last_reissued_at":"2026-05-18T00:41:43.247710Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:41:43.247710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1706.08198","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":"2026-05-18T00:41:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"VpwpD5Oo4y2tWq+oyLZqTZADGJ/7X84n6A6cW4bvKoRHSc3E/jGHUO0iO/jL5v1+hMrisbtF84MF8R65N3XPAg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T13:48:02.001766Z"},"content_sha256":"63aa8335c7cb675f98eea7363fd92f675b9c60a0bb4f51091368781132a333ec","schema_version":"1.0","event_id":"sha256:63aa8335c7cb675f98eea7363fd92f675b9c60a0bb4f51091368781132a333ec"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2017:H65ZO2UQJNGBTLCBOSDMBXUQ2N","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Mamoru Komachi, Takayuki Sato, Yukio Matsumura","submitted_at":"2017-06-26T00:55:04Z","abstract_excerpt":"Neural machine translation (NMT) has recently become popular in the field of machine translation. However, NMT suffers from the problem of repeating or missing words in the translation. To address this problem, Tu et al. (2017) proposed an encoder-decoder-reconstructor framework for NMT using back-translation. In this method, they selected the best forward translation model in the same manner as Bahdanau et al. (2015), and then trained a bi-directional translation model as fine-tuning. Their experiments show that it offers significant improvement in BLEU scores in Chinese-English translation t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08198","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":"2026-05-18T00:41:43Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"g3qLhXh2FL3SY32VMlE2UTnV4qUZXQoBYiYcBrACQqIaLCVDtfXDh4cxftGbzGwn0VniFXfbF6sW/rnIqVk1BQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-26T13:48:02.002122Z"},"content_sha256":"00ba601494105eb56d51fb4f0a411c3484d5385400b2eae11048e42edbe14eed","schema_version":"1.0","event_id":"sha256:00ba601494105eb56d51fb4f0a411c3484d5385400b2eae11048e42edbe14eed"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/H65ZO2UQJNGBTLCBOSDMBXUQ2N/bundle.json","state_url":"https://pith.science/pith/H65ZO2UQJNGBTLCBOSDMBXUQ2N/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/H65ZO2UQJNGBTLCBOSDMBXUQ2N/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":"2026-06-26T13:48:02Z","links":{"resolver":"https://pith.science/pith/H65ZO2UQJNGBTLCBOSDMBXUQ2N","bundle":"https://pith.science/pith/H65ZO2UQJNGBTLCBOSDMBXUQ2N/bundle.json","state":"https://pith.science/pith/H65ZO2UQJNGBTLCBOSDMBXUQ2N/state.json","well_known_bundle":"https://pith.science/.well-known/pith/H65ZO2UQJNGBTLCBOSDMBXUQ2N/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:H65ZO2UQJNGBTLCBOSDMBXUQ2N","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":"29f8ade650d2546eaf9d3fbdc11e5b41b54f2f378c83abea5007f63f233a94e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-06-26T00:55:04Z","title_canon_sha256":"c791f9a6359c7c914386af7ebda205e4c97ccc992971ef51ab94cfff9497ee3a"},"schema_version":"1.0","source":{"id":"1706.08198","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1706.08198","created_at":"2026-05-18T00:41:43Z"},{"alias_kind":"arxiv_version","alias_value":"1706.08198v1","created_at":"2026-05-18T00:41:43Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1706.08198","created_at":"2026-05-18T00:41:43Z"},{"alias_kind":"pith_short_12","alias_value":"H65ZO2UQJNGB","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_16","alias_value":"H65ZO2UQJNGBTLCB","created_at":"2026-05-18T12:31:18Z"},{"alias_kind":"pith_short_8","alias_value":"H65ZO2UQ","created_at":"2026-05-18T12:31:18Z"}],"graph_snapshots":[{"event_id":"sha256:00ba601494105eb56d51fb4f0a411c3484d5385400b2eae11048e42edbe14eed","target":"graph","created_at":"2026-05-18T00:41:43Z","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 (NMT) has recently become popular in the field of machine translation. However, NMT suffers from the problem of repeating or missing words in the translation. To address this problem, Tu et al. (2017) proposed an encoder-decoder-reconstructor framework for NMT using back-translation. In this method, they selected the best forward translation model in the same manner as Bahdanau et al. (2015), and then trained a bi-directional translation model as fine-tuning. Their experiments show that it offers significant improvement in BLEU scores in Chinese-English translation t","authors_text":"Mamoru Komachi, Takayuki Sato, Yukio Matsumura","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-06-26T00:55:04Z","title":"English-Japanese Neural Machine Translation with Encoder-Decoder-Reconstructor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1706.08198","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":"sha256:63aa8335c7cb675f98eea7363fd92f675b9c60a0bb4f51091368781132a333ec","target":"record","created_at":"2026-05-18T00:41:43Z","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":"29f8ade650d2546eaf9d3fbdc11e5b41b54f2f378c83abea5007f63f233a94e1","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2017-06-26T00:55:04Z","title_canon_sha256":"c791f9a6359c7c914386af7ebda205e4c97ccc992971ef51ab94cfff9497ee3a"},"schema_version":"1.0","source":{"id":"1706.08198","kind":"arxiv","version":1}},"canonical_sha256":"3fbb976a904b4c19ac417486c0de90d358c90e541506ec225bf7556d5284481f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"3fbb976a904b4c19ac417486c0de90d358c90e541506ec225bf7556d5284481f","first_computed_at":"2026-05-18T00:41:43.247710Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:41:43.247710Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"+EYF/6hOroZd1h+FceGO1aMo18u7i3VcylgkoB7HuHVLyWvaw5bAiNZNyek2BywQdiO9vT/1cKK1Jio3HtLiAg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:41:43.248512Z","signed_message":"canonical_sha256_bytes"},"source_id":"1706.08198","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:63aa8335c7cb675f98eea7363fd92f675b9c60a0bb4f51091368781132a333ec","sha256:00ba601494105eb56d51fb4f0a411c3484d5385400b2eae11048e42edbe14eed"],"state_sha256":"4d9dc3b5a32f78aa8ed0995bc7e59fee36c972c83387d2bba5013b170bbeeeef"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aiXXx74EPUPe7ZMCz2sDCzj+zLpw9Ig+i83V385ZrWegprvanp5bb6gFsGTp68c/MpE5U50kAK4cTbJTemUFAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-26T13:48:02.004040Z","bundle_sha256":"e99f736385484bc2de9e141ac6c1fa6c81c7a77166882a3c79f3f443a6ddd45f"}}