{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2018:PDRQZQYHW2DOAODCP2YK4Y4WIG","short_pith_number":"pith:PDRQZQYH","canonical_record":{"source":{"id":"1808.08866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T14:43:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bdb1ee28b6e0fe1cc7f7ddb914912f76c8ef94ff1528d4f6f16334a10884200d","abstract_canon_sha256":"d6ab28c3fb398b82636f310d6f1a3a8bad6dc58c0c693c7c96d02d588ec097ac"},"schema_version":"1.0"},"canonical_sha256":"78e30cc307b686e038627eb0ae63964195ca34779d3b760bfd4a740e92aebd64","source":{"kind":"arxiv","id":"1808.08866","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08866","created_at":"2026-05-18T00:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08866v1","created_at":"2026-05-18T00:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08866","created_at":"2026-05-18T00:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"PDRQZQYHW2DO","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PDRQZQYHW2DOAODC","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PDRQZQYH","created_at":"2026-05-18T12:32:43Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2018:PDRQZQYHW2DOAODCP2YK4Y4WIG","target":"record","payload":{"canonical_record":{"source":{"id":"1808.08866","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T14:43:38Z","cross_cats_sorted":["cs.AI","stat.ML"],"title_canon_sha256":"bdb1ee28b6e0fe1cc7f7ddb914912f76c8ef94ff1528d4f6f16334a10884200d","abstract_canon_sha256":"d6ab28c3fb398b82636f310d6f1a3a8bad6dc58c0c693c7c96d02d588ec097ac"},"schema_version":"1.0"},"canonical_sha256":"78e30cc307b686e038627eb0ae63964195ca34779d3b760bfd4a740e92aebd64","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:07:12.997714Z","signature_b64":"RsnvOnZAPAvEXBbAVaxlZdD/15L/IKkMkTOXh+j1kvxcefZ1WhZDNFk1u5uvFpQcWitKwCjt5Zcuf0SzPj37Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"78e30cc307b686e038627eb0ae63964195ca34779d3b760bfd4a740e92aebd64","last_reissued_at":"2026-05-18T00:07:12.997223Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:07:12.997223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"1808.08866","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":"2026-05-18T00:07:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"QwPdOAx6tMwtm83i/9mGQ/4p9goJb+f2VdEoI4nReJzYFddCp3HFZN4ZKNTNja0v7NGgQ/LDdV/K8A5ymManDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:29:53.476119Z"},"content_sha256":"4575362f6c2dccb0616a57942ccebd883587293f0ffc8e794250a0f31b29abfa","schema_version":"1.0","event_id":"sha256:4575362f6c2dccb0616a57942ccebd883587293f0ffc8e794250a0f31b29abfa"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2018:PDRQZQYHW2DOAODCP2YK4Y4WIG","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"A Study of Reinforcement Learning for Neural Machine Translation","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","stat.ML"],"primary_cat":"cs.LG","authors_text":"Fei Tian, Jianhuang Lai, Lijun Wu, Tao Qin, Tie-Yan Liu","submitted_at":"2018-08-27T14:43:38Z","abstract_excerpt":"Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging, especially in real-world systems where deep models and large datasets are leveraged. In this paper, taking several large-scale translation tasks as testbeds, we conduct a systematic study on how to train better NMT models using reinforcement learning. We provide a comprehensive comparison of several important factors (e.g., baseline reward, reward shaping) in RL tra"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08866","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":"2026-05-18T00:07:12Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"jY4UsPUZcLhfLxc0Be0N52SX/9f5oXqR8UvQs+K+AJWXHh+nqlzq7v96VkIP+6xK+tmh1ZoUtlKPDeRZRV21Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-25T21:29:53.476811Z"},"content_sha256":"55342cfc4e68d55c1bc0abed1897b36e07914a9a50b01bcd67475b164fa59ce1","schema_version":"1.0","event_id":"sha256:55342cfc4e68d55c1bc0abed1897b36e07914a9a50b01bcd67475b164fa59ce1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/PDRQZQYHW2DOAODCP2YK4Y4WIG/bundle.json","state_url":"https://pith.science/pith/PDRQZQYHW2DOAODCP2YK4Y4WIG/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/PDRQZQYHW2DOAODCP2YK4Y4WIG/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":"2026-05-25T21:29:53Z","links":{"resolver":"https://pith.science/pith/PDRQZQYHW2DOAODCP2YK4Y4WIG","bundle":"https://pith.science/pith/PDRQZQYHW2DOAODCP2YK4Y4WIG/bundle.json","state":"https://pith.science/pith/PDRQZQYHW2DOAODCP2YK4Y4WIG/state.json","well_known_bundle":"https://pith.science/.well-known/pith/PDRQZQYHW2DOAODCP2YK4Y4WIG/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2018:PDRQZQYHW2DOAODCP2YK4Y4WIG","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":"d6ab28c3fb398b82636f310d6f1a3a8bad6dc58c0c693c7c96d02d588ec097ac","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T14:43:38Z","title_canon_sha256":"bdb1ee28b6e0fe1cc7f7ddb914912f76c8ef94ff1528d4f6f16334a10884200d"},"schema_version":"1.0","source":{"id":"1808.08866","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1808.08866","created_at":"2026-05-18T00:07:12Z"},{"alias_kind":"arxiv_version","alias_value":"1808.08866v1","created_at":"2026-05-18T00:07:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1808.08866","created_at":"2026-05-18T00:07:12Z"},{"alias_kind":"pith_short_12","alias_value":"PDRQZQYHW2DO","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_16","alias_value":"PDRQZQYHW2DOAODC","created_at":"2026-05-18T12:32:43Z"},{"alias_kind":"pith_short_8","alias_value":"PDRQZQYH","created_at":"2026-05-18T12:32:43Z"}],"graph_snapshots":[{"event_id":"sha256:55342cfc4e68d55c1bc0abed1897b36e07914a9a50b01bcd67475b164fa59ce1","target":"graph","created_at":"2026-05-18T00:07:12Z","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":"Recent studies have shown that reinforcement learning (RL) is an effective approach for improving the performance of neural machine translation (NMT) system. However, due to its instability, successfully RL training is challenging, especially in real-world systems where deep models and large datasets are leveraged. In this paper, taking several large-scale translation tasks as testbeds, we conduct a systematic study on how to train better NMT models using reinforcement learning. We provide a comprehensive comparison of several important factors (e.g., baseline reward, reward shaping) in RL tra","authors_text":"Fei Tian, Jianhuang Lai, Lijun Wu, Tao Qin, Tie-Yan Liu","cross_cats":["cs.AI","stat.ML"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T14:43:38Z","title":"A Study of Reinforcement Learning for Neural Machine Translation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1808.08866","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":"sha256:4575362f6c2dccb0616a57942ccebd883587293f0ffc8e794250a0f31b29abfa","target":"record","created_at":"2026-05-18T00:07:12Z","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":"d6ab28c3fb398b82636f310d6f1a3a8bad6dc58c0c693c7c96d02d588ec097ac","cross_cats_sorted":["cs.AI","stat.ML"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2018-08-27T14:43:38Z","title_canon_sha256":"bdb1ee28b6e0fe1cc7f7ddb914912f76c8ef94ff1528d4f6f16334a10884200d"},"schema_version":"1.0","source":{"id":"1808.08866","kind":"arxiv","version":1}},"canonical_sha256":"78e30cc307b686e038627eb0ae63964195ca34779d3b760bfd4a740e92aebd64","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"78e30cc307b686e038627eb0ae63964195ca34779d3b760bfd4a740e92aebd64","first_computed_at":"2026-05-18T00:07:12.997223Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:07:12.997223Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RsnvOnZAPAvEXBbAVaxlZdD/15L/IKkMkTOXh+j1kvxcefZ1WhZDNFk1u5uvFpQcWitKwCjt5Zcuf0SzPj37Cg==","signature_status":"signed_v1","signed_at":"2026-05-18T00:07:12.997714Z","signed_message":"canonical_sha256_bytes"},"source_id":"1808.08866","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:4575362f6c2dccb0616a57942ccebd883587293f0ffc8e794250a0f31b29abfa","sha256:55342cfc4e68d55c1bc0abed1897b36e07914a9a50b01bcd67475b164fa59ce1"],"state_sha256":"4bcea94762845f200a245fc08c82e3152c99cc5ee68534c73cea091cfe4b7341"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"OOvYiMDMnAgzcu+1kFs37xYreLEftoamQ9GXo+hzpavaqJ70HCuFxy0r+ZBfEZDBDn44UftxYdd3FL59h4syDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-25T21:29:53.480574Z","bundle_sha256":"9f9dbc104d8d04b36237db2ce2011d7100c5ef4d745820a372202fcf800bc3fe"}}