{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2017:565B5WKSS6AMWDLKEMIDIJ5NZH","short_pith_number":"pith:565B5WKS","schema_version":"1.0","canonical_sha256":"efba1ed9529780cb0d6a23103427adc9ea225ee03252c87272c1e7fe3ef85866","source":{"kind":"arxiv","id":"1707.07402","version":4},"attestation_state":"computed","paper":{"title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hal Daum\\'e III, Jordan Boyd-Graber, Khanh Nguyen","submitted_at":"2017-07-24T04:35:19Z","abstract_excerpt":"Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems from simulated human feedback. Our algorithm combines the advantage actor-critic algorithm (Mnih et al., 2016) with the attention-based neural encoder-decoder architecture (Luong et al., 2015). This algor"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"1707.07402","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-24T04:35:19Z","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"title_canon_sha256":"4296bbd493218810414903340d497c3d0f5b8d0de765a2a09e938f58f8909b59","abstract_canon_sha256":"2e92203b732f674216a011e5ff9b3a8741c63960dcff43337da5ce983729ddf4"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-18T00:30:50.581290Z","signature_b64":"/jHRRaPBJfVbXnZJ5qhsdpBmlN2AIbynMr9cMOIIJTI0ZlKfrJBZiCSJ5Yf+vCP8EjfaCz+qslky2ZkfQOdUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"efba1ed9529780cb0d6a23103427adc9ea225ee03252c87272c1e7fe3ef85866","last_reissued_at":"2026-05-18T00:30:50.580791Z","signature_status":"signed_v1","first_computed_at":"2026-05-18T00:30:50.580791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.HC","cs.LG"],"primary_cat":"cs.CL","authors_text":"Hal Daum\\'e III, Jordan Boyd-Graber, Khanh Nguyen","submitted_at":"2017-07-24T04:35:19Z","abstract_excerpt":"Machine translation is a natural candidate problem for reinforcement learning from human feedback: users provide quick, dirty ratings on candidate translations to guide a system to improve. Yet, current neural machine translation training focuses on expensive human-generated reference translations. We describe a reinforcement learning algorithm that improves neural machine translation systems from simulated human feedback. Our algorithm combines the advantage actor-critic algorithm (Mnih et al., 2016) with the attention-based neural encoder-decoder architecture (Luong et al., 2015). This algor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07402","kind":"arxiv","version":4},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"1707.07402","created_at":"2026-05-18T00:30:50.580866+00:00"},{"alias_kind":"arxiv_version","alias_value":"1707.07402v4","created_at":"2026-05-18T00:30:50.580866+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07402","created_at":"2026-05-18T00:30:50.580866+00:00"},{"alias_kind":"pith_short_12","alias_value":"565B5WKSS6AM","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_16","alias_value":"565B5WKSS6AMWDLK","created_at":"2026-05-18T12:31:00.734936+00:00"},{"alias_kind":"pith_short_8","alias_value":"565B5WKS","created_at":"2026-05-18T12:31:00.734936+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2009.01325","citing_title":"Learning to summarize from human feedback","ref_index":43,"is_internal_anchor":true},{"citing_arxiv_id":"1909.08593","citing_title":"Fine-Tuning Language Models from Human Preferences","ref_index":18,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH","json":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH.json","graph_json":"https://pith.science/api/pith-number/565B5WKSS6AMWDLKEMIDIJ5NZH/graph.json","events_json":"https://pith.science/api/pith-number/565B5WKSS6AMWDLKEMIDIJ5NZH/events.json","paper":"https://pith.science/paper/565B5WKS"},"agent_actions":{"view_html":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH","download_json":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH.json","view_paper":"https://pith.science/paper/565B5WKS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=1707.07402&json=true","fetch_graph":"https://pith.science/api/pith-number/565B5WKSS6AMWDLKEMIDIJ5NZH/graph.json","fetch_events":"https://pith.science/api/pith-number/565B5WKSS6AMWDLKEMIDIJ5NZH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH/action/storage_attestation","attest_author":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH/action/author_attestation","sign_citation":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH/action/citation_signature","submit_replication":"https://pith.science/pith/565B5WKSS6AMWDLKEMIDIJ5NZH/action/replication_record"}},"created_at":"2026-05-18T00:30:50.580866+00:00","updated_at":"2026-05-18T00:30:50.580866+00:00"}