{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2017:565B5WKSS6AMWDLKEMIDIJ5NZH","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":"2e92203b732f674216a011e5ff9b3a8741c63960dcff43337da5ce983729ddf4","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-24T04:35:19Z","title_canon_sha256":"4296bbd493218810414903340d497c3d0f5b8d0de765a2a09e938f58f8909b59"},"schema_version":"1.0","source":{"id":"1707.07402","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1707.07402","created_at":"2026-05-18T00:30:50Z"},{"alias_kind":"arxiv_version","alias_value":"1707.07402v4","created_at":"2026-05-18T00:30:50Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1707.07402","created_at":"2026-05-18T00:30:50Z"},{"alias_kind":"pith_short_12","alias_value":"565B5WKSS6AM","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_16","alias_value":"565B5WKSS6AMWDLK","created_at":"2026-05-18T12:31:00Z"},{"alias_kind":"pith_short_8","alias_value":"565B5WKS","created_at":"2026-05-18T12:31:00Z"}],"graph_snapshots":[{"event_id":"sha256:0886993d0acc6a5b742aa512de5fe306a9e5cee5c557fecf458278745e7040a7","target":"graph","created_at":"2026-05-18T00:30:50Z","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":"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","authors_text":"Hal Daum\\'e III, Jordan Boyd-Graber, Khanh Nguyen","cross_cats":["cs.AI","cs.HC","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-24T04:35:19Z","title":"Reinforcement Learning for Bandit Neural Machine Translation with Simulated Human Feedback"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1707.07402","kind":"arxiv","version":4},"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":"sha256:04c6156b2ec4d567bb0595a595fb0d1ef12005791429c8dbb3c85594e25e2141","target":"record","created_at":"2026-05-18T00:30:50Z","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":"2e92203b732f674216a011e5ff9b3a8741c63960dcff43337da5ce983729ddf4","cross_cats_sorted":["cs.AI","cs.HC","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2017-07-24T04:35:19Z","title_canon_sha256":"4296bbd493218810414903340d497c3d0f5b8d0de765a2a09e938f58f8909b59"},"schema_version":"1.0","source":{"id":"1707.07402","kind":"arxiv","version":4}},"canonical_sha256":"efba1ed9529780cb0d6a23103427adc9ea225ee03252c87272c1e7fe3ef85866","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"efba1ed9529780cb0d6a23103427adc9ea225ee03252c87272c1e7fe3ef85866","first_computed_at":"2026-05-18T00:30:50.580791Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T00:30:50.580791Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"/jHRRaPBJfVbXnZJ5qhsdpBmlN2AIbynMr9cMOIIJTI0ZlKfrJBZiCSJ5Yf+vCP8EjfaCz+qslky2ZkfQOdUDw==","signature_status":"signed_v1","signed_at":"2026-05-18T00:30:50.581290Z","signed_message":"canonical_sha256_bytes"},"source_id":"1707.07402","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:04c6156b2ec4d567bb0595a595fb0d1ef12005791429c8dbb3c85594e25e2141","sha256:0886993d0acc6a5b742aa512de5fe306a9e5cee5c557fecf458278745e7040a7"],"state_sha256":"7be2931c6d45783f8ee886f63df360bc42007e3e4433cbd54d7268b4dcd6262d"}