{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2016:L3QHCFZEZBC5372J72XNAGEVAG","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":"2e13ff5ad02fa2799130774f1045632c45d218e08939b5d12e92a95f18475236","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-08T19:03:06Z","title_canon_sha256":"e8c02e34448a833597a5cfd90ce612025883f67c86b46391e188d3c044dabc95"},"schema_version":"1.0","source":{"id":"1606.02689","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"1606.02689","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"arxiv_version","alias_value":"1606.02689v1","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.1606.02689","created_at":"2026-05-18T01:12:40Z"},{"alias_kind":"pith_short_12","alias_value":"L3QHCFZEZBC5","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_16","alias_value":"L3QHCFZEZBC5372J","created_at":"2026-05-18T12:30:29Z"},{"alias_kind":"pith_short_8","alias_value":"L3QHCFZE","created_at":"2026-05-18T12:30:29Z"}],"graph_snapshots":[{"event_id":"sha256:6ec6938710756b791808cd78f1ea9296bc2cbc77767e41416f5a15bfcc11727b","target":"graph","created_at":"2026-05-18T01:12:40Z","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":"We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then continuously improve its behaviour via reinforcement learning, all using gradient-based algorithms on one single model. The experiments demonstrate the supervised model's effectiveness in the corpus-based evaluation, with user simulation, and with paid human subjects. The use of reinforcement learning further improves the model's performance in both interactive set","authors_text":"David Vandyke, Lina Rojas-Barahona, Milica Gasic, Nikola Mrksic, Pei-Hao Su, Stefan Ultes, Steve Young, Tsung-Hsien Wen","cross_cats":["cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-08T19:03:06Z","title":"Continuously Learning Neural Dialogue Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"1606.02689","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":"sha256:6e356fa07b93f900b3e21c4586c2a52e1ae64d17f8f4ff306be00e33da63aaa6","target":"record","created_at":"2026-05-18T01:12:40Z","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":"2e13ff5ad02fa2799130774f1045632c45d218e08939b5d12e92a95f18475236","cross_cats_sorted":["cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2016-06-08T19:03:06Z","title_canon_sha256":"e8c02e34448a833597a5cfd90ce612025883f67c86b46391e188d3c044dabc95"},"schema_version":"1.0","source":{"id":"1606.02689","kind":"arxiv","version":1}},"canonical_sha256":"5ee0711724c845ddff49feaed0189501821ca796aa097908052510d93c1acf45","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5ee0711724c845ddff49feaed0189501821ca796aa097908052510d93c1acf45","first_computed_at":"2026-05-18T01:12:40.852879Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-18T01:12:40.852879Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"9PPOE9JlHsRxJ1zIBb2R7/rCC1ZGnHWhp5OvYY0ChSdfid1mt2mmt6ieAZPjWg/aoAubLDgbnvo3hYlz9/jfCg==","signature_status":"signed_v1","signed_at":"2026-05-18T01:12:40.853237Z","signed_message":"canonical_sha256_bytes"},"source_id":"1606.02689","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6e356fa07b93f900b3e21c4586c2a52e1ae64d17f8f4ff306be00e33da63aaa6","sha256:6ec6938710756b791808cd78f1ea9296bc2cbc77767e41416f5a15bfcc11727b"],"state_sha256":"84650d639b0101430a2108bbbbfd4257ed974393fc78c8f27c2e3c0b83ba0f9e"}