{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:IIIYDZ5XU3QW2GI3CKU7IGHNP3","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":"38a583009a5db3974cf5b42d79c918d0136da1a6135f25addae1e7d9ec3618b7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-11T20:55:28Z","title_canon_sha256":"9a434045ea3a7cf31c42c73d38c253156d897a7d9f4f59bd290d03deb6b9854a"},"schema_version":"1.0","source":{"id":"2006.06814","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2006.06814","created_at":"2026-07-05T02:16:37Z"},{"alias_kind":"arxiv_version","alias_value":"2006.06814v4","created_at":"2026-07-05T02:16:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2006.06814","created_at":"2026-07-05T02:16:37Z"},{"alias_kind":"pith_short_12","alias_value":"IIIYDZ5XU3QW","created_at":"2026-07-05T02:16:37Z"},{"alias_kind":"pith_short_16","alias_value":"IIIYDZ5XU3QW2GI3","created_at":"2026-07-05T02:16:37Z"},{"alias_kind":"pith_short_8","alias_value":"IIIYDZ5X","created_at":"2026-07-05T02:16:37Z"}],"graph_snapshots":[{"event_id":"sha256:1190959ee121ae45fde01579f9486b59c02ed82b4942b6932c857af2653b012c","target":"graph","created_at":"2026-07-05T02:16:37Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2006.06814/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Designing task-oriented dialogue systems is a challenging research topic, since it needs not only to generate utterances fulfilling user requests but also to guarantee the comprehensibility. Many previous works trained end-to-end (E2E) models with supervised learning (SL), however, the bias in annotated system utterances remains as a bottleneck. Reinforcement learning (RL) deals with the problem through using non-differentiable evaluation metrics (e.g., the success rate) as rewards. Nonetheless, existing works with RL showed that the comprehensibility of generated system utterances could be co","authors_text":"Jianhong Wang, Tae-Kyun Kim, Yuan Zhang, Yunjie Gu","cross_cats":["cs.AI","cs.LG"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-11T20:55:28Z","title":"Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2006.06814","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:e93dee730144d77f77d811d846fb64f4dd4439b4302769669e540cf88a2a45cf","target":"record","created_at":"2026-07-05T02:16:37Z","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":"38a583009a5db3974cf5b42d79c918d0136da1a6135f25addae1e7d9ec3618b7","cross_cats_sorted":["cs.AI","cs.LG"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-06-11T20:55:28Z","title_canon_sha256":"9a434045ea3a7cf31c42c73d38c253156d897a7d9f4f59bd290d03deb6b9854a"},"schema_version":"1.0","source":{"id":"2006.06814","kind":"arxiv","version":4}},"canonical_sha256":"421181e7b7a6e16d191b12a9f418ed7edfc1501dd57ab3e1c8055e24021b5c67","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"421181e7b7a6e16d191b12a9f418ed7edfc1501dd57ab3e1c8055e24021b5c67","first_computed_at":"2026-07-05T02:16:37.324946Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:16:37.324946Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"P/ACxFFgVIzzk/EkvzVm6gS9E0UgHOoGU7FbGg1ny2u3jsjkUhEiQ70G5iZnATIHvAQS08PcQj8w3C8Pwp1YBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T02:16:37.325382Z","signed_message":"canonical_sha256_bytes"},"source_id":"2006.06814","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e93dee730144d77f77d811d846fb64f4dd4439b4302769669e540cf88a2a45cf","sha256:1190959ee121ae45fde01579f9486b59c02ed82b4942b6932c857af2653b012c"],"state_sha256":"893ec04d28918b67c5cedc5023c9a3ca80bd83528f504b25ea523472c69bb48f"}