{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:JQW42A46BBB4OLHO4TDY3MNVG5","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":"3c86480afa0d524e4fbef952fc0d15ea2c415fe29b62fcbadb1e0248cec0a77c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-31T19:00:41Z","title_canon_sha256":"efb5526091ce9812392198c4790945fdb1421f8b4134ed86cd035b86f06f61be"},"schema_version":"1.0","source":{"id":"2206.00059","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2206.00059","created_at":"2026-07-05T04:28:12Z"},{"alias_kind":"arxiv_version","alias_value":"2206.00059v1","created_at":"2026-07-05T04:28:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00059","created_at":"2026-07-05T04:28:12Z"},{"alias_kind":"pith_short_12","alias_value":"JQW42A46BBB4","created_at":"2026-07-05T04:28:12Z"},{"alias_kind":"pith_short_16","alias_value":"JQW42A46BBB4OLHO","created_at":"2026-07-05T04:28:12Z"},{"alias_kind":"pith_short_8","alias_value":"JQW42A46","created_at":"2026-07-05T04:28:12Z"}],"graph_snapshots":[{"event_id":"sha256:bdb8eeda01b20e03233c75cdbb4f2f66bafdcf6f3abcaa8794a5df4d78591fe2","target":"graph","created_at":"2026-07-05T04:28:12Z","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"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2206.00059/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Despite recent advancements in language models (LMs), their application to dialogue management (DM) problems and ability to carry on rich conversations remain a challenge. We use reinforcement learning (RL) to develop a dialogue agent that avoids being short-sighted (outputting generic utterances) and maximizes overall user satisfaction. Most existing RL approaches to DM train the agent at the word-level, and thus, have to deal with a combinatorially complex action space even for a medium-size vocabulary. As a result, they struggle to produce a successful and engaging dialogue even if they are","authors_text":"Aza Tulepbergenov, Craig Boutilier, Mohammad Ghavamzadeh, Moonkyung Ryu, Ofir Nachum, Yinlam Chow","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-31T19:00:41Z","title":"A Mixture-of-Expert Approach to RL-based Dialogue Management"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00059","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:e4bff10c883f6cc35645f361aeb91045b96a9f86fb17b3ed5bd8e10de23f141b","target":"record","created_at":"2026-07-05T04:28:12Z","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":"3c86480afa0d524e4fbef952fc0d15ea2c415fe29b62fcbadb1e0248cec0a77c","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-31T19:00:41Z","title_canon_sha256":"efb5526091ce9812392198c4790945fdb1421f8b4134ed86cd035b86f06f61be"},"schema_version":"1.0","source":{"id":"2206.00059","kind":"arxiv","version":1}},"canonical_sha256":"4c2dcd039e0843c72ceee4c78db1b53745eff2325378daa8974b728e9e383eb6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"4c2dcd039e0843c72ceee4c78db1b53745eff2325378daa8974b728e9e383eb6","first_computed_at":"2026-07-05T04:28:12.700963Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:28:12.700963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"njELPY8mRmg7kpK2b43MqUjW/5ZFi0YsY4pNtyWsCllw3UDi3QPxxaGD+2BfvPwWq1p3J3mIV3yhgJ6AS3a5Ag==","signature_status":"signed_v1","signed_at":"2026-07-05T04:28:12.701384Z","signed_message":"canonical_sha256_bytes"},"source_id":"2206.00059","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e4bff10c883f6cc35645f361aeb91045b96a9f86fb17b3ed5bd8e10de23f141b","sha256:bdb8eeda01b20e03233c75cdbb4f2f66bafdcf6f3abcaa8794a5df4d78591fe2"],"state_sha256":"d6e19c69e31c1b014f55f16626cf9975f18d79de3b1ccd202176d6805deee241"}