{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JQW42A46BBB4OLHO4TDY3MNVG5","short_pith_number":"pith:JQW42A46","schema_version":"1.0","canonical_sha256":"4c2dcd039e0843c72ceee4c78db1b53745eff2325378daa8974b728e9e383eb6","source":{"kind":"arxiv","id":"2206.00059","version":1},"attestation_state":"computed","paper":{"title":"A Mixture-of-Expert Approach to RL-based Dialogue Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aza Tulepbergenov, Craig Boutilier, Mohammad Ghavamzadeh, Moonkyung Ryu, Ofir Nachum, Yinlam Chow","submitted_at":"2022-05-31T19:00:41Z","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"},"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":"2206.00059","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2022-05-31T19:00:41Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"efb5526091ce9812392198c4790945fdb1421f8b4134ed86cd035b86f06f61be","abstract_canon_sha256":"3c86480afa0d524e4fbef952fc0d15ea2c415fe29b62fcbadb1e0248cec0a77c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:28:12.701384Z","signature_b64":"njELPY8mRmg7kpK2b43MqUjW/5ZFi0YsY4pNtyWsCllw3UDi3QPxxaGD+2BfvPwWq1p3J3mIV3yhgJ6AS3a5Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4c2dcd039e0843c72ceee4c78db1b53745eff2325378daa8974b728e9e383eb6","last_reissued_at":"2026-07-05T04:28:12.700963Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:28:12.700963Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"A Mixture-of-Expert Approach to RL-based Dialogue Management","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Aza Tulepbergenov, Craig Boutilier, Mohammad Ghavamzadeh, Moonkyung Ryu, Ofir Nachum, Yinlam Chow","submitted_at":"2022-05-31T19:00:41Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2206.00059","kind":"arxiv","version":1},"verdict":{"id":null,"model_set":{},"created_at":null,"strongest_claim":"","one_line_summary":"","pipeline_version":null,"weakest_assumption":"","pith_extraction_headline":""},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2206.00059/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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":"2206.00059","created_at":"2026-07-05T04:28:12.701023+00:00"},{"alias_kind":"arxiv_version","alias_value":"2206.00059v1","created_at":"2026-07-05T04:28:12.701023+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2206.00059","created_at":"2026-07-05T04:28:12.701023+00:00"},{"alias_kind":"pith_short_12","alias_value":"JQW42A46BBB4","created_at":"2026-07-05T04:28:12.701023+00:00"},{"alias_kind":"pith_short_16","alias_value":"JQW42A46BBB4OLHO","created_at":"2026-07-05T04:28:12.701023+00:00"},{"alias_kind":"pith_short_8","alias_value":"JQW42A46","created_at":"2026-07-05T04:28:12.701023+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5","json":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5.json","graph_json":"https://pith.science/api/pith-number/JQW42A46BBB4OLHO4TDY3MNVG5/graph.json","events_json":"https://pith.science/api/pith-number/JQW42A46BBB4OLHO4TDY3MNVG5/events.json","paper":"https://pith.science/paper/JQW42A46"},"agent_actions":{"view_html":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5","download_json":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5.json","view_paper":"https://pith.science/paper/JQW42A46","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2206.00059&json=true","fetch_graph":"https://pith.science/api/pith-number/JQW42A46BBB4OLHO4TDY3MNVG5/graph.json","fetch_events":"https://pith.science/api/pith-number/JQW42A46BBB4OLHO4TDY3MNVG5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5/action/storage_attestation","attest_author":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5/action/author_attestation","sign_citation":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5/action/citation_signature","submit_replication":"https://pith.science/pith/JQW42A46BBB4OLHO4TDY3MNVG5/action/replication_record"}},"created_at":"2026-07-05T04:28:12.701023+00:00","updated_at":"2026-07-05T04:28:12.701023+00:00"}