{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2023:ZZPW6DPNTKNVO2TNGDILYF4ZN3","short_pith_number":"pith:ZZPW6DPN","schema_version":"1.0","canonical_sha256":"ce5f6f0ded9a9b576a6d30d0bc17996edebdb376edc733b76667917c06418587","source":{"kind":"arxiv","id":"2302.10342","version":1},"attestation_state":"computed","paper":{"title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Huan Wang, Jianguo Zhang, Mingyuan Zhou, Shentao Yang, Shujian Zhang, Yihao Feng","submitted_at":"2023-02-20T22:10:04Z","abstract_excerpt":"When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied. This paper aims at answering the question of how to efficiently learn and leverage a reward function for training end-to-end (E2E) ToD agents. Specifically, we introduce two generalized objectives for reward-function learning, inspired by the classical learning-to-rank literat"},"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":"2302.10342","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2023-02-20T22:10:04Z","cross_cats_sorted":[],"title_canon_sha256":"d0f058e45b98d37e4df80af8567195a5235988509eef2ee0ed191fafb9604aa2","abstract_canon_sha256":"0755bee85a900e8c4ac141d7aa4b4df9cafd8323223ecf8bd7f76020d57b9528"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:43:38.038192Z","signature_b64":"2xgReGK+inCCNnsDByUguCqQwmQorrnkLHyoAVOwHBOsE/JaXNJWyvrlqyjOAmoFNX8/QfZJGKDX/tjZzJ3QAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ce5f6f0ded9a9b576a6d30d0bc17996edebdb376edc733b76667917c06418587","last_reissued_at":"2026-07-05T05:43:38.037860Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:43:38.037860Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Fantastic Rewards and How to Tame Them: A Case Study on Reward Learning for Task-oriented Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Caiming Xiong, Huan Wang, Jianguo Zhang, Mingyuan Zhou, Shentao Yang, Shujian Zhang, Yihao Feng","submitted_at":"2023-02-20T22:10:04Z","abstract_excerpt":"When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Prior works mainly focus on adopting advanced RL techniques to train the ToD agents, while the design of the reward function is not well studied. This paper aims at answering the question of how to efficiently learn and leverage a reward function for training end-to-end (E2E) ToD agents. Specifically, we introduce two generalized objectives for reward-function learning, inspired by the classical learning-to-rank literat"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2302.10342","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/2302.10342/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":"2302.10342","created_at":"2026-07-05T05:43:38.037913+00:00"},{"alias_kind":"arxiv_version","alias_value":"2302.10342v1","created_at":"2026-07-05T05:43:38.037913+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2302.10342","created_at":"2026-07-05T05:43:38.037913+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZZPW6DPNTKNV","created_at":"2026-07-05T05:43:38.037913+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZZPW6DPNTKNVO2TN","created_at":"2026-07-05T05:43:38.037913+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZZPW6DPN","created_at":"2026-07-05T05:43:38.037913+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/ZZPW6DPNTKNVO2TNGDILYF4ZN3","json":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3.json","graph_json":"https://pith.science/api/pith-number/ZZPW6DPNTKNVO2TNGDILYF4ZN3/graph.json","events_json":"https://pith.science/api/pith-number/ZZPW6DPNTKNVO2TNGDILYF4ZN3/events.json","paper":"https://pith.science/paper/ZZPW6DPN"},"agent_actions":{"view_html":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3","download_json":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3.json","view_paper":"https://pith.science/paper/ZZPW6DPN","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2302.10342&json=true","fetch_graph":"https://pith.science/api/pith-number/ZZPW6DPNTKNVO2TNGDILYF4ZN3/graph.json","fetch_events":"https://pith.science/api/pith-number/ZZPW6DPNTKNVO2TNGDILYF4ZN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3/action/storage_attestation","attest_author":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3/action/author_attestation","sign_citation":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3/action/citation_signature","submit_replication":"https://pith.science/pith/ZZPW6DPNTKNVO2TNGDILYF4ZN3/action/replication_record"}},"created_at":"2026-07-05T05:43:38.037913+00:00","updated_at":"2026-07-05T05:43:38.037913+00:00"}