{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:H5ORLE5UVZJCVYF7ZDXJTTXM5N","short_pith_number":"pith:H5ORLE5U","schema_version":"1.0","canonical_sha256":"3f5d1593b4ae522ae0bfc8ee99ceeceb590a897bc7d2bff5fb5254f7e11d7900","source":{"kind":"arxiv","id":"2505.18731","version":1},"attestation_state":"computed","paper":{"title":"Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuheng Zhang, Wanchun Dou, Wei Shen, Xiaolong Xu, Xiaonan He, Xuyun Zhang","submitted_at":"2025-05-24T15:01:30Z","abstract_excerpt":"Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, this framework triggers clarification questions when detecting potential user dissatisfaction during interactions in the industrial dialogue system. Traditional works typically rely on training a neural network model based on weak labels which are generated by a simple model trained on user actions after current turn. However, existing methods suffer from two critical limitations in real-world scenarios: (1) Noisy Rewar"},"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":"2505.18731","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-05-24T15:01:30Z","cross_cats_sorted":[],"title_canon_sha256":"642eea21fbef8a334f82f477b9a881421dbe29ecfd465971e093b0b8c23c5533","abstract_canon_sha256":"623a5860d26946dda5a231e71e16b171e31731037c1f5866badb3d3951a7012c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:09:18.724933Z","signature_b64":"/VmgQwHq7GD8/gTcfsqTFhY1F/o+XodLaUNIvZCcEOauOOIHgY+s6gJK42KXF9XtMwyOTAxmS1JCiwQw1oUpCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"3f5d1593b4ae522ae0bfc8ee99ceeceb590a897bc7d2bff5fb5254f7e11d7900","last_reissued_at":"2026-07-05T11:09:18.724523Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:09:18.724523Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Reward-Driven Interaction: Enhancing Proactive Dialogue Agents through User Satisfaction Prediction","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Chuheng Zhang, Wanchun Dou, Wei Shen, Xiaolong Xu, Xiaonan He, Xuyun Zhang","submitted_at":"2025-05-24T15:01:30Z","abstract_excerpt":"Reward-driven proactive dialogue agents require precise estimation of user satisfaction as an intrinsic reward signal to determine optimal interaction strategies. Specifically, this framework triggers clarification questions when detecting potential user dissatisfaction during interactions in the industrial dialogue system. Traditional works typically rely on training a neural network model based on weak labels which are generated by a simple model trained on user actions after current turn. However, existing methods suffer from two critical limitations in real-world scenarios: (1) Noisy Rewar"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.18731","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/2505.18731/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":"2505.18731","created_at":"2026-07-05T11:09:18.724580+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.18731v1","created_at":"2026-07-05T11:09:18.724580+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.18731","created_at":"2026-07-05T11:09:18.724580+00:00"},{"alias_kind":"pith_short_12","alias_value":"H5ORLE5UVZJC","created_at":"2026-07-05T11:09:18.724580+00:00"},{"alias_kind":"pith_short_16","alias_value":"H5ORLE5UVZJCVYF7","created_at":"2026-07-05T11:09:18.724580+00:00"},{"alias_kind":"pith_short_8","alias_value":"H5ORLE5U","created_at":"2026-07-05T11:09:18.724580+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/H5ORLE5UVZJCVYF7ZDXJTTXM5N","json":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N.json","graph_json":"https://pith.science/api/pith-number/H5ORLE5UVZJCVYF7ZDXJTTXM5N/graph.json","events_json":"https://pith.science/api/pith-number/H5ORLE5UVZJCVYF7ZDXJTTXM5N/events.json","paper":"https://pith.science/paper/H5ORLE5U"},"agent_actions":{"view_html":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N","download_json":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N.json","view_paper":"https://pith.science/paper/H5ORLE5U","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.18731&json=true","fetch_graph":"https://pith.science/api/pith-number/H5ORLE5UVZJCVYF7ZDXJTTXM5N/graph.json","fetch_events":"https://pith.science/api/pith-number/H5ORLE5UVZJCVYF7ZDXJTTXM5N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N/action/storage_attestation","attest_author":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N/action/author_attestation","sign_citation":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N/action/citation_signature","submit_replication":"https://pith.science/pith/H5ORLE5UVZJCVYF7ZDXJTTXM5N/action/replication_record"}},"created_at":"2026-07-05T11:09:18.724580+00:00","updated_at":"2026-07-05T11:09:18.724580+00:00"}