{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:KNQ4TAF7XJPY7OOIM6X4BLL67W","short_pith_number":"pith:KNQ4TAF7","schema_version":"1.0","canonical_sha256":"5361c980bfba5f8fb9c867afc0ad7efdb02fbfbf477d714fd1f0deb2bc75f33e","source":{"kind":"arxiv","id":"2606.09293","version":1},"attestation_state":"computed","paper":{"title":"One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Enguo Zhou, Jing Xiang, Lang Gao, Mingzhe Li, Qishen Zhang, Tai Li, Xiangliang Zhang, Xiuying Chen","submitted_at":"2026-06-08T10:01:07Z","abstract_excerpt":"Dialogue systems in e-commerce scenarios often need to satisfy multiple objectives: accurately reasoning over user profiles (e.g., eligibility, credit limit) to ensure correct decision-making and user state interpretation, while also generating natural and faithful responses. These goals are complementary but not identical. In this work, we propose MORE, an adaptive Multi-Objective REinforcement learning framework that jointly optimizes reasoning accuracy and linguistic naturalness. Our preliminary experiments show that directly mixing rewards with diverging optimization dynamics can cause osc"},"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":"2606.09293","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2026-06-08T10:01:07Z","cross_cats_sorted":[],"title_canon_sha256":"496ce0aa669b76afad99f8bb0162ac4ee986adfb4c834114ce563d4f63895b6f","abstract_canon_sha256":"890f6a4ca596232f1eecf303a7a3131d257a6e3bfb3b7024442be04e0d16552b"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-09T02:08:12.965123Z","signature_b64":"uEdpDl2rNRQAisiMvu3Hj0GkTKBBp+PW+MCZ/2xWx4IEpheMOYa9Sxmo40UofhLx+LhbbYP05jHBKXmgJFSxDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5361c980bfba5f8fb9c867afc0ad7efdb02fbfbf477d714fd1f0deb2bc75f33e","last_reissued_at":"2026-06-09T02:08:12.964261Z","signature_status":"signed_v1","first_computed_at":"2026-06-09T02:08:12.964261Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"One Model, Multiple Goals: Adaptive Multi-Objective Learning for E-commerce Dialogue Systems","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Enguo Zhou, Jing Xiang, Lang Gao, Mingzhe Li, Qishen Zhang, Tai Li, Xiangliang Zhang, Xiuying Chen","submitted_at":"2026-06-08T10:01:07Z","abstract_excerpt":"Dialogue systems in e-commerce scenarios often need to satisfy multiple objectives: accurately reasoning over user profiles (e.g., eligibility, credit limit) to ensure correct decision-making and user state interpretation, while also generating natural and faithful responses. These goals are complementary but not identical. In this work, we propose MORE, an adaptive Multi-Objective REinforcement learning framework that jointly optimizes reasoning accuracy and linguistic naturalness. Our preliminary experiments show that directly mixing rewards with diverging optimization dynamics can cause osc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.09293","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/2606.09293/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":"2606.09293","created_at":"2026-06-09T02:08:12.964422+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.09293v1","created_at":"2026-06-09T02:08:12.964422+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.09293","created_at":"2026-06-09T02:08:12.964422+00:00"},{"alias_kind":"pith_short_12","alias_value":"KNQ4TAF7XJPY","created_at":"2026-06-09T02:08:12.964422+00:00"},{"alias_kind":"pith_short_16","alias_value":"KNQ4TAF7XJPY7OOI","created_at":"2026-06-09T02:08:12.964422+00:00"},{"alias_kind":"pith_short_8","alias_value":"KNQ4TAF7","created_at":"2026-06-09T02:08:12.964422+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/KNQ4TAF7XJPY7OOIM6X4BLL67W","json":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W.json","graph_json":"https://pith.science/api/pith-number/KNQ4TAF7XJPY7OOIM6X4BLL67W/graph.json","events_json":"https://pith.science/api/pith-number/KNQ4TAF7XJPY7OOIM6X4BLL67W/events.json","paper":"https://pith.science/paper/KNQ4TAF7"},"agent_actions":{"view_html":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W","download_json":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W.json","view_paper":"https://pith.science/paper/KNQ4TAF7","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.09293&json=true","fetch_graph":"https://pith.science/api/pith-number/KNQ4TAF7XJPY7OOIM6X4BLL67W/graph.json","fetch_events":"https://pith.science/api/pith-number/KNQ4TAF7XJPY7OOIM6X4BLL67W/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W/action/timestamp_anchor","attest_storage":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W/action/storage_attestation","attest_author":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W/action/author_attestation","sign_citation":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W/action/citation_signature","submit_replication":"https://pith.science/pith/KNQ4TAF7XJPY7OOIM6X4BLL67W/action/replication_record"}},"created_at":"2026-06-09T02:08:12.964422+00:00","updated_at":"2026-06-09T02:08:12.964422+00:00"}