{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:U62XPS3HRH6XCHZCHP5BO4HPEQ","short_pith_number":"pith:U62XPS3H","schema_version":"1.0","canonical_sha256":"a7b577cb6789fd711f223bfa1770ef241e252ade130a5b0226a712b378782ab8","source":{"kind":"arxiv","id":"2510.22143","version":3},"attestation_state":"computed","paper":{"title":"Benchmarking and Learning Real-World Customer Service Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Shi, Huiyu Yu, Jiapeng Wang, Jundong Shen, Junfeng Yao, Tianhong Gao, Ying Ju","submitted_at":"2025-10-25T03:29:55Z","abstract_excerpt":"Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) remain misaligned with real-world dialogue requirements, overemphasizing verifiable task success while under-measuring subjective service quality and realistic failure modes, leaving a gap between offline gains and deployable dialogue behavior. We close this gap with a benchmark-to-optimization loop: we first introduce OlaBench, an ICS benchmark spanning retrieval-augmented generation, workflow-based systems, and agentic settings, which evaluates service capability, safety, and latency sensitivity; mor"},"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":"2510.22143","kind":"arxiv","version":3},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-10-25T03:29:55Z","cross_cats_sorted":[],"title_canon_sha256":"8d08d37edc8788eaf6dc5c501f0a383d332ef398101e019e663aee43ea9ce84c","abstract_canon_sha256":"64aed0b18f9ab9ce92caf9aab3bead8ad09423cd01a66266f72c16fd48f420d3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-26T02:03:58.555953Z","signature_b64":"Oaf0q0QGsbsdzn8+r35PlTV2/gDGCXoOYexSh2KjUxofgxTns1KJBYypTnQAvPWaFe5QIWyupoQE25u48FzFBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a7b577cb6789fd711f223bfa1770ef241e252ade130a5b0226a712b378782ab8","last_reissued_at":"2026-05-26T02:03:58.555108Z","signature_status":"signed_v1","first_computed_at":"2026-05-26T02:03:58.555108Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Benchmarking and Learning Real-World Customer Service Dialogue","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Bei Shi, Huiyu Yu, Jiapeng Wang, Jundong Shen, Junfeng Yao, Tianhong Gao, Ying Ju","submitted_at":"2025-10-25T03:29:55Z","abstract_excerpt":"Existing benchmarks and training pipelines for industrial intelligent customer service (ICS) remain misaligned with real-world dialogue requirements, overemphasizing verifiable task success while under-measuring subjective service quality and realistic failure modes, leaving a gap between offline gains and deployable dialogue behavior. We close this gap with a benchmark-to-optimization loop: we first introduce OlaBench, an ICS benchmark spanning retrieval-augmented generation, workflow-based systems, and agentic settings, which evaluates service capability, safety, and latency sensitivity; mor"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2510.22143","kind":"arxiv","version":3},"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/2510.22143/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":"2510.22143","created_at":"2026-05-26T02:03:58.555222+00:00"},{"alias_kind":"arxiv_version","alias_value":"2510.22143v3","created_at":"2026-05-26T02:03:58.555222+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2510.22143","created_at":"2026-05-26T02:03:58.555222+00:00"},{"alias_kind":"pith_short_12","alias_value":"U62XPS3HRH6X","created_at":"2026-05-26T02:03:58.555222+00:00"},{"alias_kind":"pith_short_16","alias_value":"U62XPS3HRH6XCHZC","created_at":"2026-05-26T02:03:58.555222+00:00"},{"alias_kind":"pith_short_8","alias_value":"U62XPS3H","created_at":"2026-05-26T02:03:58.555222+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/U62XPS3HRH6XCHZCHP5BO4HPEQ","json":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ.json","graph_json":"https://pith.science/api/pith-number/U62XPS3HRH6XCHZCHP5BO4HPEQ/graph.json","events_json":"https://pith.science/api/pith-number/U62XPS3HRH6XCHZCHP5BO4HPEQ/events.json","paper":"https://pith.science/paper/U62XPS3H"},"agent_actions":{"view_html":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ","download_json":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ.json","view_paper":"https://pith.science/paper/U62XPS3H","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2510.22143&json=true","fetch_graph":"https://pith.science/api/pith-number/U62XPS3HRH6XCHZCHP5BO4HPEQ/graph.json","fetch_events":"https://pith.science/api/pith-number/U62XPS3HRH6XCHZCHP5BO4HPEQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ/action/storage_attestation","attest_author":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ/action/author_attestation","sign_citation":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ/action/citation_signature","submit_replication":"https://pith.science/pith/U62XPS3HRH6XCHZCHP5BO4HPEQ/action/replication_record"}},"created_at":"2026-05-26T02:03:58.555222+00:00","updated_at":"2026-05-26T02:03:58.555222+00:00"}