{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:6YU5TPID4SJJX7WI4DMS5BUDNO","merge_version":"pith-open-graph-merge-v1","event_count":7,"valid_event_count":7,"invalid_event_count":0,"equivocation_count":1,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"8c757af591eebba897df48515cccd951ea6c2d0730e5664b681aa9249bf174e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-20T15:07:58Z","title_canon_sha256":"0ea6138be87e76ad8edf26add7d89852b9538c811f7c87af529fb450223e4d65"},"schema_version":"1.0","source":{"id":"2607.18039","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2607.18039","created_at":"2026-07-21T02:22:12Z"},{"alias_kind":"arxiv_version","alias_value":"2607.18039v1","created_at":"2026-07-21T02:22:12Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.18039","created_at":"2026-07-21T02:22:12Z"},{"alias_kind":"pith_short_12","alias_value":"6YU5TPID4SJJ","created_at":"2026-07-21T02:22:12Z"},{"alias_kind":"pith_short_16","alias_value":"6YU5TPID4SJJX7WI","created_at":"2026-07-21T02:22:12Z"},{"alias_kind":"pith_short_8","alias_value":"6YU5TPID","created_at":"2026-07-21T02:22:12Z"}],"graph_snapshots":[{"event_id":"sha256:cafa99791c2c62fff2d00625cf5b0fe93fbb6386c09e2b605abab1bab37ec488","target":"graph","created_at":"2026-07-21T02:22:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2607.18039/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Production customer-service bots must improve answer quality across iterative releases, yet large language models must not bypass evidence boundaries, policy rules, or human-handoff safeguards. We present an \\textbf{Evidence-Grounded Customer-Service Agent Workflow} deployed in a real-world customer-service setting. BM25 recall, issue-title-vector recall, issue-description-vector recall, weighted RRF fusion, and cross-encoder reranking construct grounded FAQ evidence for controlled LLM decisions. Policy-guided orchestration then combines this RAG evidence with scenario-specific rule evidence, ","authors_text":"Charles Quan, Chunming Wu, Congde Yuan, Dafei Qiu, Gavin Xie, Hope Chen, Jun Wu, Max Yao, Mo Wu, Suipeng Li","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-20T15:07:58Z","title":"Evidence-in-the-Loop: Trace-Driven Optimization for Customer-Service LLM Agents"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.18039","kind":"arxiv","version":1},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:4cff155ef17421c3fe649ed53073f67fe2ad0153b985e7f92a53e47a2df5c8a5","target":"record","created_at":"2026-07-21T02:22:12Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"8c757af591eebba897df48515cccd951ea6c2d0730e5664b681aa9249bf174e4","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.IR","submitted_at":"2026-07-20T15:07:58Z","title_canon_sha256":"0ea6138be87e76ad8edf26add7d89852b9538c811f7c87af529fb450223e4d65"},"schema_version":"1.0","source":{"id":"2607.18039","kind":"arxiv","version":1}},"canonical_sha256":"f629d9bd03e4929bfec8e0d92e86836b95ad5ac8c5f9f02404a1f80f12e07ba6","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"f629d9bd03e4929bfec8e0d92e86836b95ad5ac8c5f9f02404a1f80f12e07ba6","first_computed_at":"2026-07-21T02:22:12.943660Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-21T02:22:12.943660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"8pjj1sZTPxSisPnYuZKO0nU14iySB52YW9wldxtQAf8xTXvulDb/T7B1M4lCkaN32T/c4uCfHNXJbUixe7ViAg==","signature_status":"signed_v1","signed_at":"2026-07-21T02:22:12.944567Z","signed_message":"canonical_sha256_bytes"},"source_id":"2607.18039","source_kind":"arxiv","source_version":1}}},"equivocations":[{"signer_id":"pith.science","event_type":"integrity_finding","target":"integrity","event_ids":["sha256:108520b3ab5e38381714163d934decf6a5d713d2f060dba850eb0629e38099d6","sha256:23ff4b05624624cc92ce8066753b3b952005722ae485ef2c14cf7dcc16a512fa","sha256:39f45ccdf29dfa149a702f19712da5f064adedb6da17d9132bb8aa59247a2e08","sha256:691a2df27295e3b6c4b272eb14aa272d50c959e42336534f489d679edc302fdf","sha256:72c3cb80491fb384af14bc8f559a9c34f1a2b83987dcd7094abb8b86c13087c6"]}],"invalid_events":[],"applied_event_ids":["sha256:4cff155ef17421c3fe649ed53073f67fe2ad0153b985e7f92a53e47a2df5c8a5","sha256:cafa99791c2c62fff2d00625cf5b0fe93fbb6386c09e2b605abab1bab37ec488"],"state_sha256":"38e268db08643081a40bc670b963f8e72adf9fd0c3e1354fffeef1450ad3ec71"}