{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LAY5REU3FF7RAKVAXNCK3B6JEF","short_pith_number":"pith:LAY5REU3","schema_version":"1.0","canonical_sha256":"5831d8929b297f102aa0bb44ad87c9214419dd17fc880625faae6a63efecba1d","source":{"kind":"arxiv","id":"2604.13353","version":2},"attestation_state":"computed","paper":{"title":"Cross-Domain Query Translation for Network Troubleshooting: A Multi-Agent LLM Framework with Privacy Preservation and Self-Reflection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multi-agent LLM system classifies network queries, anonymizes PII, and translates expert advice for users.","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Brigitte Jaumard, Karthikeyan Premkumar, Nguyen Phuc Tran, Salman Memon","submitted_at":"2026-04-14T23:23:46Z","abstract_excerpt":"This paper presents a hierarchical multi-agent LLM architecture to bridge communication gaps between non-technical end users and telecommunications domain experts in private network environments. We propose a cross-domain query translation framework that leverages specialized language models coordinated through multi-agent reflection-based reasoning. The resulting system addresses three critical challenges: (1) accurately classify user queries related to telecommunications network issues using a dual-stage hierarchical approach, (2) preserve user privacy through the anonymization of semantical"},"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":"2604.13353","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.NI","submitted_at":"2026-04-14T23:23:46Z","cross_cats_sorted":[],"title_canon_sha256":"3efb0ec70e100e30f7b6736375e8344e2c4c593551bdd67e5ce39474abe4d8a9","abstract_canon_sha256":"b1b791c5ac0601925f9bb432b4a30cfcbaf91621a925ce4f3e33d0bda574feae"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:04:31.600595Z","signature_b64":"kj3nuzFzj1CcGqs2E2UlvlS5ul93c1SFSsbWEQ+M3DL8BtoQ8kliDHKC12ghV8RwJzOamuBFg9aun928F2tCDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5831d8929b297f102aa0bb44ad87c9214419dd17fc880625faae6a63efecba1d","last_reissued_at":"2026-05-20T00:04:31.599758Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:04:31.599758Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Cross-Domain Query Translation for Network Troubleshooting: A Multi-Agent LLM Framework with Privacy Preservation and Self-Reflection","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"Multi-agent LLM system classifies network queries, anonymizes PII, and translates expert advice for users.","cross_cats":[],"primary_cat":"cs.NI","authors_text":"Brigitte Jaumard, Karthikeyan Premkumar, Nguyen Phuc Tran, Salman Memon","submitted_at":"2026-04-14T23:23:46Z","abstract_excerpt":"This paper presents a hierarchical multi-agent LLM architecture to bridge communication gaps between non-technical end users and telecommunications domain experts in private network environments. We propose a cross-domain query translation framework that leverages specialized language models coordinated through multi-agent reflection-based reasoning. The resulting system addresses three critical challenges: (1) accurately classify user queries related to telecommunications network issues using a dual-stage hierarchical approach, (2) preserve user privacy through the anonymization of semantical"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"The resulting system addresses three critical challenges: (1) accurately classify user queries related to telecommunications network issues using a dual-stage hierarchical approach, (2) preserve user privacy through the anonymization of semantically relevant personally identifiable information (PII) while maintaining diagnostic utility, and (3) translate technical expert responses into user-comprehensible language.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That the proposed semantic-preserving anonymization techniques can simultaneously respect k-anonymity and differential privacy principles while retaining enough diagnostic utility for accurate expert responses, and that the multi-agent self-reflection loop will reliably improve outputs without introducing new errors.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"A hierarchical multi-agent LLM framework with self-reflection and semantic-preserving anonymization translates cross-domain queries for network troubleshooting and was evaluated on 10,000 unseen scenarios.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"Multi-agent LLM system classifies network queries, anonymizes PII, and translates expert advice for users.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"bdb07f74fda103249710d23f82244fde3a78c23918cd50d4a5d5dcb7351b413e"},"source":{"id":"2604.13353","kind":"arxiv","version":2},"verdict":{"id":"c52b7c4b-b330-40c6-91d2-008d4c18d060","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-10T13:41:22.608740Z","strongest_claim":"The resulting system addresses three critical challenges: (1) accurately classify user queries related to telecommunications network issues using a dual-stage hierarchical approach, (2) preserve user privacy through the anonymization of semantically relevant personally identifiable information (PII) while maintaining diagnostic utility, and (3) translate technical expert responses into user-comprehensible language.","one_line_summary":"A hierarchical multi-agent LLM framework with self-reflection and semantic-preserving anonymization translates cross-domain queries for network troubleshooting and was evaluated on 10,000 unseen scenarios.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That the proposed semantic-preserving anonymization techniques can simultaneously respect k-anonymity and differential privacy principles while retaining enough diagnostic utility for accurate expert responses, and that the multi-agent self-reflection loop will reliably improve outputs without introducing new errors.","pith_extraction_headline":"Multi-agent LLM system classifies network queries, anonymizes PII, and translates expert advice for users."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2604.13353/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":"2604.13353","created_at":"2026-05-20T00:04:31.599893+00:00"},{"alias_kind":"arxiv_version","alias_value":"2604.13353v2","created_at":"2026-05-20T00:04:31.599893+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2604.13353","created_at":"2026-05-20T00:04:31.599893+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAY5REU3FF7R","created_at":"2026-05-20T00:04:31.599893+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAY5REU3FF7RAKVA","created_at":"2026-05-20T00:04:31.599893+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAY5REU3","created_at":"2026-05-20T00:04:31.599893+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/LAY5REU3FF7RAKVAXNCK3B6JEF","json":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF.json","graph_json":"https://pith.science/api/pith-number/LAY5REU3FF7RAKVAXNCK3B6JEF/graph.json","events_json":"https://pith.science/api/pith-number/LAY5REU3FF7RAKVAXNCK3B6JEF/events.json","paper":"https://pith.science/paper/LAY5REU3"},"agent_actions":{"view_html":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF","download_json":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF.json","view_paper":"https://pith.science/paper/LAY5REU3","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2604.13353&json=true","fetch_graph":"https://pith.science/api/pith-number/LAY5REU3FF7RAKVAXNCK3B6JEF/graph.json","fetch_events":"https://pith.science/api/pith-number/LAY5REU3FF7RAKVAXNCK3B6JEF/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF/action/storage_attestation","attest_author":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF/action/author_attestation","sign_citation":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF/action/citation_signature","submit_replication":"https://pith.science/pith/LAY5REU3FF7RAKVAXNCK3B6JEF/action/replication_record"}},"created_at":"2026-05-20T00:04:31.599893+00:00","updated_at":"2026-05-20T00:04:31.599893+00:00"}