{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:FLJWG4BYFGJZBNAQ5WJBHQR3OH","short_pith_number":"pith:FLJWG4BY","schema_version":"1.0","canonical_sha256":"2ad3637038299390b410ed9213c23b71eb4be66e1d4612aeda783d5c8aba9eab","source":{"kind":"arxiv","id":"2503.20791","version":1},"attestation_state":"computed","paper":{"title":"ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Murzaku, Md Mehrab Tanjim, Vaishnavi Muppala, Xiang Chen, Yunyao Li, Zifan Liu","submitted_at":"2025-03-19T23:13:34Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable progress in understanding and generating natural language across various applications. However, they often struggle with resolving ambiguities in real-world, enterprise-level interactions, where context and domain-specific knowledge play a crucial role. In this demonstration, we introduce ECLAIR (Enhanced CLArification for Interactive Responses), a multi-agent framework for interactive disambiguation. ECLAIR enhances ambiguous user query clarification through an interactive process where custom agents are defined, ambiguity reasoning is conduc"},"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":"2503.20791","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2025-03-19T23:13:34Z","cross_cats_sorted":[],"title_canon_sha256":"944c0ac8db1d2caae07464f617345ad789c4722ff2bcec5584675814932c7443","abstract_canon_sha256":"2c61cc2e8848954236a416bcd5fdc7ceb40eef2807e5853c504708a0a9c1d92a"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:39:48.167437Z","signature_b64":"NfFDqBzlBos+XI/AZB9ROwgGhNFCrHIJl+lFUuD6UzBLPEK0jdMaj+ntLELJcsv6tf9l+matSllWtQTAOhh8CQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2ad3637038299390b410ed9213c23b71eb4be66e1d4612aeda783d5c8aba9eab","last_reissued_at":"2026-07-05T10:39:48.166936Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:39:48.166936Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ECLAIR: Enhanced Clarification for Interactive Responses in an Enterprise AI Assistant","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"John Murzaku, Md Mehrab Tanjim, Vaishnavi Muppala, Xiang Chen, Yunyao Li, Zifan Liu","submitted_at":"2025-03-19T23:13:34Z","abstract_excerpt":"Large language models (LLMs) have shown remarkable progress in understanding and generating natural language across various applications. However, they often struggle with resolving ambiguities in real-world, enterprise-level interactions, where context and domain-specific knowledge play a crucial role. In this demonstration, we introduce ECLAIR (Enhanced CLArification for Interactive Responses), a multi-agent framework for interactive disambiguation. ECLAIR enhances ambiguous user query clarification through an interactive process where custom agents are defined, ambiguity reasoning is conduc"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2503.20791","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/2503.20791/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":"2503.20791","created_at":"2026-07-05T10:39:48.166997+00:00"},{"alias_kind":"arxiv_version","alias_value":"2503.20791v1","created_at":"2026-07-05T10:39:48.166997+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2503.20791","created_at":"2026-07-05T10:39:48.166997+00:00"},{"alias_kind":"pith_short_12","alias_value":"FLJWG4BYFGJZ","created_at":"2026-07-05T10:39:48.166997+00:00"},{"alias_kind":"pith_short_16","alias_value":"FLJWG4BYFGJZBNAQ","created_at":"2026-07-05T10:39:48.166997+00:00"},{"alias_kind":"pith_short_8","alias_value":"FLJWG4BY","created_at":"2026-07-05T10:39:48.166997+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.21296","citing_title":"Discriminatory Compliance: How LLMs Answer Queries from Protected Groups","ref_index":76,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH","json":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH.json","graph_json":"https://pith.science/api/pith-number/FLJWG4BYFGJZBNAQ5WJBHQR3OH/graph.json","events_json":"https://pith.science/api/pith-number/FLJWG4BYFGJZBNAQ5WJBHQR3OH/events.json","paper":"https://pith.science/paper/FLJWG4BY"},"agent_actions":{"view_html":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH","download_json":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH.json","view_paper":"https://pith.science/paper/FLJWG4BY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2503.20791&json=true","fetch_graph":"https://pith.science/api/pith-number/FLJWG4BYFGJZBNAQ5WJBHQR3OH/graph.json","fetch_events":"https://pith.science/api/pith-number/FLJWG4BYFGJZBNAQ5WJBHQR3OH/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH/action/timestamp_anchor","attest_storage":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH/action/storage_attestation","attest_author":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH/action/author_attestation","sign_citation":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH/action/citation_signature","submit_replication":"https://pith.science/pith/FLJWG4BYFGJZBNAQ5WJBHQR3OH/action/replication_record"}},"created_at":"2026-07-05T10:39:48.166997+00:00","updated_at":"2026-07-05T10:39:48.166997+00:00"}