{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:RYLGPTWGOXBGHXPQ757XHFGJDW","short_pith_number":"pith:RYLGPTWG","schema_version":"1.0","canonical_sha256":"8e1667cec675c263ddf0ff7f7394c91da03577ee8781249af4aae8acfef811ee","source":{"kind":"arxiv","id":"2606.28370","version":1},"attestation_state":"computed","paper":{"title":"Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Anindya Moitra, Ankur Vivek Singh, Darshita Rathore, Vaibhav Singal, Vineet Kumar","submitted_at":"2026-06-15T17:02:22Z","abstract_excerpt":"Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different access methods, cost profiles, and correctness semantics. Existing AI-enabled interfaces force users to select the right tool: NL2SQL systems cannot reason over slide decks, and RAG pipelines lack access to live warehouse tables.\n  We present COGNI, a production conversational BI system that treats natural-language analytics as a heterogeneous query processing problem, organized as four architectural layers. First, an indexing layer implements sl"},"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":"2606.28370","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.IR","submitted_at":"2026-06-15T17:02:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"7f7b00dc6012999d3918e8e19fca82a5ee4b718695e092f25bf389ce7d0144c3","abstract_canon_sha256":"fa7c472754e1bd34de0249cd2270d859625453fa12923042189db6d5789f10a3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-30T00:15:12.212966Z","signature_b64":"nXWi5ECAxhS4EklBo3j8ZCY60Q1ljBHq0Ies1F5+G03mvCwdOqBqN0TkGL4eMGnMomSvQySxyoaHm/TK1/VSBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"8e1667cec675c263ddf0ff7f7394c91da03577ee8781249af4aae8acfef811ee","last_reissued_at":"2026-06-30T00:15:12.212484Z","signature_status":"signed_v1","first_computed_at":"2026-06-30T00:15:12.212484Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Conversational Query Engine for Mixed-Modality Heterogeneous Enterprise Data Sources","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.IR","authors_text":"Anindya Moitra, Ankur Vivek Singh, Darshita Rathore, Vaibhav Singal, Vineet Kumar","submitted_at":"2026-06-15T17:02:22Z","abstract_excerpt":"Enterprise business intelligence queries span structured warehouses and unstructured document repositories -- modalities with fundamentally different access methods, cost profiles, and correctness semantics. Existing AI-enabled interfaces force users to select the right tool: NL2SQL systems cannot reason over slide decks, and RAG pipelines lack access to live warehouse tables.\n  We present COGNI, a production conversational BI system that treats natural-language analytics as a heterogeneous query processing problem, organized as four architectural layers. First, an indexing layer implements sl"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.28370","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/2606.28370/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":"2606.28370","created_at":"2026-06-30T00:15:12.212543+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.28370v1","created_at":"2026-06-30T00:15:12.212543+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.28370","created_at":"2026-06-30T00:15:12.212543+00:00"},{"alias_kind":"pith_short_12","alias_value":"RYLGPTWGOXBG","created_at":"2026-06-30T00:15:12.212543+00:00"},{"alias_kind":"pith_short_16","alias_value":"RYLGPTWGOXBGHXPQ","created_at":"2026-06-30T00:15:12.212543+00:00"},{"alias_kind":"pith_short_8","alias_value":"RYLGPTWG","created_at":"2026-06-30T00:15:12.212543+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/RYLGPTWGOXBGHXPQ757XHFGJDW","json":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW.json","graph_json":"https://pith.science/api/pith-number/RYLGPTWGOXBGHXPQ757XHFGJDW/graph.json","events_json":"https://pith.science/api/pith-number/RYLGPTWGOXBGHXPQ757XHFGJDW/events.json","paper":"https://pith.science/paper/RYLGPTWG"},"agent_actions":{"view_html":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW","download_json":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW.json","view_paper":"https://pith.science/paper/RYLGPTWG","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.28370&json=true","fetch_graph":"https://pith.science/api/pith-number/RYLGPTWGOXBGHXPQ757XHFGJDW/graph.json","fetch_events":"https://pith.science/api/pith-number/RYLGPTWGOXBGHXPQ757XHFGJDW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW/action/storage_attestation","attest_author":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW/action/author_attestation","sign_citation":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW/action/citation_signature","submit_replication":"https://pith.science/pith/RYLGPTWGOXBGHXPQ757XHFGJDW/action/replication_record"}},"created_at":"2026-06-30T00:15:12.212543+00:00","updated_at":"2026-06-30T00:15:12.212543+00:00"}