{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:BSWXEBIQ7DBTEFFGKWKKHZYIIZ","short_pith_number":"pith:BSWXEBIQ","schema_version":"1.0","canonical_sha256":"0cad720510f8c33214a65594a3e708466869ec33285970b04986291dbfa79805","source":{"kind":"arxiv","id":"2501.16220","version":2},"attestation_state":"computed","paper":{"title":"DBRouting: Routing End User Queries to Databases for Answerability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lovekesh Vig, Manasi Patwardhan, Mayur Patidar, Priyangshu Mandal","submitted_at":"2025-01-27T17:09:47Z","abstract_excerpt":"Enterprise level data is often distributed across multiple sources and identifying the correct set-of data-sources with relevant information for a knowledge request is a fundamental challenge. In this work, we define the novel task of routing an end-user query to the appropriate data-source, where the data-sources are databases. We synthesize datasets by extending existing datasets designed for NL-to-SQL semantic parsing. We create baselines on these datasets by using open-source LLMs, using both pre-trained and task specific embeddings fine-tuned using the training data. With these baselines "},"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":"2501.16220","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-01-27T17:09:47Z","cross_cats_sorted":[],"title_canon_sha256":"215fffd97607d6587b58499b4edc00b60b6bca511d7ee86e52726c85251d1b44","abstract_canon_sha256":"293de623325ced38811579fd4f9bc0d3c6c451f148dd6b4f2b08b2a737b5bb88"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:06:11.312723Z","signature_b64":"mwwsQdEDTk6+p2b6Qjmoeqo5SIxt/zdyuHbeC6igld3vaBfukwJn3rRi5CfbLELIwEJ32CgpAm8xs1rde9cQBg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0cad720510f8c33214a65594a3e708466869ec33285970b04986291dbfa79805","last_reissued_at":"2026-07-05T10:06:11.312226Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:06:11.312226Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"DBRouting: Routing End User Queries to Databases for Answerability","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lovekesh Vig, Manasi Patwardhan, Mayur Patidar, Priyangshu Mandal","submitted_at":"2025-01-27T17:09:47Z","abstract_excerpt":"Enterprise level data is often distributed across multiple sources and identifying the correct set-of data-sources with relevant information for a knowledge request is a fundamental challenge. In this work, we define the novel task of routing an end-user query to the appropriate data-source, where the data-sources are databases. We synthesize datasets by extending existing datasets designed for NL-to-SQL semantic parsing. We create baselines on these datasets by using open-source LLMs, using both pre-trained and task specific embeddings fine-tuned using the training data. With these baselines "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2501.16220","kind":"arxiv","version":2},"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/2501.16220/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":"2501.16220","created_at":"2026-07-05T10:06:11.312285+00:00"},{"alias_kind":"arxiv_version","alias_value":"2501.16220v2","created_at":"2026-07-05T10:06:11.312285+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2501.16220","created_at":"2026-07-05T10:06:11.312285+00:00"},{"alias_kind":"pith_short_12","alias_value":"BSWXEBIQ7DBT","created_at":"2026-07-05T10:06:11.312285+00:00"},{"alias_kind":"pith_short_16","alias_value":"BSWXEBIQ7DBTEFFG","created_at":"2026-07-05T10:06:11.312285+00:00"},{"alias_kind":"pith_short_8","alias_value":"BSWXEBIQ","created_at":"2026-07-05T10:06:11.312285+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/BSWXEBIQ7DBTEFFGKWKKHZYIIZ","json":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ.json","graph_json":"https://pith.science/api/pith-number/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/graph.json","events_json":"https://pith.science/api/pith-number/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/events.json","paper":"https://pith.science/paper/BSWXEBIQ"},"agent_actions":{"view_html":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ","download_json":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ.json","view_paper":"https://pith.science/paper/BSWXEBIQ","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2501.16220&json=true","fetch_graph":"https://pith.science/api/pith-number/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/graph.json","fetch_events":"https://pith.science/api/pith-number/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/action/storage_attestation","attest_author":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/action/author_attestation","sign_citation":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/action/citation_signature","submit_replication":"https://pith.science/pith/BSWXEBIQ7DBTEFFGKWKKHZYIIZ/action/replication_record"}},"created_at":"2026-07-05T10:06:11.312285+00:00","updated_at":"2026-07-05T10:06:11.312285+00:00"}