{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:56D2OTZ5QEGRST6UP5GFM5IEC2","short_pith_number":"pith:56D2OTZ5","schema_version":"1.0","canonical_sha256":"ef87a74f3d810d194fd47f4c56750416a1e135c324d3f196429cd871b3778d93","source":{"kind":"arxiv","id":"2606.05836","version":1},"attestation_state":"computed","paper":{"title":"ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Hu, Chen Hou, Danqing Huang, Dazhen Deng, Defeng Xie, Haoxuan Li, Haozhe Feng, Huawei Zheng, Minfeng Zhu, Peng Chen, Sen Yang, Wei Chen, Xuan Yi, Yingcai Wu, Yuhui Zhang, Zhaorui Yang, Zhizhen Yu","submitted_at":"2026-06-04T08:13:05Z","abstract_excerpt":"Large language models have substantially advanced Text-to-SQL systems, yet applying them to enterprise-scale databases remains challenging. Real-world databases often contain large and heterogeneous schemas, incomplete metadata, dialect-specific SQL syntax, and complex analytical questions that are difficult to solve with a single SQL query. To address these challenges, we propose ProSPy, a Profiling-driven SQL--Python agentic framework for enterprise-scale Text-to-SQL. ProSPy structures the reasoning process into four stages: it first extracts fine-grained data evidence through automatic prof"},"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":"2606.05836","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2026-06-04T08:13:05Z","cross_cats_sorted":[],"title_canon_sha256":"eb799d1e7dd6f6a491c2a5eae731c4fb905606955d1f4fa05c2d264144f07041","abstract_canon_sha256":"f54096190db573b614116ad1ec05fd9c43b1e1054911f2372c004de371baf017"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-05T01:15:05.181650Z","signature_b64":"pdf6v8oiffCgIzMjSKhLdFXt3Z/b1NQey1NgaqFmB49XQchB4OwUksAuBBCFSlou1QnehgofqFAp5PoNsbn7Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"ef87a74f3d810d194fd47f4c56750416a1e135c324d3f196429cd871b3778d93","last_reissued_at":"2026-06-05T01:15:05.181105Z","signature_status":"signed_v1","first_computed_at":"2026-06-05T01:15:05.181105Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ProSPy: A Profiling-Driven SQL-Python Agentic Framework for Enterprise Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Chao Hu, Chen Hou, Danqing Huang, Dazhen Deng, Defeng Xie, Haoxuan Li, Haozhe Feng, Huawei Zheng, Minfeng Zhu, Peng Chen, Sen Yang, Wei Chen, Xuan Yi, Yingcai Wu, Yuhui Zhang, Zhaorui Yang, Zhizhen Yu","submitted_at":"2026-06-04T08:13:05Z","abstract_excerpt":"Large language models have substantially advanced Text-to-SQL systems, yet applying them to enterprise-scale databases remains challenging. Real-world databases often contain large and heterogeneous schemas, incomplete metadata, dialect-specific SQL syntax, and complex analytical questions that are difficult to solve with a single SQL query. To address these challenges, we propose ProSPy, a Profiling-driven SQL--Python agentic framework for enterprise-scale Text-to-SQL. ProSPy structures the reasoning process into four stages: it first extracts fine-grained data evidence through automatic prof"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.05836","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/2606.05836/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":"2606.05836","created_at":"2026-06-05T01:15:05.181181+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.05836v1","created_at":"2026-06-05T01:15:05.181181+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.05836","created_at":"2026-06-05T01:15:05.181181+00:00"},{"alias_kind":"pith_short_12","alias_value":"56D2OTZ5QEGR","created_at":"2026-06-05T01:15:05.181181+00:00"},{"alias_kind":"pith_short_16","alias_value":"56D2OTZ5QEGRST6U","created_at":"2026-06-05T01:15:05.181181+00:00"},{"alias_kind":"pith_short_8","alias_value":"56D2OTZ5","created_at":"2026-06-05T01:15:05.181181+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/56D2OTZ5QEGRST6UP5GFM5IEC2","json":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2.json","graph_json":"https://pith.science/api/pith-number/56D2OTZ5QEGRST6UP5GFM5IEC2/graph.json","events_json":"https://pith.science/api/pith-number/56D2OTZ5QEGRST6UP5GFM5IEC2/events.json","paper":"https://pith.science/paper/56D2OTZ5"},"agent_actions":{"view_html":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2","download_json":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2.json","view_paper":"https://pith.science/paper/56D2OTZ5","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.05836&json=true","fetch_graph":"https://pith.science/api/pith-number/56D2OTZ5QEGRST6UP5GFM5IEC2/graph.json","fetch_events":"https://pith.science/api/pith-number/56D2OTZ5QEGRST6UP5GFM5IEC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2/action/storage_attestation","attest_author":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2/action/author_attestation","sign_citation":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2/action/citation_signature","submit_replication":"https://pith.science/pith/56D2OTZ5QEGRST6UP5GFM5IEC2/action/replication_record"}},"created_at":"2026-06-05T01:15:05.181181+00:00","updated_at":"2026-06-05T01:15:05.181181+00:00"}