{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:SZOT7I2SILNHCSV34N3DA7GSSQ","short_pith_number":"pith:SZOT7I2S","schema_version":"1.0","canonical_sha256":"965d3fa35242da714abbe376307cd2942225b6d2a298286d1c58387704f3fbb1","source":{"kind":"arxiv","id":"2601.05451","version":2},"attestation_state":"computed","paper":{"title":"RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Cameron Barrie, Kevin Cushing, Kristian J. Hammond, Marko Sterbentz","submitted_at":"2026-01-09T00:46:53Z","abstract_excerpt":"Recent advances in text-to-SQL have been driven by larger models, better datasets, and new training methods like RLVR. However, progress remains limited by scarce high-quality training data, a problem RLVR is especially sensitive to since noisy data can produce spurious rewards. Manual data creation is expensive, and existing synthetic methods trade off reliability for scalability: template-based approaches guarantee correct SQL but need schema-specific templates and lack diversity, while LLM-based generation scales easily but lacks quality guarantees. We introduce RingSQL, a hybrid framework "},"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":"2601.05451","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-01-09T00:46:53Z","cross_cats_sorted":["cs.CL"],"title_canon_sha256":"cb719dd2abda06c4fa9ca37e45e3aaa89d495e8ec12178776efbb43875717c1f","abstract_canon_sha256":"84f3ffa33a7c008b3784c892f1da8fb6b8940620e5fe7aa5484581d702b317b2"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-08-06T01:16:50.915667Z","signature_b64":"y5CpsCQNFmCO3KL3FdQN3DrnaMpsiea/s5547tcw9vqJbMpCI7jQUrfVcl/u3x+5/+mmvCewGeV+AX0Kcp2kAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"965d3fa35242da714abbe376307cd2942225b6d2a298286d1c58387704f3fbb1","last_reissued_at":"2026-08-06T01:16:50.910891Z","signature_status":"signed_v1","first_computed_at":"2026-08-06T01:16:50.910891Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RingSQL: Schema-Independent Synthetic Data Generation for Text-to-SQL Reinforcement Learning","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.CL"],"primary_cat":"cs.LG","authors_text":"Cameron Barrie, Kevin Cushing, Kristian J. Hammond, Marko Sterbentz","submitted_at":"2026-01-09T00:46:53Z","abstract_excerpt":"Recent advances in text-to-SQL have been driven by larger models, better datasets, and new training methods like RLVR. However, progress remains limited by scarce high-quality training data, a problem RLVR is especially sensitive to since noisy data can produce spurious rewards. Manual data creation is expensive, and existing synthetic methods trade off reliability for scalability: template-based approaches guarantee correct SQL but need schema-specific templates and lack diversity, while LLM-based generation scales easily but lacks quality guarantees. We introduce RingSQL, a hybrid framework "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2601.05451","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/2601.05451/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":"2601.05451","created_at":"2026-08-06T01:16:50.912460+00:00"},{"alias_kind":"arxiv_version","alias_value":"2601.05451v2","created_at":"2026-08-06T01:16:50.912460+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2601.05451","created_at":"2026-08-06T01:16:50.912460+00:00"},{"alias_kind":"pith_short_12","alias_value":"SZOT7I2SILNH","created_at":"2026-08-06T01:16:50.912460+00:00"},{"alias_kind":"pith_short_16","alias_value":"SZOT7I2SILNHCSV3","created_at":"2026-08-06T01:16:50.912460+00:00"},{"alias_kind":"pith_short_8","alias_value":"SZOT7I2S","created_at":"2026-08-06T01:16:50.912460+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2608.06331","citing_title":"Tytan: Interactive Neurosymbolic Construction of Analytic Semantic Schemas from Relational Data","ref_index":47,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ","json":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ.json","graph_json":"https://pith.science/api/pith-number/SZOT7I2SILNHCSV34N3DA7GSSQ/graph.json","events_json":"https://pith.science/api/pith-number/SZOT7I2SILNHCSV34N3DA7GSSQ/events.json","paper":"https://pith.science/paper/SZOT7I2S"},"agent_actions":{"view_html":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ","download_json":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ.json","view_paper":"https://pith.science/paper/SZOT7I2S","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2601.05451&json=true","fetch_graph":"https://pith.science/api/pith-number/SZOT7I2SILNHCSV34N3DA7GSSQ/graph.json","fetch_events":"https://pith.science/api/pith-number/SZOT7I2SILNHCSV34N3DA7GSSQ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ/action/storage_attestation","attest_author":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ/action/author_attestation","sign_citation":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ/action/citation_signature","submit_replication":"https://pith.science/pith/SZOT7I2SILNHCSV34N3DA7GSSQ/action/replication_record"}},"created_at":"2026-08-06T01:16:50.912460+00:00","updated_at":"2026-08-06T01:16:50.912460+00:00"}