{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:UB5W44HFN65IHXCS4YMFEXT3ZC","short_pith_number":"pith:UB5W44HF","schema_version":"1.0","canonical_sha256":"a07b6e70e56fba83dc52e618525e7bc88ffaf41b60f14b76b62cf94ea995906e","source":{"kind":"arxiv","id":"2502.05237","version":1},"attestation_state":"computed","paper":{"title":"PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Bo Hu, Enjie Liu, Mochi Gao, Ruichao Zhong, Yuanzhen Xie, Yunzhi Tan, Zang Li, Zhenguo Yang, Zhuopan Yang","submitted_at":"2025-02-07T08:31:57Z","abstract_excerpt":"It is challenging to convert natural language (NL) questions into executable structured query language (SQL) queries for text-to-SQL tasks due to the vast number of database schemas with redundancy, which interferes with semantic learning, and the domain shift between NL and SQL. Existing works for schema linking focus on the table level and perform it once, ignoring the multi-granularity semantics and chainable cyclicity of schemas. In this paper, we propose a progressive schema linking with multi-granularity semantics (PSM-SQL) framework to reduce the redundant database schemas for text-to-S"},"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":"2502.05237","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2025-02-07T08:31:57Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c89ecb9b9a1fe06956c849ca0ce016a9c87cbfeca726855da657ff6173d4e4cc","abstract_canon_sha256":"52f44ce826c0268e4500eef67e4dae6351aca0370014688b51394699ea67b526"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:11:34.642135Z","signature_b64":"DAg3prfU2EBQbVloAk+vGiGLQ55fJO+UMnvMEEWdsk9JgAvSHuMx7ceUAIMDttFUTgkWne8+vWnClIJYbPk6Dg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"a07b6e70e56fba83dc52e618525e7bc88ffaf41b60f14b76b62cf94ea995906e","last_reissued_at":"2026-07-05T10:11:34.641671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:11:34.641671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"PSM-SQL: Progressive Schema Learning with Multi-granularity Semantics for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.DB","authors_text":"Bo Hu, Enjie Liu, Mochi Gao, Ruichao Zhong, Yuanzhen Xie, Yunzhi Tan, Zang Li, Zhenguo Yang, Zhuopan Yang","submitted_at":"2025-02-07T08:31:57Z","abstract_excerpt":"It is challenging to convert natural language (NL) questions into executable structured query language (SQL) queries for text-to-SQL tasks due to the vast number of database schemas with redundancy, which interferes with semantic learning, and the domain shift between NL and SQL. Existing works for schema linking focus on the table level and perform it once, ignoring the multi-granularity semantics and chainable cyclicity of schemas. In this paper, we propose a progressive schema linking with multi-granularity semantics (PSM-SQL) framework to reduce the redundant database schemas for text-to-S"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2502.05237","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/2502.05237/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":"2502.05237","created_at":"2026-07-05T10:11:34.641728+00:00"},{"alias_kind":"arxiv_version","alias_value":"2502.05237v1","created_at":"2026-07-05T10:11:34.641728+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2502.05237","created_at":"2026-07-05T10:11:34.641728+00:00"},{"alias_kind":"pith_short_12","alias_value":"UB5W44HFN65I","created_at":"2026-07-05T10:11:34.641728+00:00"},{"alias_kind":"pith_short_16","alias_value":"UB5W44HFN65IHXCS","created_at":"2026-07-05T10:11:34.641728+00:00"},{"alias_kind":"pith_short_8","alias_value":"UB5W44HF","created_at":"2026-07-05T10:11:34.641728+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":1,"sample":[{"citing_arxiv_id":"2509.07159","citing_title":"PaVeRL-SQL: Text-to-SQL via Partial-Match Rewards and Verbal Reinforcement Learning","ref_index":19,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC","json":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC.json","graph_json":"https://pith.science/api/pith-number/UB5W44HFN65IHXCS4YMFEXT3ZC/graph.json","events_json":"https://pith.science/api/pith-number/UB5W44HFN65IHXCS4YMFEXT3ZC/events.json","paper":"https://pith.science/paper/UB5W44HF"},"agent_actions":{"view_html":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC","download_json":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC.json","view_paper":"https://pith.science/paper/UB5W44HF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2502.05237&json=true","fetch_graph":"https://pith.science/api/pith-number/UB5W44HFN65IHXCS4YMFEXT3ZC/graph.json","fetch_events":"https://pith.science/api/pith-number/UB5W44HFN65IHXCS4YMFEXT3ZC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC/action/storage_attestation","attest_author":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC/action/author_attestation","sign_citation":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC/action/citation_signature","submit_replication":"https://pith.science/pith/UB5W44HFN65IHXCS4YMFEXT3ZC/action/replication_record"}},"created_at":"2026-07-05T10:11:34.641728+00:00","updated_at":"2026-07-05T10:11:34.641728+00:00"}