{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:N3HB53PLSE7WIGRDNTQA44UQU6","short_pith_number":"pith:N3HB53PL","schema_version":"1.0","canonical_sha256":"6ece1eedeb913f641a236ce00e7290a792027d96fa205df3ba581f6d69f70d04","source":{"kind":"arxiv","id":"2507.22478","version":1},"attestation_state":"computed","paper":{"title":"SLM-SQL: An Exploration of Small Language Models for Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lei Sheng, Shuai-Shuai Xu","submitted_at":"2025-07-30T08:29:07Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong performance in translating natural language questions into SQL queries (Text-to-SQL). In contrast, small language models (SLMs) ranging from 0.5B to 1.5B parameters currently underperform on Text-to-SQL tasks due to their limited logical reasoning capabilities. However, SLMs offer inherent advantages in inference speed and suitability for edge deployment. To explore their potential in Text-to-SQL applications, we leverage recent advancements in post-training techniques. Specifically, we used the open-source SynSQL-2.5M dataset to construct "},"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":"2507.22478","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2025-07-30T08:29:07Z","cross_cats_sorted":[],"title_canon_sha256":"e54001d83baa6f1fe03df6a00de49b0869f2bc3fe6cde2f03acf428a67b91b4e","abstract_canon_sha256":"f81d661b7f8455f6872a99e6cfb0fedd59d90a552928bbbc96aab9f6961f2225"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:45:43.091037Z","signature_b64":"ezLdITqBg/s14eNvanT7zbKiINgzHuw7lV+eYn4KgdHcLgiV6CkoS+hwGCSxQGi2olanzrjfR1wwFHLZA2pcCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6ece1eedeb913f641a236ce00e7290a792027d96fa205df3ba581f6d69f70d04","last_reissued_at":"2026-07-05T11:45:43.090578Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:45:43.090578Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SLM-SQL: An Exploration of Small Language Models for Text-to-SQL","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Lei Sheng, Shuai-Shuai Xu","submitted_at":"2025-07-30T08:29:07Z","abstract_excerpt":"Large language models (LLMs) have demonstrated strong performance in translating natural language questions into SQL queries (Text-to-SQL). In contrast, small language models (SLMs) ranging from 0.5B to 1.5B parameters currently underperform on Text-to-SQL tasks due to their limited logical reasoning capabilities. However, SLMs offer inherent advantages in inference speed and suitability for edge deployment. To explore their potential in Text-to-SQL applications, we leverage recent advancements in post-training techniques. Specifically, we used the open-source SynSQL-2.5M dataset to construct "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.22478","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/2507.22478/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":"2507.22478","created_at":"2026-07-05T11:45:43.090631+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.22478v1","created_at":"2026-07-05T11:45:43.090631+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.22478","created_at":"2026-07-05T11:45:43.090631+00:00"},{"alias_kind":"pith_short_12","alias_value":"N3HB53PLSE7W","created_at":"2026-07-05T11:45:43.090631+00:00"},{"alias_kind":"pith_short_16","alias_value":"N3HB53PLSE7WIGRD","created_at":"2026-07-05T11:45:43.090631+00:00"},{"alias_kind":"pith_short_8","alias_value":"N3HB53PL","created_at":"2026-07-05T11:45:43.090631+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2603.04334","citing_title":"SpotIt+: Verification-based Text-to-SQL Evaluation with Database Constraints","ref_index":17,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6","json":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6.json","graph_json":"https://pith.science/api/pith-number/N3HB53PLSE7WIGRDNTQA44UQU6/graph.json","events_json":"https://pith.science/api/pith-number/N3HB53PLSE7WIGRDNTQA44UQU6/events.json","paper":"https://pith.science/paper/N3HB53PL"},"agent_actions":{"view_html":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6","download_json":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6.json","view_paper":"https://pith.science/paper/N3HB53PL","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.22478&json=true","fetch_graph":"https://pith.science/api/pith-number/N3HB53PLSE7WIGRDNTQA44UQU6/graph.json","fetch_events":"https://pith.science/api/pith-number/N3HB53PLSE7WIGRDNTQA44UQU6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6/action/storage_attestation","attest_author":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6/action/author_attestation","sign_citation":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6/action/citation_signature","submit_replication":"https://pith.science/pith/N3HB53PLSE7WIGRDNTQA44UQU6/action/replication_record"}},"created_at":"2026-07-05T11:45:43.090631+00:00","updated_at":"2026-07-05T11:45:43.090631+00:00"}