{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:POBVIAGFSRQWQUL3OIBGXIJJY5","short_pith_number":"pith:POBVIAGF","schema_version":"1.0","canonical_sha256":"7b835400c5946168517b72026ba129c774ebe99fc98f985cb08cfa990a1aae47","source":{"kind":"arxiv","id":"2409.12172","version":1},"attestation_state":"computed","paper":{"title":"You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Henghui Zhu, Hideo Kobayashi, Jiang Guo, Patrick Ng, Peng Shi, Shuaichen Chang, Wuwei Lan, Zhiguo Wang","submitted_at":"2024-09-18T17:38:25Z","abstract_excerpt":"While significant progress has been made on the text-to-SQL task, recent solutions repeatedly encode the same database schema for every question, resulting in unnecessary high inference cost and often overlooking crucial database knowledge. To address these issues, we propose You Only Read Once (YORO), a novel paradigm that directly internalizes database knowledge into the parametric knowledge of a text-to-SQL model during training and eliminates the need for schema encoding during inference. YORO significantly reduces the input token length by 66%-98%. Despite its shorter inputs, our empirica"},"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":"2409.12172","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2024-09-18T17:38:25Z","cross_cats_sorted":[],"title_canon_sha256":"54347d91bf8e03c55c0e4ecb7b8aa978ba21ec34f7ac6bcabdba46d49b5addfe","abstract_canon_sha256":"02b8809a6df85f3cc371c74d7e94790cb21347cd8fd1e762957d4aa6b347d4df"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T09:08:43.885216Z","signature_b64":"JIwmj9hyNvEw33GcpgG7tV0+34tCNQjAkCcQk0dFTp0WvQfFxsIAoK+P//u7Ye07Kqfw0ly6Kc2kRjFay26jCQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"7b835400c5946168517b72026ba129c774ebe99fc98f985cb08cfa990a1aae47","last_reissued_at":"2026-07-05T09:08:43.884660Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T09:08:43.884660Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"You Only Read Once (YORO): Learning to Internalize Database Knowledge for Text-to-SQL","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Henghui Zhu, Hideo Kobayashi, Jiang Guo, Patrick Ng, Peng Shi, Shuaichen Chang, Wuwei Lan, Zhiguo Wang","submitted_at":"2024-09-18T17:38:25Z","abstract_excerpt":"While significant progress has been made on the text-to-SQL task, recent solutions repeatedly encode the same database schema for every question, resulting in unnecessary high inference cost and often overlooking crucial database knowledge. To address these issues, we propose You Only Read Once (YORO), a novel paradigm that directly internalizes database knowledge into the parametric knowledge of a text-to-SQL model during training and eliminates the need for schema encoding during inference. YORO significantly reduces the input token length by 66%-98%. Despite its shorter inputs, our empirica"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2409.12172","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/2409.12172/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":"2409.12172","created_at":"2026-07-05T09:08:43.884723+00:00"},{"alias_kind":"arxiv_version","alias_value":"2409.12172v1","created_at":"2026-07-05T09:08:43.884723+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2409.12172","created_at":"2026-07-05T09:08:43.884723+00:00"},{"alias_kind":"pith_short_12","alias_value":"POBVIAGFSRQW","created_at":"2026-07-05T09:08:43.884723+00:00"},{"alias_kind":"pith_short_16","alias_value":"POBVIAGFSRQWQUL3","created_at":"2026-07-05T09:08:43.884723+00:00"},{"alias_kind":"pith_short_8","alias_value":"POBVIAGF","created_at":"2026-07-05T09:08:43.884723+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.04066","citing_title":"Adapt to Thrive! Adaptive Power-Mean Policy Optimization for Improved LLM Reasoning","ref_index":91,"is_internal_anchor":false},{"citing_arxiv_id":"2605.04065","citing_title":"Free Energy-Driven Reinforcement Learning with Adaptive Advantage Shaping for Unsupervised Reasoning in LLMs","ref_index":106,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5","json":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5.json","graph_json":"https://pith.science/api/pith-number/POBVIAGFSRQWQUL3OIBGXIJJY5/graph.json","events_json":"https://pith.science/api/pith-number/POBVIAGFSRQWQUL3OIBGXIJJY5/events.json","paper":"https://pith.science/paper/POBVIAGF"},"agent_actions":{"view_html":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5","download_json":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5.json","view_paper":"https://pith.science/paper/POBVIAGF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2409.12172&json=true","fetch_graph":"https://pith.science/api/pith-number/POBVIAGFSRQWQUL3OIBGXIJJY5/graph.json","fetch_events":"https://pith.science/api/pith-number/POBVIAGFSRQWQUL3OIBGXIJJY5/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5/action/timestamp_anchor","attest_storage":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5/action/storage_attestation","attest_author":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5/action/author_attestation","sign_citation":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5/action/citation_signature","submit_replication":"https://pith.science/pith/POBVIAGFSRQWQUL3OIBGXIJJY5/action/replication_record"}},"created_at":"2026-07-05T09:08:43.884723+00:00","updated_at":"2026-07-05T09:08:43.884723+00:00"}