{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2022:JLQVWALY7MZENVVLKHF2O5WEFU","short_pith_number":"pith:JLQVWALY","schema_version":"1.0","canonical_sha256":"4ae15b0178fb3246d6ab51cba776c42d36dd473a5b01125f55e5ea8d5c598ff8","source":{"kind":"arxiv","id":"2205.06983","version":2},"attestation_state":"computed","paper":{"title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenghu Zhou, Jiexing Qi, Jingyao Tang, Quanshi Zhang, Xiangpeng Wan, Xinbing Wang, Yu Cheng, Zhouhan Lin, Ziwei He","submitted_at":"2022-05-14T06:27:40Z","abstract_excerpt":"Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries. However, introducing these structural relations comes with prices: they often result in a specialized model structure, which largely prohibits using large pretrained models in text-to-SQL. To address this problem, we propose RASAT: a Transformer seq2seq architecture augmented with relation-aware self-attention that could leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model effe"},"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":"2205.06983","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2022-05-14T06:27:40Z","cross_cats_sorted":["cs.AI","cs.DB","cs.LG"],"title_canon_sha256":"3947fe911057d643e00a828bcc2ef086736df44865dfe5458a93189255c6a76e","abstract_canon_sha256":"955767df366121dffbd396a795e91b204cd565fb417b628731fc899fae2bc81e"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:04:29.205626Z","signature_b64":"QXUCwbMJovIRzRqb+zfaGdoNPgLNLKT0Vj3Gt1fBLeWPlYNW79Vv+MYmPRV1hdugZ+eGbZJ9Ly1VBtx/ijCUDw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4ae15b0178fb3246d6ab51cba776c42d36dd473a5b01125f55e5ea8d5c598ff8","last_reissued_at":"2026-07-05T05:04:29.205188Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:04:29.205188Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"RASAT: Integrating Relational Structures into Pretrained Seq2Seq Model for Text-to-SQL","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.LG"],"primary_cat":"cs.CL","authors_text":"Chenghu Zhou, Jiexing Qi, Jingyao Tang, Quanshi Zhang, Xiangpeng Wan, Xinbing Wang, Yu Cheng, Zhouhan Lin, Ziwei He","submitted_at":"2022-05-14T06:27:40Z","abstract_excerpt":"Relational structures such as schema linking and schema encoding have been validated as a key component to qualitatively translating natural language into SQL queries. However, introducing these structural relations comes with prices: they often result in a specialized model structure, which largely prohibits using large pretrained models in text-to-SQL. To address this problem, we propose RASAT: a Transformer seq2seq architecture augmented with relation-aware self-attention that could leverage a variety of relational structures while inheriting the pretrained parameters from the T5 model effe"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2205.06983","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/2205.06983/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":"2205.06983","created_at":"2026-07-05T05:04:29.205249+00:00"},{"alias_kind":"arxiv_version","alias_value":"2205.06983v2","created_at":"2026-07-05T05:04:29.205249+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2205.06983","created_at":"2026-07-05T05:04:29.205249+00:00"},{"alias_kind":"pith_short_12","alias_value":"JLQVWALY7MZE","created_at":"2026-07-05T05:04:29.205249+00:00"},{"alias_kind":"pith_short_16","alias_value":"JLQVWALY7MZENVVL","created_at":"2026-07-05T05:04:29.205249+00:00"},{"alias_kind":"pith_short_8","alias_value":"JLQVWALY","created_at":"2026-07-05T05:04:29.205249+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":1,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2405.16755","citing_title":"CHESS: Contextual Harnessing for Efficient SQL Synthesis","ref_index":59,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU","json":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU.json","graph_json":"https://pith.science/api/pith-number/JLQVWALY7MZENVVLKHF2O5WEFU/graph.json","events_json":"https://pith.science/api/pith-number/JLQVWALY7MZENVVLKHF2O5WEFU/events.json","paper":"https://pith.science/paper/JLQVWALY"},"agent_actions":{"view_html":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU","download_json":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU.json","view_paper":"https://pith.science/paper/JLQVWALY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2205.06983&json=true","fetch_graph":"https://pith.science/api/pith-number/JLQVWALY7MZENVVLKHF2O5WEFU/graph.json","fetch_events":"https://pith.science/api/pith-number/JLQVWALY7MZENVVLKHF2O5WEFU/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU/action/storage_attestation","attest_author":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU/action/author_attestation","sign_citation":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU/action/citation_signature","submit_replication":"https://pith.science/pith/JLQVWALY7MZENVVLKHF2O5WEFU/action/replication_record"}},"created_at":"2026-07-05T05:04:29.205249+00:00","updated_at":"2026-07-05T05:04:29.205249+00:00"}