{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:WRU63P2ZPU7UDYMC74FEAWT3VD","short_pith_number":"pith:WRU63P2Z","schema_version":"1.0","canonical_sha256":"b469edbf597d3f41e182ff0a405a7ba8cf1e746b3840dd29b842eb2cab523060","source":{"kind":"arxiv","id":"2008.04759","version":1},"attestation_state":"computed","paper":{"title":"Hybrid Ranking Network for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianwen Zhang, Kaushik Chakrabarti, Qin Lyu, Shobhit Hathi, Souvik Kundu, Zheng Chen","submitted_at":"2020-08-11T15:01:52Z","abstract_excerpt":"In this paper, we study how to leverage pre-trained language models in Text-to-SQL. We argue that previous approaches under utilize the base language models by concatenating all columns together with the NL question and feeding them into the base language model in the encoding stage. We propose a neat approach called Hybrid Ranking Network (HydraNet) which breaks down the problem into column-wise ranking and decoding and finally assembles the column-wise outputs into a SQL query by straightforward rules. In this approach, the encoder is given a NL question and one individual column, which perf"},"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":"2008.04759","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-08-11T15:01:52Z","cross_cats_sorted":[],"title_canon_sha256":"9ce956d0367f2ec0fe687f57608d905a3ceb54d1e7fa65c60b79f2a894b93773","abstract_canon_sha256":"240fa139b480f75671c9f936232abfc7f4de8c9c70ac3f7d900d1fa6b78e0bbf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:26:28.501271Z","signature_b64":"ypHBM1piHbLVGxRs+TNH2ju2nqEKYbHwzEMGyiGfTCVHe33+xhWLhPM54gcJoFx55+2PjXNv6ArHjWY6vN7QBw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"b469edbf597d3f41e182ff0a405a7ba8cf1e746b3840dd29b842eb2cab523060","last_reissued_at":"2026-07-05T01:26:28.500764Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:26:28.500764Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Hybrid Ranking Network for Text-to-SQL","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Jianwen Zhang, Kaushik Chakrabarti, Qin Lyu, Shobhit Hathi, Souvik Kundu, Zheng Chen","submitted_at":"2020-08-11T15:01:52Z","abstract_excerpt":"In this paper, we study how to leverage pre-trained language models in Text-to-SQL. We argue that previous approaches under utilize the base language models by concatenating all columns together with the NL question and feeding them into the base language model in the encoding stage. We propose a neat approach called Hybrid Ranking Network (HydraNet) which breaks down the problem into column-wise ranking and decoding and finally assembles the column-wise outputs into a SQL query by straightforward rules. In this approach, the encoder is given a NL question and one individual column, which perf"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2008.04759","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/2008.04759/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":"2008.04759","created_at":"2026-07-05T01:26:28.500830+00:00"},{"alias_kind":"arxiv_version","alias_value":"2008.04759v1","created_at":"2026-07-05T01:26:28.500830+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2008.04759","created_at":"2026-07-05T01:26:28.500830+00:00"},{"alias_kind":"pith_short_12","alias_value":"WRU63P2ZPU7U","created_at":"2026-07-05T01:26:28.500830+00:00"},{"alias_kind":"pith_short_16","alias_value":"WRU63P2ZPU7UDYMC","created_at":"2026-07-05T01:26:28.500830+00:00"},{"alias_kind":"pith_short_8","alias_value":"WRU63P2Z","created_at":"2026-07-05T01:26:28.500830+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":188,"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":203,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD","json":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD.json","graph_json":"https://pith.science/api/pith-number/WRU63P2ZPU7UDYMC74FEAWT3VD/graph.json","events_json":"https://pith.science/api/pith-number/WRU63P2ZPU7UDYMC74FEAWT3VD/events.json","paper":"https://pith.science/paper/WRU63P2Z"},"agent_actions":{"view_html":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD","download_json":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD.json","view_paper":"https://pith.science/paper/WRU63P2Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2008.04759&json=true","fetch_graph":"https://pith.science/api/pith-number/WRU63P2ZPU7UDYMC74FEAWT3VD/graph.json","fetch_events":"https://pith.science/api/pith-number/WRU63P2ZPU7UDYMC74FEAWT3VD/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD/action/timestamp_anchor","attest_storage":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD/action/storage_attestation","attest_author":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD/action/author_attestation","sign_citation":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD/action/citation_signature","submit_replication":"https://pith.science/pith/WRU63P2ZPU7UDYMC74FEAWT3VD/action/replication_record"}},"created_at":"2026-07-05T01:26:28.500830+00:00","updated_at":"2026-07-05T01:26:28.500830+00:00"}