{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2020:MLCOZWPPSG533TJWBA3RF5446E","short_pith_number":"pith:MLCOZWPP","schema_version":"1.0","canonical_sha256":"62c4ecd9ef91bbbdcd36083712f79cf13a2212e00cda322b3b6dac90dbb43935","source":{"kind":"arxiv","id":"2010.09927","version":1},"attestation_state":"computed","paper":{"title":"ColloQL: Robust Cross-Domain Text-to-SQL Over Search Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Arvind Srikantan, Karthik Radhakrishnan, Xi Victoria Lin","submitted_at":"2020-10-19T23:53:17Z","abstract_excerpt":"Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has largely focused on textual input that is linguistically correct and semantically unambiguous. However, real-world user queries are often succinct, colloquial, and noisy, resembling the input of a search engine. In this work, we introduce data augmentation techniques and a sampling-based content-aware BERT model (ColloQL) to achieve robust text-to-SQL modeling ove"},"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":"2010.09927","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-19T23:53:17Z","cross_cats_sorted":["cs.AI","cs.DB","cs.IR"],"title_canon_sha256":"4faf946b8f66549a9f43453e61edc897988b8ed1f9dee61328349f2a211bbcdd","abstract_canon_sha256":"2c4fd3dcbf20f2ab10a680aad33df025809647078702471e21c7ed878cf0b2ea"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T01:44:25.317635Z","signature_b64":"sY81aWnxI4ERP5BQ3eltKHpc1PG5cZxPqHk2FXfphprsI/mHCzyIH7HLbGsws61XrdR5G+qZii3YR664v2lXCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"62c4ecd9ef91bbbdcd36083712f79cf13a2212e00cda322b3b6dac90dbb43935","last_reissued_at":"2026-07-05T01:44:25.317215Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T01:44:25.317215Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"ColloQL: Robust Cross-Domain Text-to-SQL Over Search Queries","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB","cs.IR"],"primary_cat":"cs.CL","authors_text":"Arvind Srikantan, Karthik Radhakrishnan, Xi Victoria Lin","submitted_at":"2020-10-19T23:53:17Z","abstract_excerpt":"Translating natural language utterances to executable queries is a helpful technique in making the vast amount of data stored in relational databases accessible to a wider range of non-tech-savvy end users. Prior work in this area has largely focused on textual input that is linguistically correct and semantically unambiguous. However, real-world user queries are often succinct, colloquial, and noisy, resembling the input of a search engine. In this work, we introduce data augmentation techniques and a sampling-based content-aware BERT model (ColloQL) to achieve robust text-to-SQL modeling ove"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.09927","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/2010.09927/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":"2010.09927","created_at":"2026-07-05T01:44:25.317272+00:00"},{"alias_kind":"arxiv_version","alias_value":"2010.09927v1","created_at":"2026-07-05T01:44:25.317272+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.09927","created_at":"2026-07-05T01:44:25.317272+00:00"},{"alias_kind":"pith_short_12","alias_value":"MLCOZWPPSG53","created_at":"2026-07-05T01:44:25.317272+00:00"},{"alias_kind":"pith_short_16","alias_value":"MLCOZWPPSG533TJW","created_at":"2026-07-05T01:44:25.317272+00:00"},{"alias_kind":"pith_short_8","alias_value":"MLCOZWPP","created_at":"2026-07-05T01:44:25.317272+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E","json":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E.json","graph_json":"https://pith.science/api/pith-number/MLCOZWPPSG533TJWBA3RF5446E/graph.json","events_json":"https://pith.science/api/pith-number/MLCOZWPPSG533TJWBA3RF5446E/events.json","paper":"https://pith.science/paper/MLCOZWPP"},"agent_actions":{"view_html":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E","download_json":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E.json","view_paper":"https://pith.science/paper/MLCOZWPP","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2010.09927&json=true","fetch_graph":"https://pith.science/api/pith-number/MLCOZWPPSG533TJWBA3RF5446E/graph.json","fetch_events":"https://pith.science/api/pith-number/MLCOZWPPSG533TJWBA3RF5446E/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E/action/storage_attestation","attest_author":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E/action/author_attestation","sign_citation":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E/action/citation_signature","submit_replication":"https://pith.science/pith/MLCOZWPPSG533TJWBA3RF5446E/action/replication_record"}},"created_at":"2026-07-05T01:44:25.317272+00:00","updated_at":"2026-07-05T01:44:25.317272+00:00"}