{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:OV2ULC6HP64Q42EQCSYUROL7WC","merge_version":"pith-open-graph-merge-v1","event_count":2,"valid_event_count":2,"invalid_event_count":0,"equivocation_count":0,"current":{"canonical_record":{"metadata":{"abstract_canon_sha256":"d58cd691f32555afb02d0822fdd31b0606b0bf76311ce814ce9c5325b70ddac9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T04:35:35Z","title_canon_sha256":"bb6bf5788ffc12c5038994c224355a32ce380143b5dd6a15c19ada46737db1ff"},"schema_version":"1.0","source":{"id":"2010.12773","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2010.12773","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"arxiv_version","alias_value":"2010.12773v3","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2010.12773","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_12","alias_value":"OV2ULC6HP64Q","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_16","alias_value":"OV2ULC6HP64Q42EQ","created_at":"2026-07-05T04:53:23Z"},{"alias_kind":"pith_short_8","alias_value":"OV2ULC6H","created_at":"2026-07-05T04:53:23Z"}],"graph_snapshots":[{"event_id":"sha256:ba31243f039fea0313a8b1ace7b9da2f2b3b5657c4495aa1841d26ca14cb57da","target":"graph","created_at":"2026-07-05T04:53:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"graph_snapshot":{"author_claims":{"count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57","strong_count":0},"builder_version":"pith-number-builder-2026-05-17-v1","claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"formal_canon":{"evidence_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2010.12773/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Learning to capture text-table alignment is essential for tasks like text-to-SQL. A model needs to correctly recognize natural language references to columns and values and to ground them in the given database schema. In this paper, we present a novel weakly supervised Structure-Grounded pretraining framework (StruG) for text-to-SQL that can effectively learn to capture text-table alignment based on a parallel text-table corpus. We identify a set of novel prediction tasks: column grounding, value grounding and column-value mapping, and leverage them to pretrain a text-table encoder. Additional","authors_text":"Ahmed Hassan Awadallah, Christopher Meek, Huan Sun, Matthew Richardson, Oleksandr Polozov, Xiang Deng","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T04:35:35Z","title":"Structure-Grounded Pretraining for Text-to-SQL"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2010.12773","kind":"arxiv","version":3},"verdict":{"created_at":null,"id":null,"model_set":{},"one_line_summary":"","pipeline_version":null,"pith_extraction_headline":"","strongest_claim":"","weakest_assumption":""}},"verdict_id":null}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:7ed697897368ca766459f7659b137febade9a51b1fe3308563434585860d6786","target":"record","created_at":"2026-07-05T04:53:23Z","signer":{"key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signer_id":"pith.science","signer_type":"pith_registry"},"payload":{"attestation_state":"computed","canonical_record":{"metadata":{"abstract_canon_sha256":"d58cd691f32555afb02d0822fdd31b0606b0bf76311ce814ce9c5325b70ddac9","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.CL","submitted_at":"2020-10-24T04:35:35Z","title_canon_sha256":"bb6bf5788ffc12c5038994c224355a32ce380143b5dd6a15c19ada46737db1ff"},"schema_version":"1.0","source":{"id":"2010.12773","kind":"arxiv","version":3}},"canonical_sha256":"7575458bc77fb90e689014b148b97fb09e93b0c4f06a472aa86bce85eeafaa07","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"7575458bc77fb90e689014b148b97fb09e93b0c4f06a472aa86bce85eeafaa07","first_computed_at":"2026-07-05T04:53:23.993394Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:53:23.993394Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"3qw1ul6gvnOHnYztvvkKpIycJotu8k3R58rKVESLLkQefGYSuot+TdtzP5PfBmE52wpF6thEy/jt7iMwu5jUAA==","signature_status":"signed_v1","signed_at":"2026-07-05T04:53:23.993778Z","signed_message":"canonical_sha256_bytes"},"source_id":"2010.12773","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:7ed697897368ca766459f7659b137febade9a51b1fe3308563434585860d6786","sha256:ba31243f039fea0313a8b1ace7b9da2f2b3b5657c4495aa1841d26ca14cb57da"],"state_sha256":"f008c710568795951b45e661bbca13f4ee0e0390d5f70b51dc36d40532127166"}