{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2020:TBZ5APQJTS7AHIKDU4N7TAHWRN","short_pith_number":"pith:TBZ5APQJ","canonical_record":{"source":{"id":"2012.10309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-18T15:53:50Z","cross_cats_sorted":[],"title_canon_sha256":"7fc62352b2d6c20b01ce0020d07584b19e357e2b28d560e8a2cbace27375830b","abstract_canon_sha256":"5fa11a05fa060a69647380c9ff843af553af8a9636c3fedf8cc133f3d0b65bd0"},"schema_version":"1.0"},"canonical_sha256":"9873d03e099cbe03a143a71bf980f68b6cfa67e8c4ddd99f0a7d6be4071c153f","source":{"kind":"arxiv","id":"2012.10309","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10309","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10309v1","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10309","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"TBZ5APQJTS7A","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"pith_short_16","alias_value":"TBZ5APQJTS7AHIKD","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"pith_short_8","alias_value":"TBZ5APQJ","created_at":"2026-07-05T02:00:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2020:TBZ5APQJTS7AHIKDU4N7TAHWRN","target":"record","payload":{"canonical_record":{"source":{"id":"2012.10309","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-18T15:53:50Z","cross_cats_sorted":[],"title_canon_sha256":"7fc62352b2d6c20b01ce0020d07584b19e357e2b28d560e8a2cbace27375830b","abstract_canon_sha256":"5fa11a05fa060a69647380c9ff843af553af8a9636c3fedf8cc133f3d0b65bd0"},"schema_version":"1.0"},"canonical_sha256":"9873d03e099cbe03a143a71bf980f68b6cfa67e8c4ddd99f0a7d6be4071c153f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T02:00:37.667046Z","signature_b64":"Zz/8E7tijzNbSx0WmgDuonfHHGfItUNHL8V6MQ8k7gvT+cM3PLNpQbjmBK40QO3y/Tpi5NaXTc1n6BJne/V8Cg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"9873d03e099cbe03a143a71bf980f68b6cfa67e8c4ddd99f0a7d6be4071c153f","last_reissued_at":"2026-07-05T02:00:37.666671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T02:00:37.666671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2012.10309","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Nu1HyTTYEpM5h1RfmTWCdthh01ZVapna7nOnCFVJlBk5xyM7JnNqTU/hv/TTIdpYaPMWzTZ/S4opvtgr6l/DAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:55:01.711222Z"},"content_sha256":"287233c31e3cd0f3a88432091a9214737b0371e88dfefc55fdb11327bd1818bc","schema_version":"1.0","event_id":"sha256:287233c31e3cd0f3a88432091a9214737b0371e88dfefc55fdb11327bd1818bc"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2020:TBZ5APQJTS7AHIKDU4N7TAHWRN","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Alexander Hanbo Li, Bing Xiang, Cicero Nogueira dos Santos, Henghui Zhu, Jun Wang, Patrick Ng, Peng Shi, Zhiguo Wang","submitted_at":"2020-12-18T15:53:50Z","abstract_excerpt":"Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL semantic parsers: fail to detect column mentions in the utterances, fail to infer column mentions from cell values, and fail to compose complex SQL queries. To mitigate these issues, we present"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10309","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/2012.10309/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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T02:00:37Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"j6K/ihCxaJIplUzwyVgJV5Q2c/q0122tRdVWmcYC8N2ASEBy/jMsKMIcsnhvPfoLSYoFy/vn31aBvQ+399snBQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-03T18:55:01.712153Z"},"content_sha256":"98db9e584b3c170091864ef8d6aeab661dfc35f5f0ae62d742a770b52c4f4042","schema_version":"1.0","event_id":"sha256:98db9e584b3c170091864ef8d6aeab661dfc35f5f0ae62d742a770b52c4f4042"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/bundle.json","state_url":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-08-03T18:55:01Z","links":{"resolver":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN","bundle":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/bundle.json","state":"https://pith.science/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/state.json","well_known_bundle":"https://pith.science/.well-known/pith/TBZ5APQJTS7AHIKDU4N7TAHWRN/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2020:TBZ5APQJTS7AHIKDU4N7TAHWRN","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":"5fa11a05fa060a69647380c9ff843af553af8a9636c3fedf8cc133f3d0b65bd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-18T15:53:50Z","title_canon_sha256":"7fc62352b2d6c20b01ce0020d07584b19e357e2b28d560e8a2cbace27375830b"},"schema_version":"1.0","source":{"id":"2012.10309","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2012.10309","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"arxiv_version","alias_value":"2012.10309v1","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2012.10309","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"pith_short_12","alias_value":"TBZ5APQJTS7A","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"pith_short_16","alias_value":"TBZ5APQJTS7AHIKD","created_at":"2026-07-05T02:00:37Z"},{"alias_kind":"pith_short_8","alias_value":"TBZ5APQJ","created_at":"2026-07-05T02:00:37Z"}],"graph_snapshots":[{"event_id":"sha256:98db9e584b3c170091864ef8d6aeab661dfc35f5f0ae62d742a770b52c4f4042","target":"graph","created_at":"2026-07-05T02:00:37Z","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/2012.10309/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Most recently, there has been significant interest in learning contextual representations for various NLP tasks, by leveraging large scale text corpora to train large neural language models with self-supervised learning objectives, such as Masked Language Model (MLM). However, based on a pilot study, we observe three issues of existing general-purpose language models when they are applied to text-to-SQL semantic parsers: fail to detect column mentions in the utterances, fail to infer column mentions from cell values, and fail to compose complex SQL queries. To mitigate these issues, we present","authors_text":"Alexander Hanbo Li, Bing Xiang, Cicero Nogueira dos Santos, Henghui Zhu, Jun Wang, Patrick Ng, Peng Shi, Zhiguo Wang","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-18T15:53:50Z","title":"Learning Contextual Representations for Semantic Parsing with Generation-Augmented Pre-Training"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2012.10309","kind":"arxiv","version":1},"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":"sha256:287233c31e3cd0f3a88432091a9214737b0371e88dfefc55fdb11327bd1818bc","target":"record","created_at":"2026-07-05T02:00:37Z","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":"5fa11a05fa060a69647380c9ff843af553af8a9636c3fedf8cc133f3d0b65bd0","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2020-12-18T15:53:50Z","title_canon_sha256":"7fc62352b2d6c20b01ce0020d07584b19e357e2b28d560e8a2cbace27375830b"},"schema_version":"1.0","source":{"id":"2012.10309","kind":"arxiv","version":1}},"canonical_sha256":"9873d03e099cbe03a143a71bf980f68b6cfa67e8c4ddd99f0a7d6be4071c153f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"9873d03e099cbe03a143a71bf980f68b6cfa67e8c4ddd99f0a7d6be4071c153f","first_computed_at":"2026-07-05T02:00:37.666671Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T02:00:37.666671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zz/8E7tijzNbSx0WmgDuonfHHGfItUNHL8V6MQ8k7gvT+cM3PLNpQbjmBK40QO3y/Tpi5NaXTc1n6BJne/V8Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T02:00:37.667046Z","signed_message":"canonical_sha256_bytes"},"source_id":"2012.10309","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:287233c31e3cd0f3a88432091a9214737b0371e88dfefc55fdb11327bd1818bc","sha256:98db9e584b3c170091864ef8d6aeab661dfc35f5f0ae62d742a770b52c4f4042"],"state_sha256":"24c453b40d1239885d1c1713b94f0ed8a8c8461ae7faf2dcc0e8cb9a941d525f"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"fRSFVCAH+VXa+IgLCFUzppjT8jdjbeyo/MjT9f5mIoVHxRTKOnPg+6sy0WOPVzpcBgaQ0iP1TeeQsiXMkmUcAA==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-03T18:55:01.718157Z","bundle_sha256":"50527828089cd1cb10ced0c6112630968cde407ccc7117ed0572b742a2068963"}}