{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2022:OLIRKUC6IYEEVTY55VHREYKKFF","short_pith_number":"pith:OLIRKUC6","canonical_record":{"source":{"id":"2211.06193","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T13:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"2d65881a06f1797eea5094eeddab998bcb46fa296accafedf91356aae92cc283","abstract_canon_sha256":"e74224e9ce58a537f5398354a816b412440df8687f7805f535d2133df4dae78f"},"schema_version":"1.0"},"canonical_sha256":"72d115505e46084acf1ded4f12614a295d0ed4d3af18454cdec0a96daae0a12f","source":{"kind":"arxiv","id":"2211.06193","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06193","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06193v1","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06193","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"OLIRKUC6IYEE","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"OLIRKUC6IYEEVTY5","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"OLIRKUC6","created_at":"2026-07-05T05:15:18Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2022:OLIRKUC6IYEEVTY55VHREYKKFF","target":"record","payload":{"canonical_record":{"source":{"id":"2211.06193","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T13:31:55Z","cross_cats_sorted":[],"title_canon_sha256":"2d65881a06f1797eea5094eeddab998bcb46fa296accafedf91356aae92cc283","abstract_canon_sha256":"e74224e9ce58a537f5398354a816b412440df8687f7805f535d2133df4dae78f"},"schema_version":"1.0"},"canonical_sha256":"72d115505e46084acf1ded4f12614a295d0ed4d3af18454cdec0a96daae0a12f","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T05:15:18.102870Z","signature_b64":"VPFsJc8BEr6rRqT/wyfXnrOks0GIWbFhx+vzjGiylbNoIrRpUqDAzzXpvkT/voIxumX+ITVTZ7NEIjYC+FSaAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"72d115505e46084acf1ded4f12614a295d0ed4d3af18454cdec0a96daae0a12f","last_reissued_at":"2026-07-05T05:15:18.102468Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T05:15:18.102468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2211.06193","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":"2026-07-05T05:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hFKyTuEKbkl+XnFBf3P2XdNdl5mXo/1Jz63xTCT9mZdEFPpcIptMS0d70PYKexnhTN7K64SZZM+XPds5vv+8Ag==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:38:42.070188Z"},"content_sha256":"6ed31e3b64ec2097d47d08a38cecd8153c78aedb26a71ffe18d9eb3f015001ef","schema_version":"1.0","event_id":"sha256:6ed31e3b64ec2097d47d08a38cecd8153c78aedb26a71ffe18d9eb3f015001ef"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2022:OLIRKUC6IYEEVTY55VHREYKKFF","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"DocuT5: Seq2seq SQL Generation with Table Documentation","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.CL","authors_text":"Elena Soare, Iain Mackie, Jeffrey Dalton","submitted_at":"2022-11-11T13:31:55Z","abstract_excerpt":"Current SQL generators based on pre-trained language models struggle to answer complex questions requiring domain context or understanding fine-grained table structure. Humans would deal with these unknowns by reasoning over the documentation of the tables. Based on this hypothesis, we propose DocuT5, which uses off-the-shelf language model architecture and injects knowledge from external `documentation' to improve domain generalization. We perform experiments on the Spider family of datasets that contain complex questions that are cross-domain and multi-table. Specifically, we develop a new t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06193","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/2211.06193/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":"2026-07-05T05:15:18Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"5H48v43auZtWZ7b3ppcK3qt2zLC+DEHih0ZUyznsZV8q7rZ4zmz2WcINgLtIVc0nSTNmOUXhgonvZ+09WackDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-18T01:38:42.070712Z"},"content_sha256":"493ff785651c058cff76cc7e6e248aa6330625e28aa14505da913142adb3ea44","schema_version":"1.0","event_id":"sha256:493ff785651c058cff76cc7e6e248aa6330625e28aa14505da913142adb3ea44"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/bundle.json","state_url":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/OLIRKUC6IYEEVTY55VHREYKKFF/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":"2026-08-18T01:38:42Z","links":{"resolver":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF","bundle":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/bundle.json","state":"https://pith.science/pith/OLIRKUC6IYEEVTY55VHREYKKFF/state.json","well_known_bundle":"https://pith.science/.well-known/pith/OLIRKUC6IYEEVTY55VHREYKKFF/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2022:OLIRKUC6IYEEVTY55VHREYKKFF","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":"e74224e9ce58a537f5398354a816b412440df8687f7805f535d2133df4dae78f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T13:31:55Z","title_canon_sha256":"2d65881a06f1797eea5094eeddab998bcb46fa296accafedf91356aae92cc283"},"schema_version":"1.0","source":{"id":"2211.06193","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2211.06193","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"arxiv_version","alias_value":"2211.06193v1","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2211.06193","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_12","alias_value":"OLIRKUC6IYEE","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_16","alias_value":"OLIRKUC6IYEEVTY5","created_at":"2026-07-05T05:15:18Z"},{"alias_kind":"pith_short_8","alias_value":"OLIRKUC6","created_at":"2026-07-05T05:15:18Z"}],"graph_snapshots":[{"event_id":"sha256:493ff785651c058cff76cc7e6e248aa6330625e28aa14505da913142adb3ea44","target":"graph","created_at":"2026-07-05T05:15:18Z","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/2211.06193/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Current SQL generators based on pre-trained language models struggle to answer complex questions requiring domain context or understanding fine-grained table structure. Humans would deal with these unknowns by reasoning over the documentation of the tables. Based on this hypothesis, we propose DocuT5, which uses off-the-shelf language model architecture and injects knowledge from external `documentation' to improve domain generalization. We perform experiments on the Spider family of datasets that contain complex questions that are cross-domain and multi-table. Specifically, we develop a new t","authors_text":"Elena Soare, Iain Mackie, Jeffrey Dalton","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T13:31:55Z","title":"DocuT5: Seq2seq SQL Generation with Table Documentation"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2211.06193","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":"sha256:6ed31e3b64ec2097d47d08a38cecd8153c78aedb26a71ffe18d9eb3f015001ef","target":"record","created_at":"2026-07-05T05:15:18Z","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":"e74224e9ce58a537f5398354a816b412440df8687f7805f535d2133df4dae78f","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.CL","submitted_at":"2022-11-11T13:31:55Z","title_canon_sha256":"2d65881a06f1797eea5094eeddab998bcb46fa296accafedf91356aae92cc283"},"schema_version":"1.0","source":{"id":"2211.06193","kind":"arxiv","version":1}},"canonical_sha256":"72d115505e46084acf1ded4f12614a295d0ed4d3af18454cdec0a96daae0a12f","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"72d115505e46084acf1ded4f12614a295d0ed4d3af18454cdec0a96daae0a12f","first_computed_at":"2026-07-05T05:15:18.102468Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T05:15:18.102468Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"VPFsJc8BEr6rRqT/wyfXnrOks0GIWbFhx+vzjGiylbNoIrRpUqDAzzXpvkT/voIxumX+ITVTZ7NEIjYC+FSaAg==","signature_status":"signed_v1","signed_at":"2026-07-05T05:15:18.102870Z","signed_message":"canonical_sha256_bytes"},"source_id":"2211.06193","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6ed31e3b64ec2097d47d08a38cecd8153c78aedb26a71ffe18d9eb3f015001ef","sha256:493ff785651c058cff76cc7e6e248aa6330625e28aa14505da913142adb3ea44"],"state_sha256":"86c819815230d33c30960eebe4a91d7af87a1a56ea8e941e05825f47953b2e77"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cjDIyu7LWoDX6fQd0YtIJ2K8BOl+9LkYqSeGQ+igWevSI8r6lkdHgqQ2x40EiWvRROgcaoeAQCzlyzapdI6xBg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-18T01:38:42.076233Z","bundle_sha256":"f6b3725f10095fc53ca5fb49af487e4556f61e8b753398c449afe9ceb5f6b4e2"}}