{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2021:B4QR64LJ3MCM7AG5SN74QAV57G","short_pith_number":"pith:B4QR64LJ","canonical_record":{"source":{"id":"2107.07653","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-16T00:40:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"295144d8fe348fb327d5694522e31de2109d39ba6e1150b51d143dd0519c25fb","abstract_canon_sha256":"81da3205ab4b19416cfbaa9c7cd79f4e17d8974ddb4aadf4e7b82f3a4ae15d56"},"schema_version":"1.0"},"canonical_sha256":"0f211f7169db04cf80dd937fc802bdf983064c9b019ea8f74b584d233fc96de9","source":{"kind":"arxiv","id":"2107.07653","version":3},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07653","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07653v3","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07653","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"B4QR64LJ3MCM","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"B4QR64LJ3MCM7AG5","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"B4QR64LJ","created_at":"2026-07-05T04:04:40Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2021:B4QR64LJ3MCM7AG5SN74QAV57G","target":"record","payload":{"canonical_record":{"source":{"id":"2107.07653","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-16T00:40:11Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"295144d8fe348fb327d5694522e31de2109d39ba6e1150b51d143dd0519c25fb","abstract_canon_sha256":"81da3205ab4b19416cfbaa9c7cd79f4e17d8974ddb4aadf4e7b82f3a4ae15d56"},"schema_version":"1.0"},"canonical_sha256":"0f211f7169db04cf80dd937fc802bdf983064c9b019ea8f74b584d233fc96de9","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T04:04:40.323088Z","signature_b64":"1Qh461exxdxZVIdtztmjY0yQ4hmxrfJjDmY/kjq/eTPWsR/iW0nRpVrg6ZAnkGXExIk6jF+I2GjMigll7cviCw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"0f211f7169db04cf80dd937fc802bdf983064c9b019ea8f74b584d233fc96de9","last_reissued_at":"2026-07-05T04:04:40.322636Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T04:04:40.322636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2107.07653","source_version":3,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T04:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"b5c6+oqhtqWVHc6fF7mbSd7vQkCRMZlOc7suGdzJYBs5U5nkUTrcj7VsY5BrIByyEM4km48eCpP/MLrWBJLDBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:14:54.638826Z"},"content_sha256":"6c9725e64dd81af2d74e8eb2616c8f9c27f4869ac81aeef066e958926a5b1e21","schema_version":"1.0","event_id":"sha256:6c9725e64dd81af2d74e8eb2616c8f9c27f4869ac81aeef066e958926a5b1e21"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2021:B4QR64LJ3MCM7AG5SN74QAV57G","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.CL","authors_text":"Bei Chen, Jian-Guang Lou, Jiaqi Guo, Morteza Ziyadi, Qian Liu, Weizhu Chen, Zeqi Lin","submitted_at":"2021-07-16T00:40:11Z","abstract_excerpt":"Recent progress in language model pre-training has achieved a great success via leveraging large-scale unstructured textual data. However, it is still a challenge to apply pre-training on structured tabular data due to the absence of large-scale high-quality tabular data. In this paper, we propose TAPEX to show that table pre-training can be achieved by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries and their execution outputs. TAPEX addresses the data scarcity challenge via guiding the language model to mimic a SQ"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07653","kind":"arxiv","version":3},"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/2107.07653/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":"2026-07-05T04:04:40Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"N6jSE40W2ea+Y+viigFrkl1ZCSZJ/Ef9+8rbWiB4eTbC+0ntxGgIwicwgV9Nmvj1F3IAe/PBT0eUtVVpyyk6DQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T06:14:54.639945Z"},"content_sha256":"a5a5cdfe57033368ab3777fb3aa404c3d23987d1530053fb24ff5aea2aab96de","schema_version":"1.0","event_id":"sha256:a5a5cdfe57033368ab3777fb3aa404c3d23987d1530053fb24ff5aea2aab96de"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/B4QR64LJ3MCM7AG5SN74QAV57G/bundle.json","state_url":"https://pith.science/pith/B4QR64LJ3MCM7AG5SN74QAV57G/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/B4QR64LJ3MCM7AG5SN74QAV57G/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":"2026-08-07T06:14:54Z","links":{"resolver":"https://pith.science/pith/B4QR64LJ3MCM7AG5SN74QAV57G","bundle":"https://pith.science/pith/B4QR64LJ3MCM7AG5SN74QAV57G/bundle.json","state":"https://pith.science/pith/B4QR64LJ3MCM7AG5SN74QAV57G/state.json","well_known_bundle":"https://pith.science/.well-known/pith/B4QR64LJ3MCM7AG5SN74QAV57G/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2021:B4QR64LJ3MCM7AG5SN74QAV57G","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":"81da3205ab4b19416cfbaa9c7cd79f4e17d8974ddb4aadf4e7b82f3a4ae15d56","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-16T00:40:11Z","title_canon_sha256":"295144d8fe348fb327d5694522e31de2109d39ba6e1150b51d143dd0519c25fb"},"schema_version":"1.0","source":{"id":"2107.07653","kind":"arxiv","version":3}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2107.07653","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"arxiv_version","alias_value":"2107.07653v3","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2107.07653","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"pith_short_12","alias_value":"B4QR64LJ3MCM","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"pith_short_16","alias_value":"B4QR64LJ3MCM7AG5","created_at":"2026-07-05T04:04:40Z"},{"alias_kind":"pith_short_8","alias_value":"B4QR64LJ","created_at":"2026-07-05T04:04:40Z"}],"graph_snapshots":[{"event_id":"sha256:a5a5cdfe57033368ab3777fb3aa404c3d23987d1530053fb24ff5aea2aab96de","target":"graph","created_at":"2026-07-05T04:04:40Z","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/2107.07653/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent progress in language model pre-training has achieved a great success via leveraging large-scale unstructured textual data. However, it is still a challenge to apply pre-training on structured tabular data due to the absence of large-scale high-quality tabular data. In this paper, we propose TAPEX to show that table pre-training can be achieved by learning a neural SQL executor over a synthetic corpus, which is obtained by automatically synthesizing executable SQL queries and their execution outputs. TAPEX addresses the data scarcity challenge via guiding the language model to mimic a SQ","authors_text":"Bei Chen, Jian-Guang Lou, Jiaqi Guo, Morteza Ziyadi, Qian Liu, Weizhu Chen, Zeqi Lin","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-16T00:40:11Z","title":"TAPEX: Table Pre-training via Learning a Neural SQL Executor"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2107.07653","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":"sha256:6c9725e64dd81af2d74e8eb2616c8f9c27f4869ac81aeef066e958926a5b1e21","target":"record","created_at":"2026-07-05T04:04:40Z","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":"81da3205ab4b19416cfbaa9c7cd79f4e17d8974ddb4aadf4e7b82f3a4ae15d56","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.CL","submitted_at":"2021-07-16T00:40:11Z","title_canon_sha256":"295144d8fe348fb327d5694522e31de2109d39ba6e1150b51d143dd0519c25fb"},"schema_version":"1.0","source":{"id":"2107.07653","kind":"arxiv","version":3}},"canonical_sha256":"0f211f7169db04cf80dd937fc802bdf983064c9b019ea8f74b584d233fc96de9","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"0f211f7169db04cf80dd937fc802bdf983064c9b019ea8f74b584d233fc96de9","first_computed_at":"2026-07-05T04:04:40.322636Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T04:04:40.322636Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"1Qh461exxdxZVIdtztmjY0yQ4hmxrfJjDmY/kjq/eTPWsR/iW0nRpVrg6ZAnkGXExIk6jF+I2GjMigll7cviCw==","signature_status":"signed_v1","signed_at":"2026-07-05T04:04:40.323088Z","signed_message":"canonical_sha256_bytes"},"source_id":"2107.07653","source_kind":"arxiv","source_version":3}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:6c9725e64dd81af2d74e8eb2616c8f9c27f4869ac81aeef066e958926a5b1e21","sha256:a5a5cdfe57033368ab3777fb3aa404c3d23987d1530053fb24ff5aea2aab96de"],"state_sha256":"dbe0e4bdbbc582c68bb9d4ccc00117866e10281c3c43606075b089ccf83b1105"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"MOvYWqBq1TtyXSFVal2jaKJChBoHUrL9K1aIwARy0alZD1BU8f58PYrftTzfQOJk+Y78ZUdgb7/oeWB+3ZuTBQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T06:14:54.651194Z","bundle_sha256":"04cb6621b168937560628c4374ca096f40e3f6b8373a3803b9e82f756c1070f9"}}