{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:QXYOWMNLRFPGBLZDUEMGHFDBRD","short_pith_number":"pith:QXYOWMNL","canonical_record":{"source":{"id":"2305.06090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T12:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"3c2ea4c8a38e3715e9de5713bea1ebed191df82195ad195dcc2917dda9a62e6b","abstract_canon_sha256":"eb889e34411d2ac9e95f2991c8413e48d72180fd4395166da9892158b3f8d898"},"schema_version":"1.0"},"canonical_sha256":"85f0eb31ab895e60af23a11863946188ff6c809f390793f1649f8460d98ed0da","source":{"kind":"arxiv","id":"2305.06090","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06090","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06090v1","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06090","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"QXYOWMNLRFPG","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"QXYOWMNLRFPGBLZD","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"QXYOWMNL","created_at":"2026-07-05T06:08:59Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:QXYOWMNLRFPGBLZDUEMGHFDBRD","target":"record","payload":{"canonical_record":{"source":{"id":"2305.06090","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T12:17:52Z","cross_cats_sorted":[],"title_canon_sha256":"3c2ea4c8a38e3715e9de5713bea1ebed191df82195ad195dcc2917dda9a62e6b","abstract_canon_sha256":"eb889e34411d2ac9e95f2991c8413e48d72180fd4395166da9892158b3f8d898"},"schema_version":"1.0"},"canonical_sha256":"85f0eb31ab895e60af23a11863946188ff6c809f390793f1649f8460d98ed0da","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T06:08:59.604894Z","signature_b64":"AT17sgvTC2BnOhV096MhaVmzekQsG7Gd98hfFoXtj+G6dkzSf9h1HxWgq6knvziT2rell8ZEmbuKrtRjFvD0Bw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"85f0eb31ab895e60af23a11863946188ff6c809f390793f1649f8460d98ed0da","last_reissued_at":"2026-07-05T06:08:59.604476Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T06:08:59.604476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.06090","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":"2026-07-05T06:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"Kvjdi7swfGoZMuqt/V6lvJAje2r0/GnLN2BfoCbpjFxaC5IrbvvSKwKQPajuA6+OEPCBghdU5FpX5TIKL0cXAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:04:10.128552Z"},"content_sha256":"f265109ec49c4f88f1f1d8cc1d82607dc38f8b2ebedfbdce142e05abc47bfd66","schema_version":"1.0","event_id":"sha256:f265109ec49c4f88f1f1d8cc1d82607dc38f8b2ebedfbdce142e05abc47bfd66"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:QXYOWMNLRFPGBLZDUEMGHFDBRD","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"XTab: Cross-table Pretraining for Tabular Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bingzhao Zhu, George Karypis, Mahsa Shoaran, Mu Li, Nick Erickson, Xingjian Shi","submitted_at":"2023-05-10T12:17:52Z","abstract_excerpt":"The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data tables and cannot generalize to new tables. In this work, we introduce XTab, a framework for cross-table pretraining of tabular transformers on datasets from various domains. We address the challenge of inconsistent column types and quantities among tables by utilizing independent featurizers and using federated learning to pretrain the shared"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06090","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/2305.06090/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":"2026-07-05T06:08:59Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"cag/sIhf20TBcXObueeQmYNtYtUhmwDEcnj2LvVpWS/V1gigg1Txty9C8/w/WNSKboplCL/+kDY70k7hDyTLCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:04:10.129242Z"},"content_sha256":"916d5d15f694f083f740ad2ca85a1481a2cb1546183944a76ca248a80189915c","schema_version":"1.0","event_id":"sha256:916d5d15f694f083f740ad2ca85a1481a2cb1546183944a76ca248a80189915c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/QXYOWMNLRFPGBLZDUEMGHFDBRD/bundle.json","state_url":"https://pith.science/pith/QXYOWMNLRFPGBLZDUEMGHFDBRD/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/QXYOWMNLRFPGBLZDUEMGHFDBRD/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":"2026-08-10T07:04:10Z","links":{"resolver":"https://pith.science/pith/QXYOWMNLRFPGBLZDUEMGHFDBRD","bundle":"https://pith.science/pith/QXYOWMNLRFPGBLZDUEMGHFDBRD/bundle.json","state":"https://pith.science/pith/QXYOWMNLRFPGBLZDUEMGHFDBRD/state.json","well_known_bundle":"https://pith.science/.well-known/pith/QXYOWMNLRFPGBLZDUEMGHFDBRD/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QXYOWMNLRFPGBLZDUEMGHFDBRD","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":"eb889e34411d2ac9e95f2991c8413e48d72180fd4395166da9892158b3f8d898","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T12:17:52Z","title_canon_sha256":"3c2ea4c8a38e3715e9de5713bea1ebed191df82195ad195dcc2917dda9a62e6b"},"schema_version":"1.0","source":{"id":"2305.06090","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.06090","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"arxiv_version","alias_value":"2305.06090v1","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.06090","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"pith_short_12","alias_value":"QXYOWMNLRFPG","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"pith_short_16","alias_value":"QXYOWMNLRFPGBLZD","created_at":"2026-07-05T06:08:59Z"},{"alias_kind":"pith_short_8","alias_value":"QXYOWMNL","created_at":"2026-07-05T06:08:59Z"}],"graph_snapshots":[{"event_id":"sha256:916d5d15f694f083f740ad2ca85a1481a2cb1546183944a76ca248a80189915c","target":"graph","created_at":"2026-07-05T06:08:59Z","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/2305.06090/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"The success of self-supervised learning in computer vision and natural language processing has motivated pretraining methods on tabular data. However, most existing tabular self-supervised learning models fail to leverage information across multiple data tables and cannot generalize to new tables. In this work, we introduce XTab, a framework for cross-table pretraining of tabular transformers on datasets from various domains. We address the challenge of inconsistent column types and quantities among tables by utilizing independent featurizers and using federated learning to pretrain the shared","authors_text":"Bingzhao Zhu, George Karypis, Mahsa Shoaran, Mu Li, Nick Erickson, Xingjian Shi","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T12:17:52Z","title":"XTab: Cross-table Pretraining for Tabular Transformers"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.06090","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:f265109ec49c4f88f1f1d8cc1d82607dc38f8b2ebedfbdce142e05abc47bfd66","target":"record","created_at":"2026-07-05T06:08:59Z","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":"eb889e34411d2ac9e95f2991c8413e48d72180fd4395166da9892158b3f8d898","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-10T12:17:52Z","title_canon_sha256":"3c2ea4c8a38e3715e9de5713bea1ebed191df82195ad195dcc2917dda9a62e6b"},"schema_version":"1.0","source":{"id":"2305.06090","kind":"arxiv","version":1}},"canonical_sha256":"85f0eb31ab895e60af23a11863946188ff6c809f390793f1649f8460d98ed0da","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"85f0eb31ab895e60af23a11863946188ff6c809f390793f1649f8460d98ed0da","first_computed_at":"2026-07-05T06:08:59.604476Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:08:59.604476Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"AT17sgvTC2BnOhV096MhaVmzekQsG7Gd98hfFoXtj+G6dkzSf9h1HxWgq6knvziT2rell8ZEmbuKrtRjFvD0Bw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:08:59.604894Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.06090","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:f265109ec49c4f88f1f1d8cc1d82607dc38f8b2ebedfbdce142e05abc47bfd66","sha256:916d5d15f694f083f740ad2ca85a1481a2cb1546183944a76ca248a80189915c"],"state_sha256":"d61feebd59bc68d574640ada43378b6dd6e6743e3be6ec58f70b600e2cea7f9d"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"LBb02oQ/EAEMZI2UFUSA5UCySoLuVatSHNxqtUZLmlv0iXxKxCIg4Q2s/79ljOwPMbpNmYQVHL1DuRDRoyeSCw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:04:10.134291Z","bundle_sha256":"6d1876711f9b9e8b1f71505ce6e055b63af5f70f1b8462d5bd412115c0d801b1"}}