{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2023:ZHFT2RLLWB2CZZONJULJ5S5HTC","short_pith_number":"pith:ZHFT2RLL","canonical_record":{"source":{"id":"2305.12081","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T03:37:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"622913d11aa63f40a638c5986098d5984d6e01f13432bfa4480738910a8b63cb","abstract_canon_sha256":"8ca26eccae3cc3415360d108ca62d0d68df72d3c964fb9b073c172ac0f3a24e3"},"schema_version":"1.0"},"canonical_sha256":"c9cb3d456bb0742ce5cd4d169ecba798860da80ddaae9643e8d36c2a66d7c28e","source":{"kind":"arxiv","id":"2305.12081","version":4},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12081","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12081v4","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12081","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZHFT2RLLWB2C","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZHFT2RLLWB2CZZON","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZHFT2RLL","created_at":"2026-07-05T08:13:58Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2023:ZHFT2RLLWB2CZZONJULJ5S5HTC","target":"record","payload":{"canonical_record":{"source":{"id":"2305.12081","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T03:37:09Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"622913d11aa63f40a638c5986098d5984d6e01f13432bfa4480738910a8b63cb","abstract_canon_sha256":"8ca26eccae3cc3415360d108ca62d0d68df72d3c964fb9b073c172ac0f3a24e3"},"schema_version":"1.0"},"canonical_sha256":"c9cb3d456bb0742ce5cd4d169ecba798860da80ddaae9643e8d36c2a66d7c28e","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:13:58.936215Z","signature_b64":"tCyNkQZkO09KH0qtrpezfguxHVvp7p9c4f2zawGTMayqKzpd+9OU+AhtpU4gaRs9Bf8NZH3oiOX8Ft2qylX7AQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"c9cb3d456bb0742ce5cd4d169ecba798860da80ddaae9643e8d36c2a66d7c28e","last_reissued_at":"2026-07-05T08:13:58.935797Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:13:58.935797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2305.12081","source_version":4,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-07-05T08:13:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"aiel+8/gK2+/fDbxhRmBkRzsbd5zASdWXKNEqv8tXommIjPA2FKGQ8Z1KAytA/8NOo+WNqOs/dfFJFZ995UFBA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:50:43.763065Z"},"content_sha256":"925822934562545a403692bd58ea1a818a56cf10eea63749e73fd7ed44afd346","schema_version":"1.0","event_id":"sha256:925822934562545a403692bd58ea1a818a56cf10eea63749e73fd7ed44afd346"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2023:ZHFT2RLLWB2CZZONJULJ5S5HTC","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Cao Xiao, Chufan Gao, Jimeng Sun, Zifeng Wang","submitted_at":"2023-05-20T03:37:09Z","abstract_excerpt":"Tabular data prediction has been employed in medical applications such as patient health risk prediction. However, existing methods usually revolve around the algorithm design while overlooking the significance of data engineering. Medical tabular datasets frequently exhibit significant heterogeneity across different sources, with limited sample sizes per source. As such, previous predictors are often trained on manually curated small datasets that struggle to generalize across different tabular datasets during inference. This paper proposes to scale medical tabular data predictors (MediTab) t"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12081","kind":"arxiv","version":4},"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/2305.12081/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":"2026-07-05T08:13:58Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"8Uq2Ee9Dl0OyqfZfGJtPMzymXO7q+0DuLZptT935cyLq1BhZuPm60EoU/1ba2R/7xyDS94c97S+7fElTKg4cCw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-10T07:50:43.764286Z"},"content_sha256":"7f70d5f611bd25468209ad120b5d78cf130b7dbce094fff120d35deb3fc96d2c","schema_version":"1.0","event_id":"sha256:7f70d5f611bd25468209ad120b5d78cf130b7dbce094fff120d35deb3fc96d2c"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/ZHFT2RLLWB2CZZONJULJ5S5HTC/bundle.json","state_url":"https://pith.science/pith/ZHFT2RLLWB2CZZONJULJ5S5HTC/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/ZHFT2RLLWB2CZZONJULJ5S5HTC/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":"2026-08-10T07:50:43Z","links":{"resolver":"https://pith.science/pith/ZHFT2RLLWB2CZZONJULJ5S5HTC","bundle":"https://pith.science/pith/ZHFT2RLLWB2CZZONJULJ5S5HTC/bundle.json","state":"https://pith.science/pith/ZHFT2RLLWB2CZZONJULJ5S5HTC/state.json","well_known_bundle":"https://pith.science/.well-known/pith/ZHFT2RLLWB2CZZONJULJ5S5HTC/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:ZHFT2RLLWB2CZZONJULJ5S5HTC","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":"8ca26eccae3cc3415360d108ca62d0d68df72d3c964fb9b073c172ac0f3a24e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T03:37:09Z","title_canon_sha256":"622913d11aa63f40a638c5986098d5984d6e01f13432bfa4480738910a8b63cb"},"schema_version":"1.0","source":{"id":"2305.12081","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2305.12081","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"arxiv_version","alias_value":"2305.12081v4","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2305.12081","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"pith_short_12","alias_value":"ZHFT2RLLWB2C","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"pith_short_16","alias_value":"ZHFT2RLLWB2CZZON","created_at":"2026-07-05T08:13:58Z"},{"alias_kind":"pith_short_8","alias_value":"ZHFT2RLL","created_at":"2026-07-05T08:13:58Z"}],"graph_snapshots":[{"event_id":"sha256:7f70d5f611bd25468209ad120b5d78cf130b7dbce094fff120d35deb3fc96d2c","target":"graph","created_at":"2026-07-05T08:13:58Z","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/2305.12081/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular data prediction has been employed in medical applications such as patient health risk prediction. However, existing methods usually revolve around the algorithm design while overlooking the significance of data engineering. Medical tabular datasets frequently exhibit significant heterogeneity across different sources, with limited sample sizes per source. As such, previous predictors are often trained on manually curated small datasets that struggle to generalize across different tabular datasets during inference. This paper proposes to scale medical tabular data predictors (MediTab) t","authors_text":"Cao Xiao, Chufan Gao, Jimeng Sun, Zifeng Wang","cross_cats":["cs.AI"],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T03:37:09Z","title":"MediTab: Scaling Medical Tabular Data Predictors via Data Consolidation, Enrichment, and Refinement"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2305.12081","kind":"arxiv","version":4},"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":"sha256:925822934562545a403692bd58ea1a818a56cf10eea63749e73fd7ed44afd346","target":"record","created_at":"2026-07-05T08:13:58Z","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":"8ca26eccae3cc3415360d108ca62d0d68df72d3c964fb9b073c172ac0f3a24e3","cross_cats_sorted":["cs.AI"],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2023-05-20T03:37:09Z","title_canon_sha256":"622913d11aa63f40a638c5986098d5984d6e01f13432bfa4480738910a8b63cb"},"schema_version":"1.0","source":{"id":"2305.12081","kind":"arxiv","version":4}},"canonical_sha256":"c9cb3d456bb0742ce5cd4d169ecba798860da80ddaae9643e8d36c2a66d7c28e","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"c9cb3d456bb0742ce5cd4d169ecba798860da80ddaae9643e8d36c2a66d7c28e","first_computed_at":"2026-07-05T08:13:58.935797Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T08:13:58.935797Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"tCyNkQZkO09KH0qtrpezfguxHVvp7p9c4f2zawGTMayqKzpd+9OU+AhtpU4gaRs9Bf8NZH3oiOX8Ft2qylX7AQ==","signature_status":"signed_v1","signed_at":"2026-07-05T08:13:58.936215Z","signed_message":"canonical_sha256_bytes"},"source_id":"2305.12081","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:925822934562545a403692bd58ea1a818a56cf10eea63749e73fd7ed44afd346","sha256:7f70d5f611bd25468209ad120b5d78cf130b7dbce094fff120d35deb3fc96d2c"],"state_sha256":"3cb4e5459c4de937f6387e5d98a5a4187cea1ca728d302f33947f47db83910b8"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9VuIyCM0ktIOxaFgIFoHQ84N33iZGY7mQvh+HfVPzSA6nPpoNrcMj1FdDRq1bdvbai0Y0l+XXeFjIgvwYUBZDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-10T07:50:43.771511Z","bundle_sha256":"df007a20d185418ce66bd633633c844e265ef833b46c76f4190b11ef1b2e7948"}}