{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:KYX3QDW73NG3UGGYEXPBXUZT4E","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":"ee2f254f0b1397ae21fca3b81bbfaed8f9db8f7d6d22befd8ac7a3aa8b47b792","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T09:39:07Z","title_canon_sha256":"9a7b89cc342eb194a652beae2352820f310ef9b51820c0482c14cf9bc62a9444"},"schema_version":"1.0","source":{"id":"2507.03971","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.03971","created_at":"2026-07-05T11:32:38Z"},{"alias_kind":"arxiv_version","alias_value":"2507.03971v1","created_at":"2026-07-05T11:32:38Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.03971","created_at":"2026-07-05T11:32:38Z"},{"alias_kind":"pith_short_12","alias_value":"KYX3QDW73NG3","created_at":"2026-07-05T11:32:38Z"},{"alias_kind":"pith_short_16","alias_value":"KYX3QDW73NG3UGGY","created_at":"2026-07-05T11:32:38Z"},{"alias_kind":"pith_short_8","alias_value":"KYX3QDW7","created_at":"2026-07-05T11:32:38Z"}],"graph_snapshots":[{"event_id":"sha256:43a268b179be9a113584c0d3362b49703c09be36bcebdce66d72aa888761fa3e","target":"graph","created_at":"2026-07-05T11:32:38Z","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/2507.03971/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models for tabular data, like TabPFN, achieve strong performance on small datasets when pre-trained solely on synthetic data. We show that this performance can be significantly boosted by a targeted continued pre-training phase. Specifically, we demonstrate that leveraging a small, curated collection of large, real-world datasets for continued pre-training yields superior downstream predictive accuracy compared to using broader, potentially noisier corpora like CommonCrawl or GitTables. Our resulting model, Real-TabPFN, achieves substantial performance gains on 29 datasets from the ","authors_text":"Anurag Garg, Frank Hutter, Lennart Purucker, Muhammad Ali, Noah Hollmann, Samuel M\\\"uller","cross_cats":["cs.AI","stat.ME","stat.ML"],"headline":"","license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T09:39:07Z","title":"Real-TabPFN: Improving Tabular Foundation Models via Continued Pre-training With Real-World Data"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.03971","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:db688a02ce9a1d179b9c1d8807295d273da9eb2719d45ef4df76b4871b16fde7","target":"record","created_at":"2026-07-05T11:32:38Z","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":"ee2f254f0b1397ae21fca3b81bbfaed8f9db8f7d6d22befd8ac7a3aa8b47b792","cross_cats_sorted":["cs.AI","stat.ME","stat.ML"],"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-05T09:39:07Z","title_canon_sha256":"9a7b89cc342eb194a652beae2352820f310ef9b51820c0482c14cf9bc62a9444"},"schema_version":"1.0","source":{"id":"2507.03971","kind":"arxiv","version":1}},"canonical_sha256":"562fb80edfdb4dba18d825de1bd333e1128182fe2fc9d8983a25f35475dc9a4b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"562fb80edfdb4dba18d825de1bd333e1128182fe2fc9d8983a25f35475dc9a4b","first_computed_at":"2026-07-05T11:32:38.217293Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:32:38.217293Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"amc/Rv4lM7Mf6fJUl1xfu7zRxV5bk+Nn2nt8jCc7kLTkp/YxhVmg1ZJkfCYwU8NDSbVB8TkoRC204ZSD++y1Cg==","signature_status":"signed_v1","signed_at":"2026-07-05T11:32:38.218018Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.03971","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:db688a02ce9a1d179b9c1d8807295d273da9eb2719d45ef4df76b4871b16fde7","sha256:43a268b179be9a113584c0d3362b49703c09be36bcebdce66d72aa888761fa3e"],"state_sha256":"fd2bd4632ff0a9fd146540325919d64ee622dc7b92c31936d3aa9330dae3d140"}