{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IOIYKJ6OGIJ4ZIIN7BQH273WXC","short_pith_number":"pith:IOIYKJ6O","schema_version":"1.0","canonical_sha256":"43918527ce3213cca10df8607d7f76b887d1fec36ed85197ca99dd19bfc7564e","source":{"kind":"arxiv","id":"2605.18383","version":1},"attestation_state":"computed","paper":{"title":"TabH2O: A Unified Foundation Model for Tabular Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Branden Murray, Dmitry Gordeev, Joan Salv\\`a Soler, Laura Fink, Marcos V. Conde, Mark Landry, Mathias M\\\"uller, Pascal Pfeiffer, Sri Satish Ambati","submitted_at":"2026-05-18T13:27:54Z","abstract_excerpt":"We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. TabH2O builds on the TabICL architecture with several key modifications: (1) unified training, a single model handles both classification and regression via a dual-head architecture, eliminating the need for separate models and reducing total pretraining cost; (2) single-stage pretraining, training stability improvements (bounded scalable softmax, inter-stage normalization, learnable residual scaling, logit soft-capping) eliminate the need for mul"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"canonical_record":{"source":{"id":"2605.18383","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-18T13:27:54Z","cross_cats_sorted":[],"title_canon_sha256":"3e655fd713ca3dd2cbc22ead76aa674cd42227a7550e58b8d7b93c2f09773879","abstract_canon_sha256":"56abd40f3f33d2faa4c0bcf737fa01d0c293e09dad013c10c6f0cf1e1ff22971"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:05:58.140965Z","signature_b64":"CqtxPX6nTzEeHunPe48W9bOlZv3fgS9/+i8yGFHIzFKTAZ4nNq5y8xcptktdLZNYASlU0KEPjMqL8BkHwO4zAw==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"43918527ce3213cca10df8607d7f76b887d1fec36ed85197ca99dd19bfc7564e","last_reissued_at":"2026-05-20T00:05:58.140214Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:05:58.140214Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"TabH2O: A Unified Foundation Model for Tabular Prediction","license":"http://creativecommons.org/licenses/by-nc-nd/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Branden Murray, Dmitry Gordeev, Joan Salv\\`a Soler, Laura Fink, Marcos V. Conde, Mark Landry, Mathias M\\\"uller, Pascal Pfeiffer, Sri Satish Ambati","submitted_at":"2026-05-18T13:27:54Z","abstract_excerpt":"We present TabH2O, a foundation model for tabular data that performs classification and regression in a single forward pass via in-context learning. TabH2O builds on the TabICL architecture with several key modifications: (1) unified training, a single model handles both classification and regression via a dual-head architecture, eliminating the need for separate models and reducing total pretraining cost; (2) single-stage pretraining, training stability improvements (bounded scalable softmax, inter-stage normalization, learnable residual scaling, logit soft-capping) eliminate the need for mul"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.18383","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/2605.18383/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"citation_quote_validity","ran_at":"2026-05-19T23:50:04.471371Z","status":"skipped","version":"0.1.0","findings_count":0},{"name":"ai_meta_artifact","ran_at":"2026-05-19T23:33:29.994462Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"external_links","ran_at":"2026-05-19T23:31:46.504162Z","status":"completed","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T23:21:58.755832Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"72ee05ecf3fd66596efe5eb1e63ad7280ba9241a1fce0c1713fe991657b98044"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2605.18383","created_at":"2026-05-20T00:05:58.140336+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.18383v1","created_at":"2026-05-20T00:05:58.140336+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.18383","created_at":"2026-05-20T00:05:58.140336+00:00"},{"alias_kind":"pith_short_12","alias_value":"IOIYKJ6OGIJ4","created_at":"2026-05-20T00:05:58.140336+00:00"},{"alias_kind":"pith_short_16","alias_value":"IOIYKJ6OGIJ4ZIIN","created_at":"2026-05-20T00:05:58.140336+00:00"},{"alias_kind":"pith_short_8","alias_value":"IOIYKJ6O","created_at":"2026-05-20T00:05:58.140336+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC","json":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC.json","graph_json":"https://pith.science/api/pith-number/IOIYKJ6OGIJ4ZIIN7BQH273WXC/graph.json","events_json":"https://pith.science/api/pith-number/IOIYKJ6OGIJ4ZIIN7BQH273WXC/events.json","paper":"https://pith.science/paper/IOIYKJ6O"},"agent_actions":{"view_html":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC","download_json":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC.json","view_paper":"https://pith.science/paper/IOIYKJ6O","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.18383&json=true","fetch_graph":"https://pith.science/api/pith-number/IOIYKJ6OGIJ4ZIIN7BQH273WXC/graph.json","fetch_events":"https://pith.science/api/pith-number/IOIYKJ6OGIJ4ZIIN7BQH273WXC/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC/action/storage_attestation","attest_author":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC/action/author_attestation","sign_citation":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC/action/citation_signature","submit_replication":"https://pith.science/pith/IOIYKJ6OGIJ4ZIIN7BQH273WXC/action/replication_record"}},"created_at":"2026-05-20T00:05:58.140336+00:00","updated_at":"2026-05-20T00:05:58.140336+00:00"}