{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:UZ7RYJ7VSW372LFTVSQREDASUE","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":"d79e252c6fdc89ba1b3d2d3a6b72ac738a75b3b591c57449fe82a384b3ac0d0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T14:45:05Z","title_canon_sha256":"bbdfcea8e50730105125de843bc84b485d4156e5450a2acf3a8892b68a2d0046"},"schema_version":"1.0","source":{"id":"2605.28554","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.28554","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"arxiv_version","alias_value":"2605.28554v1","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.28554","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"pith_short_12","alias_value":"UZ7RYJ7VSW37","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"pith_short_16","alias_value":"UZ7RYJ7VSW372LFT","created_at":"2026-05-28T02:04:56Z"},{"alias_kind":"pith_short_8","alias_value":"UZ7RYJ7V","created_at":"2026-05-28T02:04:56Z"}],"graph_snapshots":[{"event_id":"sha256:d5af597d3d548ab2e6c2c32e58d24fd13898ce245eeb04ed548d67479fbb96c5","target":"graph","created_at":"2026-05-28T02:04:56Z","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/2605.28554/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Recent Tabular Foundation Models (TFMs) have demonstrated state-of-the-art predictive performance, often surpassing Gradient-Boosted Decision Trees (GBDTs). However, the trustworthiness of these models, particularly their uncertainty quantification, has been largely overlooked. We investigate this gap through an extensive study comparing TFMs, GBDTs, and classical baselines on the 112 datasets of the TALENT benchmark. Our results reveal a performance-uncertainty trade-off: although TFMs achieve the highest predictive performance, measured by AUC, they exhibit lower conditional coverage under c","authors_text":"Arpad Rimmel, Bich-Li\\^en Doan, Fabrice Popineau, Jos\\'e Lucas De Melo Costa","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T14:45:05Z","title":"High Performance, Low Reliability: Uncertainty Benchmarking for Tabular Foundation Models"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.28554","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:bb65a8e5271d21a81721e1428025ef61574d3d07bc4ef125db41b69594ca1e7e","target":"record","created_at":"2026-05-28T02:04:56Z","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":"d79e252c6fdc89ba1b3d2d3a6b72ac738a75b3b591c57449fe82a384b3ac0d0e","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-27T14:45:05Z","title_canon_sha256":"bbdfcea8e50730105125de843bc84b485d4156e5450a2acf3a8892b68a2d0046"},"schema_version":"1.0","source":{"id":"2605.28554","kind":"arxiv","version":1}},"canonical_sha256":"a67f1c27f595b7fd2cb3aca1120c12a1002b57c3d157e989c89c326839df85c7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"a67f1c27f595b7fd2cb3aca1120c12a1002b57c3d157e989c89c326839df85c7","first_computed_at":"2026-05-28T02:04:56.228156Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-28T02:04:56.228156Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"ulV4iGDO9sPZS29xo90OlEu7qXJoUhXnvvWclxLy1xzOVdqWE3RcDTdOUzF5LIZVtr3MJ3iOFqU9s4MQtpjkDA==","signature_status":"signed_v1","signed_at":"2026-05-28T02:04:56.228696Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.28554","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:bb65a8e5271d21a81721e1428025ef61574d3d07bc4ef125db41b69594ca1e7e","sha256:d5af597d3d548ab2e6c2c32e58d24fd13898ce245eeb04ed548d67479fbb96c5"],"state_sha256":"360d3c1a9016d74e61dba25e767772eb90a2b94c24c65f1fdb9e000bfb8e8b0c"}