{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2023:QGDOPDLHJEHDB3PUOHPE7YLJKA","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":"f972365b3683b109a5d54d1bfd4a9c9dc2fab198c90e4a45955e29ae291876b2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T06:03:41Z","title_canon_sha256":"af82cbf992eddbc8c1b6a58073dbf88ae8740333decb2aaf1066bf51c9d32939"},"schema_version":"1.0","source":{"id":"2303.15747","kind":"arxiv","version":4}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2303.15747","created_at":"2026-07-05T06:01:18Z"},{"alias_kind":"arxiv_version","alias_value":"2303.15747v4","created_at":"2026-07-05T06:01:18Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2303.15747","created_at":"2026-07-05T06:01:18Z"},{"alias_kind":"pith_short_12","alias_value":"QGDOPDLHJEHD","created_at":"2026-07-05T06:01:18Z"},{"alias_kind":"pith_short_16","alias_value":"QGDOPDLHJEHDB3PU","created_at":"2026-07-05T06:01:18Z"},{"alias_kind":"pith_short_8","alias_value":"QGDOPDLH","created_at":"2026-07-05T06:01:18Z"}],"graph_snapshots":[{"event_id":"sha256:a22342b7d1567077cc0e8caffc7b7e9f8959c5257f1716772d43b6b2477f8139","target":"graph","created_at":"2026-07-05T06:01:18Z","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/2303.15747/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"We present \\emph{TabRet}, a pre-trainable Transformer-based model for tabular data. TabRet is designed to work on a downstream task that contains columns not seen in pre-training. Unlike other methods, TabRet has an extra learning step before fine-tuning called \\emph{retokenizing}, which calibrates feature embeddings based on the masked autoencoding loss. In experiments, we pre-trained TabRet with a large collection of public health surveys and fine-tuned it on classification tasks in healthcare, and TabRet achieved the best AUC performance on four datasets. In addition, an ablation study show","authors_text":"Kenta Oono, Kohei Hayashi, Soma Onishi","cross_cats":["cs.AI"],"headline":"","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T06:03:41Z","title":"TabRet: Pre-training Transformer-based Tabular Models for Unseen Columns"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2303.15747","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":"sha256:79bf0b97f1f072fd6859d1db89027c0b6d98a63a254c32f015c539bd2787fa5a","target":"record","created_at":"2026-07-05T06:01:18Z","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":"f972365b3683b109a5d54d1bfd4a9c9dc2fab198c90e4a45955e29ae291876b2","cross_cats_sorted":["cs.AI"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2023-03-28T06:03:41Z","title_canon_sha256":"af82cbf992eddbc8c1b6a58073dbf88ae8740333decb2aaf1066bf51c9d32939"},"schema_version":"1.0","source":{"id":"2303.15747","kind":"arxiv","version":4}},"canonical_sha256":"8186e78d67490e30edf471de4fe1695005f7769d795cdcd78b4c9e14f2e2fa7b","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"8186e78d67490e30edf471de4fe1695005f7769d795cdcd78b4c9e14f2e2fa7b","first_computed_at":"2026-07-05T06:01:18.311341Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T06:01:18.311341Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"RUbKIor3lfBfY8z53DtpmX2iHfk91snMar4ueQB0dZhozKtrEmN9ktHhpUiYYRagAAEFonkozsTMDw2qLFnFDw==","signature_status":"signed_v1","signed_at":"2026-07-05T06:01:18.311813Z","signed_message":"canonical_sha256_bytes"},"source_id":"2303.15747","source_kind":"arxiv","source_version":4}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:79bf0b97f1f072fd6859d1db89027c0b6d98a63a254c32f015c539bd2787fa5a","sha256:a22342b7d1567077cc0e8caffc7b7e9f8959c5257f1716772d43b6b2477f8139"],"state_sha256":"d90e77fcb07be388d09490e10f69b4c28f21b417be371c47cc0064f7a83ae78e"}