{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:5AC246MXVXOZO43WACG5GZEYOE","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":"ddb025093c48f91a0b41ee403d40748f16fa435f5c0e7a59d0b47564be5f6edd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T13:38:47Z","title_canon_sha256":"2ab0c60702c94b1a32edba8ccb584a6b171af4bda503f1aaa1b396a0db1412b5"},"schema_version":"1.0","source":{"id":"2606.04876","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2606.04876","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"arxiv_version","alias_value":"2606.04876v1","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.04876","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"pith_short_12","alias_value":"5AC246MXVXOZ","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"pith_short_16","alias_value":"5AC246MXVXOZO43W","created_at":"2026-06-04T01:09:52Z"},{"alias_kind":"pith_short_8","alias_value":"5AC246MX","created_at":"2026-06-04T01:09:52Z"}],"graph_snapshots":[{"event_id":"sha256:1b888d0de00881a2c9dfeb11902db1c875e0961ba7c588dd0728ecc0fd98dea8","target":"graph","created_at":"2026-06-04T01:09:52Z","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/2606.04876/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Tabular foundation models, such as TabPFN, achieve strong performance on tabular datasets with numerical and categorical data, but do not natively handle high-cardinality text features. Standard pipelines, therefore, embed text with a language model and compress the resulting vectors with PCA into a small number of scalar features before inputting them into TabPFN. This creates an information bottleneck: most embedding dimensions are discarded, and the compressed representation must then be expanded again by TabPFN's feature encoder. End-to-end alternatives can avoid PCA, but they require larg","authors_text":"Alexander Pfefferle, Frank Hutter, Lennart Purucker, Mustafa Tajjar","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T13:38:47Z","title":"Towards Pretraining Text Encoders for TabPFN"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04876","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:c472a977db0e8de89d6d27460a8e078e5aac31cd08fae18a7248505529255f54","target":"record","created_at":"2026-06-04T01:09:52Z","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":"ddb025093c48f91a0b41ee403d40748f16fa435f5c0e7a59d0b47564be5f6edd","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T13:38:47Z","title_canon_sha256":"2ab0c60702c94b1a32edba8ccb584a6b171af4bda503f1aaa1b396a0db1412b5"},"schema_version":"1.0","source":{"id":"2606.04876","kind":"arxiv","version":1}},"canonical_sha256":"e805ae7997addd977376008dd36498710432576b317d2767902dfeed73edb868","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"e805ae7997addd977376008dd36498710432576b317d2767902dfeed73edb868","first_computed_at":"2026-06-04T01:09:52.885477Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-06-04T01:09:52.885477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"CCEOEiuWJ7c2w5ZSApfDPc7HpbRQJRB9QUE2xFRKia2+PhOfPN6gfOyGYEcw+WKs8TvTAhBeJHPfrNjVxOz+Ag==","signature_status":"signed_v1","signed_at":"2026-06-04T01:09:52.886335Z","signed_message":"canonical_sha256_bytes"},"source_id":"2606.04876","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:c472a977db0e8de89d6d27460a8e078e5aac31cd08fae18a7248505529255f54","sha256:1b888d0de00881a2c9dfeb11902db1c875e0961ba7c588dd0728ecc0fd98dea8"],"state_sha256":"9cafa139563807189b0730774553737d07bf5878a478281fd0d01d1d0fbc4f59"}