{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:5AC246MXVXOZO43WACG5GZEYOE","short_pith_number":"pith:5AC246MX","canonical_record":{"source":{"id":"2606.04876","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T13:38:47Z","cross_cats_sorted":[],"title_canon_sha256":"2ab0c60702c94b1a32edba8ccb584a6b171af4bda503f1aaa1b396a0db1412b5","abstract_canon_sha256":"ddb025093c48f91a0b41ee403d40748f16fa435f5c0e7a59d0b47564be5f6edd"},"schema_version":"1.0"},"canonical_sha256":"e805ae7997addd977376008dd36498710432576b317d2767902dfeed73edb868","source":{"kind":"arxiv","id":"2606.04876","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"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:5AC246MXVXOZO43WACG5GZEYOE","target":"record","payload":{"canonical_record":{"source":{"id":"2606.04876","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-03T13:38:47Z","cross_cats_sorted":[],"title_canon_sha256":"2ab0c60702c94b1a32edba8ccb584a6b171af4bda503f1aaa1b396a0db1412b5","abstract_canon_sha256":"ddb025093c48f91a0b41ee403d40748f16fa435f5c0e7a59d0b47564be5f6edd"},"schema_version":"1.0"},"canonical_sha256":"e805ae7997addd977376008dd36498710432576b317d2767902dfeed73edb868","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-04T01:09:52.886335Z","signature_b64":"CCEOEiuWJ7c2w5ZSApfDPc7HpbRQJRB9QUE2xFRKia2+PhOfPN6gfOyGYEcw+WKs8TvTAhBeJHPfrNjVxOz+Ag==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"e805ae7997addd977376008dd36498710432576b317d2767902dfeed73edb868","last_reissued_at":"2026-06-04T01:09:52.885477Z","signature_status":"signed_v1","first_computed_at":"2026-06-04T01:09:52.885477Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2606.04876","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"9oei23V8yvBktdDm8Ag7gWXD5egn6NekUGos8vu4EErXeC1Egd92ew2+APKOfviqfCBwZ/8aKThXaz07CobHAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T14:58:51.470110Z"},"content_sha256":"c472a977db0e8de89d6d27460a8e078e5aac31cd08fae18a7248505529255f54","schema_version":"1.0","event_id":"sha256:c472a977db0e8de89d6d27460a8e078e5aac31cd08fae18a7248505529255f54"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:5AC246MXVXOZO43WACG5GZEYOE","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Pretraining Text Encoders for TabPFN","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Alexander Pfefferle, Frank Hutter, Lennart Purucker, Mustafa Tajjar","submitted_at":"2026-06-03T13:38:47Z","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"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.04876","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/2606.04876/integrity.json","findings":[],"available":true,"detectors_run":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938"},"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"},"verdict_id":null},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-06-04T01:09:52Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"iULEzo8hbmQvC7NdVc7M9wIy0hUF8Yp9m9uzpLIyBjIFexjwQ0tQHb3U/dGuw2WrKrMWyUylI43UhoC+qmZMAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-30T14:58:51.470503Z"},"content_sha256":"1b888d0de00881a2c9dfeb11902db1c875e0961ba7c588dd0728ecc0fd98dea8","schema_version":"1.0","event_id":"sha256:1b888d0de00881a2c9dfeb11902db1c875e0961ba7c588dd0728ecc0fd98dea8"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/5AC246MXVXOZO43WACG5GZEYOE/bundle.json","state_url":"https://pith.science/pith/5AC246MXVXOZO43WACG5GZEYOE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/5AC246MXVXOZO43WACG5GZEYOE/bundle.json","status":"primary"}],"public_keys":[{"key_id":"pith-v1-2026-05","algorithm":"ed25519","format":"raw","public_key_b64":"stVStoiQhXFxp4s2pdzPNoqVNBMojDU/fJ2db5S3CbM=","public_key_hex":"b2d552b68890857171a78b36a5dccf368a953413288c353f7c9d9d6f94b709b3","fingerprint_sha256_b32_first128bits":"RVFV5Z2OI2J3ZUO7ERDEBCYNKS","fingerprint_sha256_hex":"8d4b5ee74e4693bcd1df2446408b0d54","rotates_at":null,"url":"https://pith.science/pith-signing-key.json","notes":"Pith uses this Ed25519 key to sign canonical record SHA-256 digests. Verify with: ed25519_verify(public_key, message=canonical_sha256_bytes, signature=base64decode(signature_b64))."}],"merge_version":"pith-open-graph-merge-v1","built_at":"2026-06-30T14:58:51Z","links":{"resolver":"https://pith.science/pith/5AC246MXVXOZO43WACG5GZEYOE","bundle":"https://pith.science/pith/5AC246MXVXOZO43WACG5GZEYOE/bundle.json","state":"https://pith.science/pith/5AC246MXVXOZO43WACG5GZEYOE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/5AC246MXVXOZO43WACG5GZEYOE/bundle.json"},"state":{"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"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"e7NKR4i/BkdIiPQsLoQtcLwHmeO6f5FuiVOZIPT/DCVySK4fddO8a9C6viG+beri5tnra5yDemXCiPKHdOLtAw==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-30T14:58:51.472432Z","bundle_sha256":"76e2c92f86479f99c7e23d7d3094769df098aa5946eb42d8c43711a5e080f2f1"}}