{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2025:L6M2TAWUQJYQ52XFXXSCQQ4PLB","short_pith_number":"pith:L6M2TAWU","canonical_record":{"source":{"id":"2507.07829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:01:31Z","cross_cats_sorted":[],"title_canon_sha256":"6129ccc1727f7bde29d71256b67aaf0f8252e453ff7760eb3d8515dd3a7f08e8","abstract_canon_sha256":"f9f214beb22de894ce16ca6d8edc8e90f8a7e85d583919fc4a21738ec0b1d1a5"},"schema_version":"1.0"},"canonical_sha256":"5f99a982d482710eeae5bde428438f5869ccef8dd3ab560e48e423f1e0446b98","source":{"kind":"arxiv","id":"2507.07829","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07829","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07829v1","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07829","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_12","alias_value":"L6M2TAWUQJYQ","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_16","alias_value":"L6M2TAWUQJYQ52XF","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_8","alias_value":"L6M2TAWU","created_at":"2026-07-05T11:35:05Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2025:L6M2TAWUQJYQ52XFXXSCQQ4PLB","target":"record","payload":{"canonical_record":{"source":{"id":"2507.07829","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:01:31Z","cross_cats_sorted":[],"title_canon_sha256":"6129ccc1727f7bde29d71256b67aaf0f8252e453ff7760eb3d8515dd3a7f08e8","abstract_canon_sha256":"f9f214beb22de894ce16ca6d8edc8e90f8a7e85d583919fc4a21738ec0b1d1a5"},"schema_version":"1.0"},"canonical_sha256":"5f99a982d482710eeae5bde428438f5869ccef8dd3ab560e48e423f1e0446b98","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:35:05.802793Z","signature_b64":"4/idczDspnNsnEYXfFgVI99GDPt1kv7B7kqWJ6Cujywc3TiZsAvdxmY1PtjU++45Nw94aWvfeBQZKyctxv1HBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5f99a982d482710eeae5bde428438f5869ccef8dd3ab560e48e423f1e0446b98","last_reissued_at":"2026-07-05T11:35:05.802245Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:35:05.802245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2507.07829","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":"2026-07-05T11:35:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"k14JVvztDoOBhdQxztQpoGmrtdnN8btxc0cy+cPcoqE6yTNdAc2GP1g/5EWAqEQ5QbgWXU0Xx09pUMCx4DPvDw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:28:03.842269Z"},"content_sha256":"075c720ab2c7771c985e8ae6793dd2fa48163e9a31f70b772626d9be92f2f0e8","schema_version":"1.0","event_id":"sha256:075c720ab2c7771c985e8ae6793dd2fa48163e9a31f70b772626d9be92f2f0e8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2025:L6M2TAWUQJYQ52XFXXSCQQ4PLB","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"Towards Benchmarking Foundation Models for Tabular Data With Text","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Anshul Gupta, Breenda Das, Frank Hutter, Lennart Purucker, Martin Mr\\'az","submitted_at":"2025-07-10T15:01:31Z","abstract_excerpt":"Foundation models for tabular data are rapidly evolving, with increasing interest in extending them to support additional modalities such as free-text features. However, existing benchmarks for tabular data rarely include textual columns, and identifying real-world tabular datasets with semantically rich text features is non-trivial. We propose a series of simple yet effective ablation-style strategies for incorporating text into conventional tabular pipelines. Moreover, we benchmark how state-of-the-art tabular foundation models can handle textual data by manually curating a collection of rea"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07829","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/2507.07829/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":"2026-07-05T11:35:05Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"hSemwS8keGnDzBf4h7+jHh5INfz0zYMyLcQOnxTi0dGWWWxQA/Lttac1Wg3ZrP6M+ekZ2UJpAucNVx42y6QJAA==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-08-07T21:28:03.842689Z"},"content_sha256":"a08c29754358c4db05994425b742cd4d8c8d8c6cc8ad19ba61c4bce8de405c99","schema_version":"1.0","event_id":"sha256:a08c29754358c4db05994425b742cd4d8c8d8c6cc8ad19ba61c4bce8de405c99"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/bundle.json","state_url":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/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":"2026-08-07T21:28:03Z","links":{"resolver":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB","bundle":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/bundle.json","state":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/state.json","well_known_bundle":"https://pith.science/.well-known/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2025:L6M2TAWUQJYQ52XFXXSCQQ4PLB","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":"f9f214beb22de894ce16ca6d8edc8e90f8a7e85d583919fc4a21738ec0b1d1a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:01:31Z","title_canon_sha256":"6129ccc1727f7bde29d71256b67aaf0f8252e453ff7760eb3d8515dd3a7f08e8"},"schema_version":"1.0","source":{"id":"2507.07829","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2507.07829","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"arxiv_version","alias_value":"2507.07829v1","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07829","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_12","alias_value":"L6M2TAWUQJYQ","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_16","alias_value":"L6M2TAWUQJYQ52XF","created_at":"2026-07-05T11:35:05Z"},{"alias_kind":"pith_short_8","alias_value":"L6M2TAWU","created_at":"2026-07-05T11:35:05Z"}],"graph_snapshots":[{"event_id":"sha256:a08c29754358c4db05994425b742cd4d8c8d8c6cc8ad19ba61c4bce8de405c99","target":"graph","created_at":"2026-07-05T11:35:05Z","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/2507.07829/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"abstract_excerpt":"Foundation models for tabular data are rapidly evolving, with increasing interest in extending them to support additional modalities such as free-text features. However, existing benchmarks for tabular data rarely include textual columns, and identifying real-world tabular datasets with semantically rich text features is non-trivial. We propose a series of simple yet effective ablation-style strategies for incorporating text into conventional tabular pipelines. Moreover, we benchmark how state-of-the-art tabular foundation models can handle textual data by manually curating a collection of rea","authors_text":"Anshul Gupta, Breenda Das, Frank Hutter, Lennart Purucker, Martin Mr\\'az","cross_cats":[],"headline":"","license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:01:31Z","title":"Towards Benchmarking Foundation Models for Tabular Data With Text"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2507.07829","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":"sha256:075c720ab2c7771c985e8ae6793dd2fa48163e9a31f70b772626d9be92f2f0e8","target":"record","created_at":"2026-07-05T11:35:05Z","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":"f9f214beb22de894ce16ca6d8edc8e90f8a7e85d583919fc4a21738ec0b1d1a5","cross_cats_sorted":[],"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-07-10T15:01:31Z","title_canon_sha256":"6129ccc1727f7bde29d71256b67aaf0f8252e453ff7760eb3d8515dd3a7f08e8"},"schema_version":"1.0","source":{"id":"2507.07829","kind":"arxiv","version":1}},"canonical_sha256":"5f99a982d482710eeae5bde428438f5869ccef8dd3ab560e48e423f1e0446b98","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"5f99a982d482710eeae5bde428438f5869ccef8dd3ab560e48e423f1e0446b98","first_computed_at":"2026-07-05T11:35:05.802245Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-07-05T11:35:05.802245Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"4/idczDspnNsnEYXfFgVI99GDPt1kv7B7kqWJ6Cujywc3TiZsAvdxmY1PtjU++45Nw94aWvfeBQZKyctxv1HBQ==","signature_status":"signed_v1","signed_at":"2026-07-05T11:35:05.802793Z","signed_message":"canonical_sha256_bytes"},"source_id":"2507.07829","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:075c720ab2c7771c985e8ae6793dd2fa48163e9a31f70b772626d9be92f2f0e8","sha256:a08c29754358c4db05994425b742cd4d8c8d8c6cc8ad19ba61c4bce8de405c99"],"state_sha256":"88cdd928ef5c846d81296dcc50a0b5d700c3b05497dd662875786266c738787c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"XjgVicAfukUI6QORQiASoMWYYWwvtNQ0SoeAOaMaYz2Fmn+dOwT2LB92bmI4Xzq8lEe9YpMHftjm1eRaUQdNAQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-08-07T21:28:03.845769Z","bundle_sha256":"c7b08390315fba0e2f3a6640defb0b2ce637ac4d979384e17179510db30c9cc8"}}