{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:L6M2TAWUQJYQ52XFXXSCQQ4PLB","short_pith_number":"pith:L6M2TAWU","schema_version":"1.0","canonical_sha256":"5f99a982d482710eeae5bde428438f5869ccef8dd3ab560e48e423f1e0446b98","source":{"kind":"arxiv","id":"2507.07829","version":1},"attestation_state":"computed","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"},"verification_status":{"content_addressed":true,"pith_receipt":true,"author_attested":false,"weak_author_claims":0,"strong_author_claims":0,"externally_anchored":false,"storage_verified":false,"citation_signatures":0,"replication_records":0,"graph_snapshot":true,"references_resolved":false,"formal_links_present":false},"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"},"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"},"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"},"aliases":[{"alias_kind":"arxiv","alias_value":"2507.07829","created_at":"2026-07-05T11:35:05.802302+00:00"},{"alias_kind":"arxiv_version","alias_value":"2507.07829v1","created_at":"2026-07-05T11:35:05.802302+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2507.07829","created_at":"2026-07-05T11:35:05.802302+00:00"},{"alias_kind":"pith_short_12","alias_value":"L6M2TAWUQJYQ","created_at":"2026-07-05T11:35:05.802302+00:00"},{"alias_kind":"pith_short_16","alias_value":"L6M2TAWUQJYQ52XF","created_at":"2026-07-05T11:35:05.802302+00:00"},{"alias_kind":"pith_short_8","alias_value":"L6M2TAWU","created_at":"2026-07-05T11:35:05.802302+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.30452","citing_title":"Exploring Differences Between Tabular Enterprise Data and Public Benchmarks","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2606.30410","citing_title":"Beyond IID: How General Are Tabular Foundation Models, Really?","ref_index":16,"is_internal_anchor":false},{"citing_arxiv_id":"2605.12292","citing_title":"STRABLE: Benchmarking Tabular Machine Learning with Strings","ref_index":42,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB","json":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB.json","graph_json":"https://pith.science/api/pith-number/L6M2TAWUQJYQ52XFXXSCQQ4PLB/graph.json","events_json":"https://pith.science/api/pith-number/L6M2TAWUQJYQ52XFXXSCQQ4PLB/events.json","paper":"https://pith.science/paper/L6M2TAWU"},"agent_actions":{"view_html":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB","download_json":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB.json","view_paper":"https://pith.science/paper/L6M2TAWU","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2507.07829&json=true","fetch_graph":"https://pith.science/api/pith-number/L6M2TAWUQJYQ52XFXXSCQQ4PLB/graph.json","fetch_events":"https://pith.science/api/pith-number/L6M2TAWUQJYQ52XFXXSCQQ4PLB/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/action/timestamp_anchor","attest_storage":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/action/storage_attestation","attest_author":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/action/author_attestation","sign_citation":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/action/citation_signature","submit_replication":"https://pith.science/pith/L6M2TAWUQJYQ52XFXXSCQQ4PLB/action/replication_record"}},"created_at":"2026-07-05T11:35:05.802302+00:00","updated_at":"2026-07-05T11:35:05.802302+00:00"}