{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:IJDPRBA2GMVLASLUZCQ53GSJAW","short_pith_number":"pith:IJDPRBA2","schema_version":"1.0","canonical_sha256":"4246f8841a332ab04974c8a1dd9a49059ecfa0fdaa3ba2a34d3c8e818f5cb5a7","source":{"kind":"arxiv","id":"2606.02106","version":1},"attestation_state":"computed","paper":{"title":"When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Julien Lafrance","submitted_at":"2026-06-01T11:36:20Z","abstract_excerpt":"We present a single classification pipeline that combines an Equiangular Tight Frame (ETF) preprocessing stage with a tabular foundation model for in-context inference, applied identically across modalities once data is mapped to fixed vector representations. We evaluate it on 95 datasets spanning seven signal modalities -- vision, audio, speech, text, molecular, time-series, and tabular. The main methodological contribution is to fix the comparison object: throughout the paper, performance is judged against the strongest lightweight tuned baseline on the same frozen features, while oracle sel"},"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":"2606.02106","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-06-01T11:36:20Z","cross_cats_sorted":["stat.ML"],"title_canon_sha256":"e849cd43ed3b8b7b7bc6a691f3c22bb5d5410385f40b3becd58a1f85d2ef8d2a","abstract_canon_sha256":"21cc6764993f4e5d96087da41bd815e55ca62eba5cd1a3958eb0b48a14101b1c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-02T02:05:06.644763Z","signature_b64":"B1eTxtJhe4iSlh0wcuyGs7rmfwHAUm3OkRFx83jDJCTDKKAoYZ2U14OkExkFS1acBATeMi1W4LDMm5a4/awuDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4246f8841a332ab04974c8a1dd9a49059ecfa0fdaa3ba2a34d3c8e818f5cb5a7","last_reissued_at":"2026-06-02T02:05:06.644390Z","signature_status":"signed_v1","first_computed_at":"2026-06-02T02:05:06.644390Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"When Tabular Foundation Models Transfer Across Modalities: A Systematic Evaluation Across 95 Datasets, 7 Modalities, and Two Regimes","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["stat.ML"],"primary_cat":"cs.LG","authors_text":"Julien Lafrance","submitted_at":"2026-06-01T11:36:20Z","abstract_excerpt":"We present a single classification pipeline that combines an Equiangular Tight Frame (ETF) preprocessing stage with a tabular foundation model for in-context inference, applied identically across modalities once data is mapped to fixed vector representations. We evaluate it on 95 datasets spanning seven signal modalities -- vision, audio, speech, text, molecular, time-series, and tabular. The main methodological contribution is to fix the comparison object: throughout the paper, performance is judged against the strongest lightweight tuned baseline on the same frozen features, while oracle sel"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2606.02106","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/2606.02106/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":"2606.02106","created_at":"2026-06-02T02:05:06.644447+00:00"},{"alias_kind":"arxiv_version","alias_value":"2606.02106v1","created_at":"2026-06-02T02:05:06.644447+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2606.02106","created_at":"2026-06-02T02:05:06.644447+00:00"},{"alias_kind":"pith_short_12","alias_value":"IJDPRBA2GMVL","created_at":"2026-06-02T02:05:06.644447+00:00"},{"alias_kind":"pith_short_16","alias_value":"IJDPRBA2GMVLASLU","created_at":"2026-06-02T02:05:06.644447+00:00"},{"alias_kind":"pith_short_8","alias_value":"IJDPRBA2","created_at":"2026-06-02T02:05:06.644447+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW","json":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW.json","graph_json":"https://pith.science/api/pith-number/IJDPRBA2GMVLASLUZCQ53GSJAW/graph.json","events_json":"https://pith.science/api/pith-number/IJDPRBA2GMVLASLUZCQ53GSJAW/events.json","paper":"https://pith.science/paper/IJDPRBA2"},"agent_actions":{"view_html":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW","download_json":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW.json","view_paper":"https://pith.science/paper/IJDPRBA2","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2606.02106&json=true","fetch_graph":"https://pith.science/api/pith-number/IJDPRBA2GMVLASLUZCQ53GSJAW/graph.json","fetch_events":"https://pith.science/api/pith-number/IJDPRBA2GMVLASLUZCQ53GSJAW/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW/action/timestamp_anchor","attest_storage":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW/action/storage_attestation","attest_author":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW/action/author_attestation","sign_citation":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW/action/citation_signature","submit_replication":"https://pith.science/pith/IJDPRBA2GMVLASLUZCQ53GSJAW/action/replication_record"}},"created_at":"2026-06-02T02:05:06.644447+00:00","updated_at":"2026-06-02T02:05:06.644447+00:00"}