{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:MFL2F3OFKWZRFDBCI5ZKJIM43N","short_pith_number":"pith:MFL2F3OF","schema_version":"1.0","canonical_sha256":"6157a2edc555b3128c224772a4a19cdb5a1dc26f334efc72768686ce1af25953","source":{"kind":"arxiv","id":"2412.05218","version":1},"attestation_state":"computed","paper":{"title":"Transformers Meet Relational Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Gustav \\v{S}\\'ir, Jakub Pele\\v{s}ka","submitted_at":"2024-12-06T17:48:43Z","abstract_excerpt":"Transformer models have continuously expanded into all machine learning domains convertible to the underlying sequence-to-sequence representation, including tabular data. However, while ubiquitous, this representation restricts their extension to the more general case of relational databases. In this paper, we introduce a modular neural message-passing scheme that closely adheres to the formal relational model, enabling direct end-to-end learning of tabular Transformers from database storage systems. We address the challenges of appropriate learning data representation and loading, which are c"},"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":"2412.05218","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-12-06T17:48:43Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"1b41e327b6fb6981136a04209d3cb76c7d1efac37aefba6b10c9d5d93964c4a6","abstract_canon_sha256":"0e8c8163155ae3d9d6de993640dfd709c71bf3bfc818f4f6613ef74354941cd3"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:41:37.014094Z","signature_b64":"/izDas5zI4Vx23JPHuxAtivGH8DhVZw8pjBLuZtcdikDTF0wGa7y3cP+s1WnUY6+JS7UxCMh44Er7rDZsBkTAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6157a2edc555b3128c224772a4a19cdb5a1dc26f334efc72768686ce1af25953","last_reissued_at":"2026-07-05T11:41:37.013634Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:41:37.013634Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Transformers Meet Relational Databases","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Gustav \\v{S}\\'ir, Jakub Pele\\v{s}ka","submitted_at":"2024-12-06T17:48:43Z","abstract_excerpt":"Transformer models have continuously expanded into all machine learning domains convertible to the underlying sequence-to-sequence representation, including tabular data. However, while ubiquitous, this representation restricts their extension to the more general case of relational databases. In this paper, we introduce a modular neural message-passing scheme that closely adheres to the formal relational model, enabling direct end-to-end learning of tabular Transformers from database storage systems. We address the challenges of appropriate learning data representation and loading, which are c"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2412.05218","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/2412.05218/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":"2412.05218","created_at":"2026-07-05T11:41:37.013692+00:00"},{"alias_kind":"arxiv_version","alias_value":"2412.05218v1","created_at":"2026-07-05T11:41:37.013692+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2412.05218","created_at":"2026-07-05T11:41:37.013692+00:00"},{"alias_kind":"pith_short_12","alias_value":"MFL2F3OFKWZR","created_at":"2026-07-05T11:41:37.013692+00:00"},{"alias_kind":"pith_short_16","alias_value":"MFL2F3OFKWZRFDBC","created_at":"2026-07-05T11:41:37.013692+00:00"},{"alias_kind":"pith_short_8","alias_value":"MFL2F3OF","created_at":"2026-07-05T11:41:37.013692+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":3,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2606.03040","citing_title":"RelGT-AC: A Relational Graph Transformer for Autocomplete Tasks in Relational Databases","ref_index":29,"is_internal_anchor":false},{"citing_arxiv_id":"2602.12606","citing_title":"RelBench v2: A Large-Scale Benchmark and Repository for Relational Data","ref_index":10,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14464","citing_title":"From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics","ref_index":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N","json":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N.json","graph_json":"https://pith.science/api/pith-number/MFL2F3OFKWZRFDBCI5ZKJIM43N/graph.json","events_json":"https://pith.science/api/pith-number/MFL2F3OFKWZRFDBCI5ZKJIM43N/events.json","paper":"https://pith.science/paper/MFL2F3OF"},"agent_actions":{"view_html":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N","download_json":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N.json","view_paper":"https://pith.science/paper/MFL2F3OF","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2412.05218&json=true","fetch_graph":"https://pith.science/api/pith-number/MFL2F3OFKWZRFDBCI5ZKJIM43N/graph.json","fetch_events":"https://pith.science/api/pith-number/MFL2F3OFKWZRFDBCI5ZKJIM43N/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N/action/timestamp_anchor","attest_storage":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N/action/storage_attestation","attest_author":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N/action/author_attestation","sign_citation":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N/action/citation_signature","submit_replication":"https://pith.science/pith/MFL2F3OFKWZRFDBCI5ZKJIM43N/action/replication_record"}},"created_at":"2026-07-05T11:41:37.013692+00:00","updated_at":"2026-07-05T11:41:37.013692+00:00"}