{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:3CQNCPBCK23WGCDBZTHTS5PACE","short_pith_number":"pith:3CQNCPBC","schema_version":"1.0","canonical_sha256":"d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910","source":{"kind":"arxiv","id":"2603.03805","version":5},"attestation_state":"computed","paper":{"title":"Relational In-Context Learning via Synthetic Pre-training with Structural Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RDB-PFN learns relational in-context adaptation by pre-training a transformer solely on millions of synthetic databases generated from structural causal models.","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Jiaxuan You, Muhan Zhang, Yanbo Wang","submitted_at":"2026-03-04T07:30:54Z","abstract_excerpt":"Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce, and structurally heterogeneous, making internet-scale pre-training infeasible. To overcome this data scarcity, we introduce RDB-PFN, the first relational foundation model trained purely via synthetic data. Inspired by Prior-Data Fitted Networks (PFNs), where synthetic data generated from Structural Causal Models (SCMs) enables reasoning on single tables, we design a Relational Prior Generator to cre"},"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":true},"canonical_record":{"source":{"id":"2603.03805","kind":"arxiv","version":5},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-04T07:30:54Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"6b2d0b6c0534919e143fbb24c06c8e79384c4a5631a179660dc1590a63661671","abstract_canon_sha256":"94a47104e96c7ca2618d190a88fae53f276106d69b4f03f2a42d5898eb812177"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-29T02:05:42.288569Z","signature_b64":"Zz5fj8Qc0OSZ8KSlY1/N1m5HVLm1JYFCJSF6j9k0EVuU8yShuweerzY3XIhHlfwLO4pxhWnjTmjrFPV4fbBjCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910","last_reissued_at":"2026-05-29T02:05:42.287875Z","signature_status":"signed_v1","first_computed_at":"2026-05-29T02:05:42.287875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Relational In-Context Learning via Synthetic Pre-training with Structural Prior","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RDB-PFN learns relational in-context adaptation by pre-training a transformer solely on millions of synthetic databases generated from structural causal models.","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Jiaxuan You, Muhan Zhang, Yanbo Wang","submitted_at":"2026-03-04T07:30:54Z","abstract_excerpt":"Relational Databases (RDBs) are the backbone of modern business, yet they lack foundation models comparable to those in text or vision. A key obstacle is that high-quality RDBs are private, scarce, and structurally heterogeneous, making internet-scale pre-training infeasible. To overcome this data scarcity, we introduce RDB-PFN, the first relational foundation model trained purely via synthetic data. Inspired by Prior-Data Fitted Networks (PFNs), where synthetic data generated from Structural Causal Models (SCMs) enables reasoning on single tables, we design a Relational Prior Generator to cre"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"RDB-PFN achieves strong few-shot performance on 19 real-world relational prediction tasks, outperforming graph-based and single-table foundation-model baselines (given the same DFS-linearized inputs), while using a lightweight architecture and fast inference.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"Synthetic relational databases generated by the Relational Prior Generator from Structural Causal Models sufficiently capture the structural heterogeneity, join patterns, and statistical properties of real-world RDBs to support generalization to actual tasks.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RDB-PFN is a relational foundation model pre-trained on over 2 million synthetic RDB tasks that achieves strong few-shot performance on 19 real-world relational prediction tasks via in-context learning.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RDB-PFN learns relational in-context adaptation by pre-training a transformer solely on millions of synthetic databases generated from structural causal models.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"731a49ddb63e75d60ae7f450fa896cbc87a63ffad9506e086d806e561857c4c0"},"source":{"id":"2603.03805","kind":"arxiv","version":5},"verdict":{"id":"15c12862-40cd-43e1-ba34-e4111618b7d7","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T16:54:03.121535Z","strongest_claim":"RDB-PFN achieves strong few-shot performance on 19 real-world relational prediction tasks, outperforming graph-based and single-table foundation-model baselines (given the same DFS-linearized inputs), while using a lightweight architecture and fast inference.","one_line_summary":"RDB-PFN is a relational foundation model pre-trained on over 2 million synthetic RDB tasks that achieves strong few-shot performance on 19 real-world relational prediction tasks via in-context learning.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"Synthetic relational databases generated by the Relational Prior Generator from Structural Causal Models sufficiently capture the structural heterogeneity, join patterns, and statistical properties of real-world RDBs to support generalization to actual tasks.","pith_extraction_headline":"RDB-PFN learns relational in-context adaptation by pre-training a transformer solely on millions of synthetic databases generated from structural causal models."},"integrity":{"clean":true,"summary":{"advisory":0,"critical":0,"by_detector":{},"informational":0},"endpoint":"/pith/2603.03805/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":2,"snapshot_sha256":"0061bd0a8b837f3790f2ef59463bafa6c7978bf7d4531bada606f0242f22c935"},"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":"2603.03805","created_at":"2026-05-29T02:05:42.287977+00:00"},{"alias_kind":"arxiv_version","alias_value":"2603.03805v5","created_at":"2026-05-29T02:05:42.287977+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03805","created_at":"2026-05-29T02:05:42.287977+00:00"},{"alias_kind":"pith_short_12","alias_value":"3CQNCPBCK23W","created_at":"2026-05-29T02:05:42.287977+00:00"},{"alias_kind":"pith_short_16","alias_value":"3CQNCPBCK23WGCDB","created_at":"2026-05-29T02:05:42.287977+00:00"},{"alias_kind":"pith_short_8","alias_value":"3CQNCPBC","created_at":"2026-05-29T02:05:42.287977+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.18971","citing_title":"Shaping the Prior: How Synthetic Task Distributions Determine Tabular Foundation Model Quality","ref_index":35,"is_internal_anchor":true},{"citing_arxiv_id":"2604.12596","citing_title":"KumoRFM-2: Scaling Foundation Models for Relational Learning","ref_index":13,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":2,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE","json":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE.json","graph_json":"https://pith.science/api/pith-number/3CQNCPBCK23WGCDBZTHTS5PACE/graph.json","events_json":"https://pith.science/api/pith-number/3CQNCPBCK23WGCDBZTHTS5PACE/events.json","paper":"https://pith.science/paper/3CQNCPBC"},"agent_actions":{"view_html":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE","download_json":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE.json","view_paper":"https://pith.science/paper/3CQNCPBC","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2603.03805&json=true","fetch_graph":"https://pith.science/api/pith-number/3CQNCPBCK23WGCDBZTHTS5PACE/graph.json","fetch_events":"https://pith.science/api/pith-number/3CQNCPBCK23WGCDBZTHTS5PACE/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/action/timestamp_anchor","attest_storage":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/action/storage_attestation","attest_author":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/action/author_attestation","sign_citation":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/action/citation_signature","submit_replication":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/action/replication_record"}},"created_at":"2026-05-29T02:05:42.287977+00:00","updated_at":"2026-05-29T02:05:42.287977+00:00"}