{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3CQNCPBCK23WGCDBZTHTS5PACE","short_pith_number":"pith:3CQNCPBC","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"},"canonical_sha256":"d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910","source":{"kind":"arxiv","id":"2603.03805","version":5},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03805","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03805v5","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03805","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"3CQNCPBCK23W","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"3CQNCPBCK23WGCDB","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"3CQNCPBC","created_at":"2026-05-29T02:05:42Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3CQNCPBCK23WGCDBZTHTS5PACE","target":"record","payload":{"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"},"canonical_sha256":"d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910","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"},"source_kind":"arxiv","source_id":"2603.03805","source_version":5,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0Hrxzt6p6SruzYok2B7fLz48brJq5/kHp5FtZKL2ZIZfAR8bY/EvPSqtAu+XyjWSZbHogYW8kEfAxgBr+IiPBg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:15:07.145418Z"},"content_sha256":"a4c62ebf19b957182c6489d604d3bc7fb4c168859c918d6e4eaefd15f7e099d8","schema_version":"1.0","event_id":"sha256:a4c62ebf19b957182c6489d604d3bc7fb4c168859c918d6e4eaefd15f7e099d8"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3CQNCPBCK23WGCDBZTHTS5PACE","target":"graph","payload":{"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"},"verdict_id":"15c12862-40cd-43e1-ba34-e4111618b7d7"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-29T02:05:42Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"yCa8a9GrFuYKWUhp7tkdn4qcHuhu6rwyu+YK3z3GFeoMg1yAqZPHq8Oe6JKN1nBofHVEbTScZZTULz9QKZUaDg==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-06-10T21:15:07.145898Z"},"content_sha256":"777569a1b6f294374a3c2bb515b4e5f4a1586c731c2d9ac4dd5dd3edc4d7c3f1","schema_version":"1.0","event_id":"sha256:777569a1b6f294374a3c2bb515b4e5f4a1586c731c2d9ac4dd5dd3edc4d7c3f1"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/bundle.json","state_url":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3CQNCPBCK23WGCDBZTHTS5PACE/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":"2026-06-10T21:15:07Z","links":{"resolver":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE","bundle":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/bundle.json","state":"https://pith.science/pith/3CQNCPBCK23WGCDBZTHTS5PACE/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3CQNCPBCK23WGCDBZTHTS5PACE/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3CQNCPBCK23WGCDBZTHTS5PACE","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":"94a47104e96c7ca2618d190a88fae53f276106d69b4f03f2a42d5898eb812177","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-04T07:30:54Z","title_canon_sha256":"6b2d0b6c0534919e143fbb24c06c8e79384c4a5631a179660dc1590a63661671"},"schema_version":"1.0","source":{"id":"2603.03805","kind":"arxiv","version":5}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2603.03805","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"arxiv_version","alias_value":"2603.03805v5","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2603.03805","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"pith_short_12","alias_value":"3CQNCPBCK23W","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"pith_short_16","alias_value":"3CQNCPBCK23WGCDB","created_at":"2026-05-29T02:05:42Z"},{"alias_kind":"pith_short_8","alias_value":"3CQNCPBC","created_at":"2026-05-29T02:05:42Z"}],"graph_snapshots":[{"event_id":"sha256:777569a1b6f294374a3c2bb515b4e5f4a1586c731c2d9ac4dd5dd3edc4d7c3f1","target":"graph","created_at":"2026-05-29T02:05:42Z","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":4,"items":[{"attestation":"unclaimed","claim_id":"C1","kind":"strongest_claim","source":"verdict.strongest_claim","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","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."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"RDB-PFN learns relational in-context adaptation by pre-training a transformer solely on millions of synthetic databases generated from structural causal models."}],"snapshot_sha256":"731a49ddb63e75d60ae7f450fa896cbc87a63ffad9506e086d806e561857c4c0"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"0061bd0a8b837f3790f2ef59463bafa6c7978bf7d4531bada606f0242f22c935"},"integrity":{"available":true,"clean":true,"detectors_run":[],"endpoint":"/pith/2603.03805/integrity.json","findings":[],"snapshot_sha256":"c28c3603d3b5d939e8dc4c7e95fa8dfce3d595e45f758748cecf8e644a296938","summary":{"advisory":0,"by_detector":{},"critical":0,"informational":0}},"paper":{"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","authors_text":"Chuan Shi, Jiaxuan You, Muhan Zhang, Yanbo Wang","cross_cats":["cs.AI","cs.DB"],"headline":"RDB-PFN learns relational in-context adaptation by pre-training a transformer solely on millions of synthetic databases generated from structural causal models.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-04T07:30:54Z","title":"Relational In-Context Learning via Synthetic Pre-training with Structural Prior"},"references":{"count":0,"internal_anchors":0,"resolved_work":0,"sample":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2603.03805","kind":"arxiv","version":5},"verdict":{"created_at":"2026-05-15T16:54:03.121535Z","id":"15c12862-40cd-43e1-ba34-e4111618b7d7","model_set":{"reader":"grok-4.3"},"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","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.","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.","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."}},"verdict_id":"15c12862-40cd-43e1-ba34-e4111618b7d7"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:a4c62ebf19b957182c6489d604d3bc7fb4c168859c918d6e4eaefd15f7e099d8","target":"record","created_at":"2026-05-29T02:05:42Z","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":"94a47104e96c7ca2618d190a88fae53f276106d69b4f03f2a42d5898eb812177","cross_cats_sorted":["cs.AI","cs.DB"],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-03-04T07:30:54Z","title_canon_sha256":"6b2d0b6c0534919e143fbb24c06c8e79384c4a5631a179660dc1590a63661671"},"schema_version":"1.0","source":{"id":"2603.03805","kind":"arxiv","version":5}},"canonical_sha256":"d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d8a0d13c2256b7630861cccf3975e0113be24cc11af21261adb8d4c28e214910","first_computed_at":"2026-05-29T02:05:42.287875Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-29T02:05:42.287875Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"Zz5fj8Qc0OSZ8KSlY1/N1m5HVLm1JYFCJSF6j9k0EVuU8yShuweerzY3XIhHlfwLO4pxhWnjTmjrFPV4fbBjCg==","signature_status":"signed_v1","signed_at":"2026-05-29T02:05:42.288569Z","signed_message":"canonical_sha256_bytes"},"source_id":"2603.03805","source_kind":"arxiv","source_version":5}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:a4c62ebf19b957182c6489d604d3bc7fb4c168859c918d6e4eaefd15f7e099d8","sha256:777569a1b6f294374a3c2bb515b4e5f4a1586c731c2d9ac4dd5dd3edc4d7c3f1"],"state_sha256":"e2fc3219e50813f58f64f989729f89bab49d93344f42efcf68a100386a93e9b2"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"G2t9LU2pwqMFKqsI6myEgzBFHKhUbWCkrwykr2iyiu118DHlduYsYIv+8eMltaLTyO+Uv47SyJqp9FCxgfYCCg==","signed_message":"bundle_sha256_bytes","signed_at":"2026-06-10T21:15:07.148292Z","bundle_sha256":"328f4f900c08e16e696e2cb910504faac38773c92ef42bdeb0ec3ad7cddfe5aa"}}