{"bundle_type":"pith_open_graph_bundle","bundle_version":"1.0","pith_number":"pith:2026:3FNQX4UGHYN2U6UZIODRHBPZTA","short_pith_number":"pith:3FNQX4UG","canonical_record":{"source":{"id":"2605.14464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-14T06:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"e6426a98ed3310a0afb148fe2450671cd93a18088c01049b92d7a2674287c321","abstract_canon_sha256":"53ede7d1db1bfced8ee54bcc07d586269ccfc55593f348327f3de21c9b818515"},"schema_version":"1.0"},"canonical_sha256":"d95b0bf2863e1baa7a9943871385f9980dae89f35b12d258db5ea9c7d025a3f7","source":{"kind":"arxiv","id":"2605.14464","version":1},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14464","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14464v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14464","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"3FNQX4UGHYN2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"3FNQX4UGHYN2U6UZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"3FNQX4UG","created_at":"2026-05-18T12:33:37Z"}],"events":[{"event_type":"record_created","subject_pith_number":"pith:2026:3FNQX4UGHYN2U6UZIODRHBPZTA","target":"record","payload":{"canonical_record":{"source":{"id":"2605.14464","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-14T06:59:32Z","cross_cats_sorted":[],"title_canon_sha256":"e6426a98ed3310a0afb148fe2450671cd93a18088c01049b92d7a2674287c321","abstract_canon_sha256":"53ede7d1db1bfced8ee54bcc07d586269ccfc55593f348327f3de21c9b818515"},"schema_version":"1.0"},"canonical_sha256":"d95b0bf2863e1baa7a9943871385f9980dae89f35b12d258db5ea9c7d025a3f7","receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-17T23:39:06.744272Z","signature_b64":"MkjSVjXE2Fo3ENNYjKlHE80iazn0zpBawWuqFaZRlIJXMoAE9XCtqf4xazz21RIo5dsuwKWKHBSZJJ5MJ3o9DQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d95b0bf2863e1baa7a9943871385f9980dae89f35b12d258db5ea9c7d025a3f7","last_reissued_at":"2026-05-17T23:39:06.743562Z","signature_status":"signed_v1","first_computed_at":"2026-05-17T23:39:06.743562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"source_kind":"arxiv","source_id":"2605.14464","source_version":1,"attestation_state":"computed"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"JdIbR+NhM5jHlNlLVwl1D1vM/c9GPouEg7nxSEyi3kul91vjrMHRCTYNFZRtOzHyQ2ZE/z/gUtJjZiLw3S/XAQ==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T09:18:55.169276Z"},"content_sha256":"e00ecb99d176d327a501d4057cdc22959ed5991f30b31ca235fe7d9c7551ee52","schema_version":"1.0","event_id":"sha256:e00ecb99d176d327a501d4057cdc22959ed5991f30b31ca235fe7d9c7551ee52"},{"event_type":"graph_snapshot","subject_pith_number":"pith:2026:3FNQX4UGHYN2U6UZIODRHBPZTA","target":"graph","payload":{"graph_snapshot":{"paper":{"title":"From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"RAM improves predictions on relational databases by augmenting schema graphs with semantic signals from tuple attributes via random walks and retrieval.","cross_cats":[],"primary_cat":"cs.DB","authors_text":"Beng Chin Ooi, Changshuo Liu, Lingze Zeng, Shaofeng Cai, Yuncheng Wu, Zhongle Xie","submitted_at":"2026-05-14T06:59:32Z","abstract_excerpt":"Relational data stored in RDBMS is foundational to many real-world applications across domains such as e-commerce, finance, and sociality. While deep neural networks (DNNs) have achieved strong performance on tabular data with a single table, extending these models to relational databases is challenging due to the normalized multi-table structure and complex inter-table relationships. Existing approaches often rely strictly on schema-defined graphs, which overlook implicit semantic signals embedded in tuple attributes and suffer from rigid connectivity.\n  In this work, we propose Retrieval-Aug"},"claims":{"count":4,"items":[{"kind":"strongest_claim","text":"Extensive experiments on five real-world relational databases demonstrate that RAM consistently outperforms existing baselines in diverse prediction tasks, establishing a state-of-the-art for relational data analytics.","source":"verdict.strongest_claim","status":"machine_extracted","claim_id":"C1","attestation":"unclaimed"},{"kind":"weakest_assumption","text":"That random-walk documents built from tuple attributes plus off-the-shelf IR relevance scores reliably surface semantically meaningful intra- and inter-table connections without introducing substantial noise or spurious correlations that degrade downstream learning.","source":"verdict.weakest_assumption","status":"machine_extracted","claim_id":"C2","attestation":"unclaimed"},{"kind":"one_line_summary","text":"RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases.","source":"verdict.one_line_summary","status":"machine_extracted","claim_id":"C3","attestation":"unclaimed"},{"kind":"headline","text":"RAM improves predictions on relational databases by augmenting schema graphs with semantic signals from tuple attributes via random walks and retrieval.","source":"verdict.pith_extraction.headline","status":"machine_extracted","claim_id":"C4","attestation":"unclaimed"}],"snapshot_sha256":"d758efb4d6e6b308881620edf0f1797f4d399f16febd10b34efbe46c61af4f8f"},"source":{"id":"2605.14464","kind":"arxiv","version":1},"verdict":{"id":"08997310-b0af-49a9-b379-37b748cded9e","model_set":{"reader":"grok-4.3"},"created_at":"2026-05-15T01:55:45.738270Z","strongest_claim":"Extensive experiments on five real-world relational databases demonstrate that RAM consistently outperforms existing baselines in diverse prediction tasks, establishing a state-of-the-art for relational data analytics.","one_line_summary":"RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases.","pipeline_version":"pith-pipeline@v0.9.0","weakest_assumption":"That random-walk documents built from tuple attributes plus off-the-shelf IR relevance scores reliably surface semantically meaningful intra- and inter-table connections without introducing substantial noise or spurious correlations that degrade downstream learning.","pith_extraction_headline":"RAM improves predictions on relational databases by augmenting schema graphs with semantic signals from tuple attributes via random walks and retrieval."},"references":{"count":47,"sample":[{"doi":"","year":2013,"title":"Event Recommendation Engine Challenge","work_id":"3aef96c0-2353-413a-b5f5-ad80e78ff8a5","ref_index":1,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2014,"title":"Stack Exchange Data Dump","work_id":"c44434c6-ebd5-4bb5-9443-938dc6787ff5","ref_index":2,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2015,"title":"Avito Context Ad Clicks","work_id":"12ad40d6-a9e4-4883-bac4-40ecd0175b24","ref_index":3,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2016,"title":"AACT Clinical Trials.gove","work_id":"a4bcd505-4351-470a-827b-3543bf79665d","ref_index":4,"cited_arxiv_id":"","is_internal_anchor":false},{"doi":"","year":2021,"title":"Sercan Ö Arik and Tomas Pfister. 2021. Tabnet: Attentive interpretable tabular learning. InProceedings of the AAAI conference on artificial intelligence. AAAI Press, Palo Alto, California USA, 6679–66","work_id":"6041b0c6-67db-4da6-bee8-c1f5a21d95d8","ref_index":5,"cited_arxiv_id":"","is_internal_anchor":false}],"resolved_work":47,"snapshot_sha256":"bff43303094362dd024b3cba9ae8174a2e94a114723ec4490369482b159f01d9","internal_anchors":5},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fe36b68dbb96ed817b04503d77ff715799856265f2e01bfd44d1a097e0ef0b33"},"author_claims":{"count":0,"strong_count":0,"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"builder_version":"pith-number-builder-2026-05-17-v1"},"verdict_id":"08997310-b0af-49a9-b379-37b748cded9e"},"signer":{"signer_id":"pith.science","signer_type":"pith_registry","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"created_at":"2026-05-17T23:39:06Z","supersedes":[],"prev_event":null,"signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"R5BoV/n8TLn6GfQmg3Nq5Aav6s3K+2PHAkrkepK9UKIxd1+wZcDhr/MkQt7fRrlc5kGfOqtdolWU8d+CdvygBw==","signed_message":"open_graph_event_sha256_bytes","signed_at":"2026-05-24T09:18:55.170449Z"},"content_sha256":"19d3b2bfad63b31f60b9fdf5f2c5c5d4ccf3ab6b158f5f43f499b9b919ef0a39","schema_version":"1.0","event_id":"sha256:19d3b2bfad63b31f60b9fdf5f2c5c5d4ccf3ab6b158f5f43f499b9b919ef0a39"}],"timestamp_proofs":[],"mirror_hints":[{"mirror_type":"https","name":"Pith Resolver","base_url":"https://pith.science","bundle_url":"https://pith.science/pith/3FNQX4UGHYN2U6UZIODRHBPZTA/bundle.json","state_url":"https://pith.science/pith/3FNQX4UGHYN2U6UZIODRHBPZTA/state.json","well_known_bundle_url":"https://pith.science/.well-known/pith/3FNQX4UGHYN2U6UZIODRHBPZTA/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":"2026-05-24T09:18:55Z","links":{"resolver":"https://pith.science/pith/3FNQX4UGHYN2U6UZIODRHBPZTA","bundle":"https://pith.science/pith/3FNQX4UGHYN2U6UZIODRHBPZTA/bundle.json","state":"https://pith.science/pith/3FNQX4UGHYN2U6UZIODRHBPZTA/state.json","well_known_bundle":"https://pith.science/.well-known/pith/3FNQX4UGHYN2U6UZIODRHBPZTA/bundle.json"},"state":{"state_type":"pith_open_graph_state","state_version":"1.0","pith_number":"pith:2026:3FNQX4UGHYN2U6UZIODRHBPZTA","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":"53ede7d1db1bfced8ee54bcc07d586269ccfc55593f348327f3de21c9b818515","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-14T06:59:32Z","title_canon_sha256":"e6426a98ed3310a0afb148fe2450671cd93a18088c01049b92d7a2674287c321"},"schema_version":"1.0","source":{"id":"2605.14464","kind":"arxiv","version":1}},"source_aliases":[{"alias_kind":"arxiv","alias_value":"2605.14464","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"arxiv_version","alias_value":"2605.14464v1","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.14464","created_at":"2026-05-17T23:39:06Z"},{"alias_kind":"pith_short_12","alias_value":"3FNQX4UGHYN2","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_16","alias_value":"3FNQX4UGHYN2U6UZ","created_at":"2026-05-18T12:33:37Z"},{"alias_kind":"pith_short_8","alias_value":"3FNQX4UG","created_at":"2026-05-18T12:33:37Z"}],"graph_snapshots":[{"event_id":"sha256:19d3b2bfad63b31f60b9fdf5f2c5c5d4ccf3ab6b158f5f43f499b9b919ef0a39","target":"graph","created_at":"2026-05-17T23:39:06Z","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":"Extensive experiments on five real-world relational databases demonstrate that RAM consistently outperforms existing baselines in diverse prediction tasks, establishing a state-of-the-art for relational data analytics."},{"attestation":"unclaimed","claim_id":"C2","kind":"weakest_assumption","source":"verdict.weakest_assumption","status":"machine_extracted","text":"That random-walk documents built from tuple attributes plus off-the-shelf IR relevance scores reliably surface semantically meaningful intra- and inter-table connections without introducing substantial noise or spurious correlations that degrade downstream learning."},{"attestation":"unclaimed","claim_id":"C3","kind":"one_line_summary","source":"verdict.one_line_summary","status":"machine_extracted","text":"RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases."},{"attestation":"unclaimed","claim_id":"C4","kind":"headline","source":"verdict.pith_extraction.headline","status":"machine_extracted","text":"RAM improves predictions on relational databases by augmenting schema graphs with semantic signals from tuple attributes via random walks and retrieval."}],"snapshot_sha256":"d758efb4d6e6b308881620edf0f1797f4d399f16febd10b34efbe46c61af4f8f"},"formal_canon":{"evidence_count":2,"snapshot_sha256":"fe36b68dbb96ed817b04503d77ff715799856265f2e01bfd44d1a097e0ef0b33"},"paper":{"abstract_excerpt":"Relational data stored in RDBMS is foundational to many real-world applications across domains such as e-commerce, finance, and sociality. While deep neural networks (DNNs) have achieved strong performance on tabular data with a single table, extending these models to relational databases is challenging due to the normalized multi-table structure and complex inter-table relationships. Existing approaches often rely strictly on schema-defined graphs, which overlook implicit semantic signals embedded in tuple attributes and suffer from rigid connectivity.\n  In this work, we propose Retrieval-Aug","authors_text":"Beng Chin Ooi, Changshuo Liu, Lingze Zeng, Shaofeng Cai, Yuncheng Wu, Zhongle Xie","cross_cats":[],"headline":"RAM improves predictions on relational databases by augmenting schema graphs with semantic signals from tuple attributes via random walks and retrieval.","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-14T06:59:32Z","title":"From Schema to Signal: Retrieval-Augmented Modeling for Relational Data Analytics"},"references":{"count":47,"internal_anchors":5,"resolved_work":47,"sample":[{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":1,"title":"Event Recommendation Engine Challenge","work_id":"3aef96c0-2353-413a-b5f5-ad80e78ff8a5","year":2013},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":2,"title":"Stack Exchange Data Dump","work_id":"c44434c6-ebd5-4bb5-9443-938dc6787ff5","year":2014},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":3,"title":"Avito Context Ad Clicks","work_id":"12ad40d6-a9e4-4883-bac4-40ecd0175b24","year":2015},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":4,"title":"AACT Clinical Trials.gove","work_id":"a4bcd505-4351-470a-827b-3543bf79665d","year":2016},{"cited_arxiv_id":"","doi":"","is_internal_anchor":false,"ref_index":5,"title":"Sercan Ö Arik and Tomas Pfister. 2021. Tabnet: Attentive interpretable tabular learning. InProceedings of the AAAI conference on artificial intelligence. AAAI Press, Palo Alto, California USA, 6679–66","work_id":"6041b0c6-67db-4da6-bee8-c1f5a21d95d8","year":2021}],"snapshot_sha256":"bff43303094362dd024b3cba9ae8174a2e94a114723ec4490369482b159f01d9"},"source":{"id":"2605.14464","kind":"arxiv","version":1},"verdict":{"created_at":"2026-05-15T01:55:45.738270Z","id":"08997310-b0af-49a9-b379-37b748cded9e","model_set":{"reader":"grok-4.3"},"one_line_summary":"RAM augments relational graph models with attribute-semantic retrieval via random-walk documents and two contrastive augmentations (ATRA, ETRA) to achieve state-of-the-art results on five real-world databases.","pipeline_version":"pith-pipeline@v0.9.0","pith_extraction_headline":"RAM improves predictions on relational databases by augmenting schema graphs with semantic signals from tuple attributes via random walks and retrieval.","strongest_claim":"Extensive experiments on five real-world relational databases demonstrate that RAM consistently outperforms existing baselines in diverse prediction tasks, establishing a state-of-the-art for relational data analytics.","weakest_assumption":"That random-walk documents built from tuple attributes plus off-the-shelf IR relevance scores reliably surface semantically meaningful intra- and inter-table connections without introducing substantial noise or spurious correlations that degrade downstream learning."}},"verdict_id":"08997310-b0af-49a9-b379-37b748cded9e"}}],"author_attestations":[],"timestamp_anchors":[],"storage_attestations":[],"citation_signatures":[],"replication_records":[],"corrections":[],"mirror_hints":[],"record_created":{"event_id":"sha256:e00ecb99d176d327a501d4057cdc22959ed5991f30b31ca235fe7d9c7551ee52","target":"record","created_at":"2026-05-17T23:39:06Z","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":"53ede7d1db1bfced8ee54bcc07d586269ccfc55593f348327f3de21c9b818515","cross_cats_sorted":[],"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.DB","submitted_at":"2026-05-14T06:59:32Z","title_canon_sha256":"e6426a98ed3310a0afb148fe2450671cd93a18088c01049b92d7a2674287c321"},"schema_version":"1.0","source":{"id":"2605.14464","kind":"arxiv","version":1}},"canonical_sha256":"d95b0bf2863e1baa7a9943871385f9980dae89f35b12d258db5ea9c7d025a3f7","receipt":{"algorithm":"ed25519","builder_version":"pith-number-builder-2026-05-17-v1","canonical_sha256":"d95b0bf2863e1baa7a9943871385f9980dae89f35b12d258db5ea9c7d025a3f7","first_computed_at":"2026-05-17T23:39:06.743562Z","key_id":"pith-v1-2026-05","kind":"pith_receipt","last_reissued_at":"2026-05-17T23:39:06.743562Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","receipt_version":"0.3","signature_b64":"MkjSVjXE2Fo3ENNYjKlHE80iazn0zpBawWuqFaZRlIJXMoAE9XCtqf4xazz21RIo5dsuwKWKHBSZJJ5MJ3o9DQ==","signature_status":"signed_v1","signed_at":"2026-05-17T23:39:06.744272Z","signed_message":"canonical_sha256_bytes"},"source_id":"2605.14464","source_kind":"arxiv","source_version":1}}},"equivocations":[],"invalid_events":[],"applied_event_ids":["sha256:e00ecb99d176d327a501d4057cdc22959ed5991f30b31ca235fe7d9c7551ee52","sha256:19d3b2bfad63b31f60b9fdf5f2c5c5d4ccf3ab6b158f5f43f499b9b919ef0a39"],"state_sha256":"61bbda159c9d53bb273fd1ab6687842c752b44eb92bef26b32d4981c8220b88c"},"bundle_signature":{"signature_status":"signed_v1","algorithm":"ed25519","key_id":"pith-v1-2026-05","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54","signature_b64":"0pflntnSJu2jmYLPkojXXwp7lVFj7Zm4OhsuvCBNW9G0aNRwJBw27FoyCO+ZWU1AQQLCgdbPJS99pO0lKyAtDQ==","signed_message":"bundle_sha256_bytes","signed_at":"2026-05-24T09:18:55.173851Z","bundle_sha256":"6e0e3ce5c4f7d1d920648458370be34802896c0a8fb1335122589a9ef41efc0a"}}