{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:ZWWJYX6Z3ZXTWNNDSWXDBP3E22","short_pith_number":"pith:ZWWJYX6Z","schema_version":"1.0","canonical_sha256":"cdac9c5fd9de6f3b35a395ae30bf64d69c7a045a691562df341edf7a63abf91e","source":{"kind":"arxiv","id":"2505.05568","version":2},"attestation_state":"computed","paper":{"title":"Griffin: Towards a Graph-Centric Relational Database Foundation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"David Wipf, Minjie Wang, Muhan Zhang, Qibin Yang, Quan Gan, Xiyuan Wang, Yanbo Wang","submitted_at":"2025-05-08T18:03:43Z","abstract_excerpt":"We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Griffin unifies the data encoder and task decoder to handle diverse tasks. Additionally, we enhance the architecture by incorporating a cross-attention module and a novel aggregator. Griffin utilizes pretraining on both single-table and RDB datasets, employing advanced encoders for categorical, numerical, and metadata features, along with innovative components such as cross-attention modules and enhanced message-passing"},"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":"2505.05568","kind":"arxiv","version":2},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-05-08T18:03:43Z","cross_cats_sorted":["cs.AI","cs.DB"],"title_canon_sha256":"065c965a778b401b32460c1fc0d7502b501dc3c5efb750d0ba803c064b86cccb","abstract_canon_sha256":"35ec081c664f7e3df04d01d353529291f0f1400982d722036a117153f43a6804"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T11:19:52.564099Z","signature_b64":"4/p/wB8rptoBL7imxeHKIWXp0q101CstMT3R76caZJPpWqkmh6NGJKVA/b3DbDnbTANC+Tz+WFmzC+ZNNUxwDA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"cdac9c5fd9de6f3b35a395ae30bf64d69c7a045a691562df341edf7a63abf91e","last_reissued_at":"2026-07-05T11:19:52.563624Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T11:19:52.563624Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Griffin: Towards a Graph-Centric Relational Database Foundation Model","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI","cs.DB"],"primary_cat":"cs.LG","authors_text":"David Wipf, Minjie Wang, Muhan Zhang, Qibin Yang, Quan Gan, Xiyuan Wang, Yanbo Wang","submitted_at":"2025-05-08T18:03:43Z","abstract_excerpt":"We introduce Griffin, the first foundation model attemptation designed specifically for Relational Databases (RDBs). Unlike previous smaller models focused on single RDB tasks, Griffin unifies the data encoder and task decoder to handle diverse tasks. Additionally, we enhance the architecture by incorporating a cross-attention module and a novel aggregator. Griffin utilizes pretraining on both single-table and RDB datasets, employing advanced encoders for categorical, numerical, and metadata features, along with innovative components such as cross-attention modules and enhanced message-passing"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2505.05568","kind":"arxiv","version":2},"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/2505.05568/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":"2505.05568","created_at":"2026-07-05T11:19:52.563682+00:00"},{"alias_kind":"arxiv_version","alias_value":"2505.05568v2","created_at":"2026-07-05T11:19:52.563682+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2505.05568","created_at":"2026-07-05T11:19:52.563682+00:00"},{"alias_kind":"pith_short_12","alias_value":"ZWWJYX6Z3ZXT","created_at":"2026-07-05T11:19:52.563682+00:00"},{"alias_kind":"pith_short_16","alias_value":"ZWWJYX6Z3ZXTWNND","created_at":"2026-07-05T11:19:52.563682+00:00"},{"alias_kind":"pith_short_8","alias_value":"ZWWJYX6Z","created_at":"2026-07-05T11:19:52.563682+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.13986","citing_title":"TabPFN-3: Technical Report","ref_index":64,"is_internal_anchor":false},{"citing_arxiv_id":"2606.21434","citing_title":"Universal Encoders for Modular Relational Deep Learning","ref_index":30,"is_internal_anchor":false},{"citing_arxiv_id":"2605.23241","citing_title":"RelPrism: A Multi-Faceted Pre-training Framework with Self-Generated Tasks for Relational Databases","ref_index":50,"is_internal_anchor":false},{"citing_arxiv_id":"2605.13986","citing_title":"TabPFN-3: Technical Report","ref_index":62,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22","json":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22.json","graph_json":"https://pith.science/api/pith-number/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/graph.json","events_json":"https://pith.science/api/pith-number/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/events.json","paper":"https://pith.science/paper/ZWWJYX6Z"},"agent_actions":{"view_html":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22","download_json":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22.json","view_paper":"https://pith.science/paper/ZWWJYX6Z","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2505.05568&json=true","fetch_graph":"https://pith.science/api/pith-number/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/graph.json","fetch_events":"https://pith.science/api/pith-number/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/action/storage_attestation","attest_author":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/action/author_attestation","sign_citation":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/action/citation_signature","submit_replication":"https://pith.science/pith/ZWWJYX6Z3ZXTWNNDSWXDBP3E22/action/replication_record"}},"created_at":"2026-07-05T11:19:52.563682+00:00","updated_at":"2026-07-05T11:19:52.563682+00:00"}