{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:ECIOJHQWDT3S3HVKTJYUCO7Z47","short_pith_number":"pith:ECIOJHQW","schema_version":"1.0","canonical_sha256":"2090e49e161cf72d9eaa9a71413bf9e7d6a869769fa2e6d49313ee446ed66086","source":{"kind":"arxiv","id":"2605.21475","version":1},"attestation_state":"computed","paper":{"title":"Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jia Li, Jianxin Li, Qingyun Sun, Xingcheng Fu, Yi Huang","submitted_at":"2026-05-20T17:56:09Z","abstract_excerpt":"Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored in relational databases (RDBs). Relational Deep Learning (RDL) addresses this problem by modeling RDBs as graphs and applying graph neural networks (GNNs) for end-to-end learning. However, the full-resolution property is commonly adopted as a design principle in graph construction for RDBs to preserve relational semantics, which leads most existing methods to rely on fixed graph structures. In this paper, we propose FROG, a Full-Resolution and Optimizable Graph Structure Learning} frame"},"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":"2605.21475","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-20T17:56:09Z","cross_cats_sorted":[],"title_canon_sha256":"1db4a645e4b6b202005eb8c57ee79ed255bd63940a91ed26bbcd5ee8cfb7eb82","abstract_canon_sha256":"0ac02694cf71c062d903bfd72ffe19b8288343ca53422ce3e6e14455609e60bf"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-21T02:05:39.008822Z","signature_b64":"uMvLcPXtNcRnpDmfB4dEUTNlWyyWBgiVKhFGavzIS1pIwRWP0ybhTIMLSAOzpGtYrGjA6JEx+WLeyUUHE9ypAg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"2090e49e161cf72d9eaa9a71413bf9e7d6a869769fa2e6d49313ee446ed66086","last_reissued_at":"2026-05-21T02:05:39.008207Z","signature_status":"signed_v1","first_computed_at":"2026-05-21T02:05:39.008207Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Is Fixing Schema Graphs Necessary? Full-Resolution Graph Structure Learning for Relational Deep Learning","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Jia Li, Jianxin Li, Qingyun Sun, Xingcheng Fu, Yi Huang","submitted_at":"2026-05-20T17:56:09Z","abstract_excerpt":"Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored in relational databases (RDBs). Relational Deep Learning (RDL) addresses this problem by modeling RDBs as graphs and applying graph neural networks (GNNs) for end-to-end learning. However, the full-resolution property is commonly adopted as a design principle in graph construction for RDBs to preserve relational semantics, which leads most existing methods to rely on fixed graph structures. In this paper, we propose FROG, a Full-Resolution and Optimizable Graph Structure Learning} frame"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.21475","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/2605.21475/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":"2605.21475","created_at":"2026-05-21T02:05:39.008308+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.21475v1","created_at":"2026-05-21T02:05:39.008308+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.21475","created_at":"2026-05-21T02:05:39.008308+00:00"},{"alias_kind":"pith_short_12","alias_value":"ECIOJHQWDT3S","created_at":"2026-05-21T02:05:39.008308+00:00"},{"alias_kind":"pith_short_16","alias_value":"ECIOJHQWDT3S3HVK","created_at":"2026-05-21T02:05:39.008308+00:00"},{"alias_kind":"pith_short_8","alias_value":"ECIOJHQW","created_at":"2026-05-21T02:05:39.008308+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":0,"internal_anchor_count":0,"sample":[]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47","json":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47.json","graph_json":"https://pith.science/api/pith-number/ECIOJHQWDT3S3HVKTJYUCO7Z47/graph.json","events_json":"https://pith.science/api/pith-number/ECIOJHQWDT3S3HVKTJYUCO7Z47/events.json","paper":"https://pith.science/paper/ECIOJHQW"},"agent_actions":{"view_html":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47","download_json":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47.json","view_paper":"https://pith.science/paper/ECIOJHQW","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.21475&json=true","fetch_graph":"https://pith.science/api/pith-number/ECIOJHQWDT3S3HVKTJYUCO7Z47/graph.json","fetch_events":"https://pith.science/api/pith-number/ECIOJHQWDT3S3HVKTJYUCO7Z47/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47/action/timestamp_anchor","attest_storage":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47/action/storage_attestation","attest_author":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47/action/author_attestation","sign_citation":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47/action/citation_signature","submit_replication":"https://pith.science/pith/ECIOJHQWDT3S3HVKTJYUCO7Z47/action/replication_record"}},"created_at":"2026-05-21T02:05:39.008308+00:00","updated_at":"2026-05-21T02:05:39.008308+00:00"}