{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:NWXZPWIYYE5MTYPA4OHRWLN25Z","short_pith_number":"pith:NWXZPWIY","schema_version":"1.0","canonical_sha256":"6daf97d918c13ac9e1e0e38f1b2dbaee42efbe294849fa1c824f6b5277ea7df8","source":{"kind":"arxiv","id":"2605.15575","version":1},"attestation_state":"computed","paper":{"title":"Gaussian Relational Graph Transformer","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Jin Li, Xike Xie, Xugang Wang, Zezhong Ding","submitted_at":"2026-05-15T03:36:28Z","abstract_excerpt":"Relational graph learning models relational databases as graphs and has demonstrated superior performance on a wide range of relational predictive tasks. However, existing methods struggle to capture long-range dependencies due to information decay in their message-passing mechanisms, and recent relational graph transformers remain limited in jointly modeling structural, semantic, and temporal information. In this paper, we propose GelGT, a Gaussian relational graph transformer that explicitly addresses these challenges. GelGT introduces a structure-semantic collaborative sampling strategy to "},"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":"2605.15575","kind":"arxiv","version":1},"metadata":{"license":"http://creativecommons.org/licenses/by-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2026-05-15T03:36:28Z","cross_cats_sorted":["cs.DB"],"title_canon_sha256":"aab31dbfa531febe0cb73e34f2b98136bc70bad2c033734b100229893a237d99","abstract_canon_sha256":"d9cf3f030c1f3990e127dff297003e1cb5a62d7e71c40308ebb7273f622054ed"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-05-20T00:01:06.243644Z","signature_b64":"Zq7FQ8Gr+2hidY/vSrbrCaqsJX+aAnuaNV3pm7ovXv23rmsVp8b8HGHLNyqDyFhC5hGof1QYQbwebVxFegT9BQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6daf97d918c13ac9e1e0e38f1b2dbaee42efbe294849fa1c824f6b5277ea7df8","last_reissued_at":"2026-05-20T00:01:06.242768Z","signature_status":"signed_v1","first_computed_at":"2026-05-20T00:01:06.242768Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Gaussian Relational Graph Transformer","license":"http://creativecommons.org/licenses/by-sa/4.0/","headline":"","cross_cats":["cs.DB"],"primary_cat":"cs.LG","authors_text":"Jin Li, Xike Xie, Xugang Wang, Zezhong Ding","submitted_at":"2026-05-15T03:36:28Z","abstract_excerpt":"Relational graph learning models relational databases as graphs and has demonstrated superior performance on a wide range of relational predictive tasks. However, existing methods struggle to capture long-range dependencies due to information decay in their message-passing mechanisms, and recent relational graph transformers remain limited in jointly modeling structural, semantic, and temporal information. In this paper, we propose GelGT, a Gaussian relational graph transformer that explicitly addresses these challenges. GelGT introduces a structure-semantic collaborative sampling strategy to "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2605.15575","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/2605.15575/integrity.json","findings":[],"available":true,"detectors_run":[{"name":"ai_meta_artifact","ran_at":"2026-05-19T19:34:35.251473Z","status":"skipped","version":"1.0.0","findings_count":0},{"name":"claim_evidence","ran_at":"2026-05-19T17:41:56.074762Z","status":"completed","version":"1.0.0","findings_count":0}],"snapshot_sha256":"9d6161ef04ee7d7c1a53f6667632efb9e0ed050f6265773234bcc000eda7e19b"},"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":"2605.15575","created_at":"2026-05-20T00:01:06.242908+00:00"},{"alias_kind":"arxiv_version","alias_value":"2605.15575v1","created_at":"2026-05-20T00:01:06.242908+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2605.15575","created_at":"2026-05-20T00:01:06.242908+00:00"},{"alias_kind":"pith_short_12","alias_value":"NWXZPWIYYE5M","created_at":"2026-05-20T00:01:06.242908+00:00"},{"alias_kind":"pith_short_16","alias_value":"NWXZPWIYYE5MTYPA","created_at":"2026-05-20T00:01:06.242908+00:00"},{"alias_kind":"pith_short_8","alias_value":"NWXZPWIY","created_at":"2026-05-20T00:01:06.242908+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/NWXZPWIYYE5MTYPA4OHRWLN25Z","json":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z.json","graph_json":"https://pith.science/api/pith-number/NWXZPWIYYE5MTYPA4OHRWLN25Z/graph.json","events_json":"https://pith.science/api/pith-number/NWXZPWIYYE5MTYPA4OHRWLN25Z/events.json","paper":"https://pith.science/paper/NWXZPWIY"},"agent_actions":{"view_html":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z","download_json":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z.json","view_paper":"https://pith.science/paper/NWXZPWIY","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2605.15575&json=true","fetch_graph":"https://pith.science/api/pith-number/NWXZPWIYYE5MTYPA4OHRWLN25Z/graph.json","fetch_events":"https://pith.science/api/pith-number/NWXZPWIYYE5MTYPA4OHRWLN25Z/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z/action/storage_attestation","attest_author":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z/action/author_attestation","sign_citation":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z/action/citation_signature","submit_replication":"https://pith.science/pith/NWXZPWIYYE5MTYPA4OHRWLN25Z/action/replication_record"}},"created_at":"2026-05-20T00:01:06.242908+00:00","updated_at":"2026-05-20T00:01:06.242908+00:00"}