{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:JMFTLPPHDJ4CVJ5IAEARMU5VBS","short_pith_number":"pith:JMFTLPPH","schema_version":"1.0","canonical_sha256":"4b0b35bde71a782aa7a801011653b50c9a86fe0b55ef414bd757c1ea34cc8bcb","source":{"kind":"arxiv","id":"2405.01102","version":2},"attestation_state":"computed","paper":{"title":"Less is More: on the Over-Globalizing Problem in Graph Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Hai Huang, Xiao Wang, Yibo Li, Yujie Xing","submitted_at":"2024-05-02T09:12:22Z","abstract_excerpt":"Graph Transformer, due to its global attention mechanism, has emerged as a new tool in dealing with graph-structured data. It is well recognized that the global attention mechanism considers a wider receptive field in a fully connected graph, leading many to believe that useful information can be extracted from all the nodes. In this paper, we challenge this belief: does the globalizing property always benefit Graph Transformers? We reveal the over-globalizing problem in Graph Transformer by presenting both empirical evidence and theoretical analysis, i.e., the current attention mechanism over"},"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":"2405.01102","kind":"arxiv","version":2},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2024-05-02T09:12:22Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"c532deac15a9564ed3cfa374a57f9e3cf27ac9b256a32fbc79f1aef6aacd220b","abstract_canon_sha256":"656ba92c7d334e30ac17a854180a384df82189ab42ee870d5e9133794ddecd3d"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:22:40.165941Z","signature_b64":"fseE8V5lNKLFd4lZ6F2W+AhqtamjCm0aHqecDm9TkSrUqscg+TMgHESjh7cHvcysnYuCsDRa2twymu2hFLjaBQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"4b0b35bde71a782aa7a801011653b50c9a86fe0b55ef414bd757c1ea34cc8bcb","last_reissued_at":"2026-07-05T08:22:40.165510Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:22:40.165510Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Less is More: on the Over-Globalizing Problem in Graph Transformers","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Chuan Shi, Hai Huang, Xiao Wang, Yibo Li, Yujie Xing","submitted_at":"2024-05-02T09:12:22Z","abstract_excerpt":"Graph Transformer, due to its global attention mechanism, has emerged as a new tool in dealing with graph-structured data. It is well recognized that the global attention mechanism considers a wider receptive field in a fully connected graph, leading many to believe that useful information can be extracted from all the nodes. In this paper, we challenge this belief: does the globalizing property always benefit Graph Transformers? We reveal the over-globalizing problem in Graph Transformer by presenting both empirical evidence and theoretical analysis, i.e., the current attention mechanism over"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2405.01102","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/2405.01102/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":"2405.01102","created_at":"2026-07-05T08:22:40.165560+00:00"},{"alias_kind":"arxiv_version","alias_value":"2405.01102v2","created_at":"2026-07-05T08:22:40.165560+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2405.01102","created_at":"2026-07-05T08:22:40.165560+00:00"},{"alias_kind":"pith_short_12","alias_value":"JMFTLPPHDJ4C","created_at":"2026-07-05T08:22:40.165560+00:00"},{"alias_kind":"pith_short_16","alias_value":"JMFTLPPHDJ4CVJ5I","created_at":"2026-07-05T08:22:40.165560+00:00"},{"alias_kind":"pith_short_8","alias_value":"JMFTLPPH","created_at":"2026-07-05T08:22:40.165560+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":4,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2604.22414","citing_title":"Computational Control of Nonlinear Partial Differential Equations Using Machine Learning","ref_index":4,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14769","citing_title":"Composable Crystals: Controllable Materials Discovery via Concept Learning","ref_index":37,"is_internal_anchor":false},{"citing_arxiv_id":"2605.14759","citing_title":"Crys-JEPA: Accelerating Crystal Discovery via Embedding Screening and Generative Refinement","ref_index":52,"is_internal_anchor":false},{"citing_arxiv_id":"2604.22413","citing_title":"Distance-Misaligned Training in Graph Transformers and Adaptive Graph-Aware Control","ref_index":4,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS","json":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS.json","graph_json":"https://pith.science/api/pith-number/JMFTLPPHDJ4CVJ5IAEARMU5VBS/graph.json","events_json":"https://pith.science/api/pith-number/JMFTLPPHDJ4CVJ5IAEARMU5VBS/events.json","paper":"https://pith.science/paper/JMFTLPPH"},"agent_actions":{"view_html":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS","download_json":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS.json","view_paper":"https://pith.science/paper/JMFTLPPH","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2405.01102&json=true","fetch_graph":"https://pith.science/api/pith-number/JMFTLPPHDJ4CVJ5IAEARMU5VBS/graph.json","fetch_events":"https://pith.science/api/pith-number/JMFTLPPHDJ4CVJ5IAEARMU5VBS/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS/action/timestamp_anchor","attest_storage":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS/action/storage_attestation","attest_author":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS/action/author_attestation","sign_citation":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS/action/citation_signature","submit_replication":"https://pith.science/pith/JMFTLPPHDJ4CVJ5IAEARMU5VBS/action/replication_record"}},"created_at":"2026-07-05T08:22:40.165560+00:00","updated_at":"2026-07-05T08:22:40.165560+00:00"}