{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2026:LD3HPA3LR7L5IQNF25YMAF7VN3","short_pith_number":"pith:LD3HPA3L","schema_version":"1.0","canonical_sha256":"58f677836b8fd7d441a5d770c017f56ee7e0f98858a9ccf2b100436d97b10f91","source":{"kind":"arxiv","id":"2607.01553","version":1},"attestation_state":"computed","paper":{"title":"X-LogSMask: Expand Transformer for Graph-Structured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Leyan Li, Liping Hu, Rennong Yang, Zhenxing Zhang","submitted_at":"2026-07-02T00:20:58Z","abstract_excerpt":"Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sparse, structured and multi-scale. Existing Graph Transformers address this mismatch through structural encodings, hybrid message-passing modules or learned attention constraints, often introducing additional complexity and limited interpretability. Here we introduce X-LogSMask, an explainable multi-head logarithmic structural mask that injects symmetrically normalized graph topology directly into attention logits. The logarithmic transform conver"},"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":"2607.01553","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2026-07-02T00:20:58Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"9b1772959bd60c24af02275583a6aa9f47517c7c10ef63fd720d37104031ccb3","abstract_canon_sha256":"3b222206f428f8f4cc9e7a65e297a2a9fa305cb20d8b5bbf81c8361f6392e151"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-03T00:17:03.862042Z","signature_b64":"+4RE3AErUYfP+f0CjfDFWWFs3rb+nybnmUrHDYEMs9UtQOhUo43dtDtf8QKS/oRxIxKYXpJ7u1ufMQLJjinFBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"58f677836b8fd7d441a5d770c017f56ee7e0f98858a9ccf2b100436d97b10f91","last_reissued_at":"2026-07-03T00:17:03.861703Z","signature_status":"signed_v1","first_computed_at":"2026-07-03T00:17:03.861703Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"X-LogSMask: Expand Transformer for Graph-Structured Data","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Leyan Li, Liping Hu, Rennong Yang, Zhenxing Zhang","submitted_at":"2026-07-02T00:20:58Z","abstract_excerpt":"Transformers have become general-purpose architectures, but their all-to-all self-attention is poorly matched to graph data, whose interactions are sparse, structured and multi-scale. Existing Graph Transformers address this mismatch through structural encodings, hybrid message-passing modules or learned attention constraints, often introducing additional complexity and limited interpretability. Here we introduce X-LogSMask, an explainable multi-head logarithmic structural mask that injects symmetrically normalized graph topology directly into attention logits. The logarithmic transform conver"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2607.01553","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/2607.01553/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":"2607.01553","created_at":"2026-07-03T00:17:03.861757+00:00"},{"alias_kind":"arxiv_version","alias_value":"2607.01553v1","created_at":"2026-07-03T00:17:03.861757+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2607.01553","created_at":"2026-07-03T00:17:03.861757+00:00"},{"alias_kind":"pith_short_12","alias_value":"LD3HPA3LR7L5","created_at":"2026-07-03T00:17:03.861757+00:00"},{"alias_kind":"pith_short_16","alias_value":"LD3HPA3LR7L5IQNF","created_at":"2026-07-03T00:17:03.861757+00:00"},{"alias_kind":"pith_short_8","alias_value":"LD3HPA3L","created_at":"2026-07-03T00:17:03.861757+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/LD3HPA3LR7L5IQNF25YMAF7VN3","json":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3.json","graph_json":"https://pith.science/api/pith-number/LD3HPA3LR7L5IQNF25YMAF7VN3/graph.json","events_json":"https://pith.science/api/pith-number/LD3HPA3LR7L5IQNF25YMAF7VN3/events.json","paper":"https://pith.science/paper/LD3HPA3L"},"agent_actions":{"view_html":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3","download_json":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3.json","view_paper":"https://pith.science/paper/LD3HPA3L","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2607.01553&json=true","fetch_graph":"https://pith.science/api/pith-number/LD3HPA3LR7L5IQNF25YMAF7VN3/graph.json","fetch_events":"https://pith.science/api/pith-number/LD3HPA3LR7L5IQNF25YMAF7VN3/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3/action/storage_attestation","attest_author":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3/action/author_attestation","sign_citation":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3/action/citation_signature","submit_replication":"https://pith.science/pith/LD3HPA3LR7L5IQNF25YMAF7VN3/action/replication_record"}},"created_at":"2026-07-03T00:17:03.861757+00:00","updated_at":"2026-07-03T00:17:03.861757+00:00"}