{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:LAR2C6NS3Q56AR6B5E7EZMMBC2","short_pith_number":"pith:LAR2C6NS","schema_version":"1.0","canonical_sha256":"5823a179b2dc3be047c1e93e4cb18116b38c3fa96d42b1015d824e46e6171377","source":{"kind":"arxiv","id":"2504.20666","version":1},"attestation_state":"computed","paper":{"title":"SFi-Former: Sparse Flow Induced Attention for Graph Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Li, Ji Shi, Miao Zhang, Xinming Zhang, Zhonghao Li","submitted_at":"2025-04-29T11:45:24Z","abstract_excerpt":"Graph Transformers (GTs) have demonstrated superior performance compared to traditional message-passing graph neural networks in many studies, especially in processing graph data with long-range dependencies. However, GTs tend to suffer from weak inductive bias, overfitting and over-globalizing problems due to the dense attention. In this paper, we introduce SFi-attention, a novel attention mechanism designed to learn sparse pattern by minimizing an energy function based on network flows with l1-norm regularization, to relieve those issues caused by dense attention. Furthermore, SFi-Former is "},"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":"2504.20666","kind":"arxiv","version":1},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2025-04-29T11:45:24Z","cross_cats_sorted":[],"title_canon_sha256":"9469ab65e1d5d2ee5414442bbddaa7f1a2dc4e7633483aa8e9685369420bc217","abstract_canon_sha256":"a0cbeef37bc02644dcd0c023aeb83c77ce9c4ad1bb61d033abe91cdc08e510ce"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T10:55:46.681192Z","signature_b64":"/oR+4GBy46spaAqGthnRbB2osp+9/ItuHTJ2bJ85s37g8RsWzh6GbjZV30Kz+NfEvahY0WprCHD2MRvPy5ofDg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"5823a179b2dc3be047c1e93e4cb18116b38c3fa96d42b1015d824e46e6171377","last_reissued_at":"2026-07-05T10:55:46.680671Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T10:55:46.680671Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"SFi-Former: Sparse Flow Induced Attention for Graph Transformer","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Bo Li, Ji Shi, Miao Zhang, Xinming Zhang, Zhonghao Li","submitted_at":"2025-04-29T11:45:24Z","abstract_excerpt":"Graph Transformers (GTs) have demonstrated superior performance compared to traditional message-passing graph neural networks in many studies, especially in processing graph data with long-range dependencies. However, GTs tend to suffer from weak inductive bias, overfitting and over-globalizing problems due to the dense attention. In this paper, we introduce SFi-attention, a novel attention mechanism designed to learn sparse pattern by minimizing an energy function based on network flows with l1-norm regularization, to relieve those issues caused by dense attention. Furthermore, SFi-Former is "},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2504.20666","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/2504.20666/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":"2504.20666","created_at":"2026-07-05T10:55:46.680736+00:00"},{"alias_kind":"arxiv_version","alias_value":"2504.20666v1","created_at":"2026-07-05T10:55:46.680736+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2504.20666","created_at":"2026-07-05T10:55:46.680736+00:00"},{"alias_kind":"pith_short_12","alias_value":"LAR2C6NS3Q56","created_at":"2026-07-05T10:55:46.680736+00:00"},{"alias_kind":"pith_short_16","alias_value":"LAR2C6NS3Q56AR6B","created_at":"2026-07-05T10:55:46.680736+00:00"},{"alias_kind":"pith_short_8","alias_value":"LAR2C6NS","created_at":"2026-07-05T10:55:46.680736+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/LAR2C6NS3Q56AR6B5E7EZMMBC2","json":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2.json","graph_json":"https://pith.science/api/pith-number/LAR2C6NS3Q56AR6B5E7EZMMBC2/graph.json","events_json":"https://pith.science/api/pith-number/LAR2C6NS3Q56AR6B5E7EZMMBC2/events.json","paper":"https://pith.science/paper/LAR2C6NS"},"agent_actions":{"view_html":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2","download_json":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2.json","view_paper":"https://pith.science/paper/LAR2C6NS","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2504.20666&json=true","fetch_graph":"https://pith.science/api/pith-number/LAR2C6NS3Q56AR6B5E7EZMMBC2/graph.json","fetch_events":"https://pith.science/api/pith-number/LAR2C6NS3Q56AR6B5E7EZMMBC2/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2/action/timestamp_anchor","attest_storage":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2/action/storage_attestation","attest_author":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2/action/author_attestation","sign_citation":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2/action/citation_signature","submit_replication":"https://pith.science/pith/LAR2C6NS3Q56AR6B5E7EZMMBC2/action/replication_record"}},"created_at":"2026-07-05T10:55:46.680736+00:00","updated_at":"2026-07-05T10:55:46.680736+00:00"}