{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2021:AJGK5DPABXYBAQQ66FUDUCOMDJ","short_pith_number":"pith:AJGK5DPA","schema_version":"1.0","canonical_sha256":"024cae8de00df010421ef1683a09cc1a68463701f2ab0585af6f2f77c4364226","source":{"kind":"arxiv","id":"2106.03893","version":3},"attestation_state":"computed","paper":{"title":"Rethinking Graph Transformers with Spectral Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Devin Kreuzer, Dominique Beaini, Prudencio Tossou, Vincent L\\'etourneau, William L. Hamilton","submitted_at":"2021-06-07T18:11:11Z","abstract_excerpt":"In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained limited due to the difficulty of properly defining positions. Here, we present the $\\textit{Spectral Attention Network}$ (SAN), which uses a learned positional encoding (LPE) that can take advantage of the full Laplacian spectrum to learn the position of each node in a given graph. This LPE is then added to the node features of the graph and passed to a fully-connected Transformer. By leveraging the full spectrum of th"},"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":"2106.03893","kind":"arxiv","version":3},"metadata":{"license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","primary_cat":"cs.LG","submitted_at":"2021-06-07T18:11:11Z","cross_cats_sorted":[],"title_canon_sha256":"4c3a88802da92c8f487d745c742e158e1c9e8d570a2327864b3cb1c7020b5808","abstract_canon_sha256":"8be93402c7671983572c6dbbdac247f7357831100f4c26fc12312fa5870593f0"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T03:26:17.670622Z","signature_b64":"HB/obiKt8aC82jryj+V8KbW17nIN2yEgRyQVnga+PcJF/LBaCqbiOcQmr/XCTRNk0w0Njl7rqinGPhiMGiBjBA==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"024cae8de00df010421ef1683a09cc1a68463701f2ab0585af6f2f77c4364226","last_reissued_at":"2026-07-05T03:26:17.670056Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T03:26:17.670056Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rethinking Graph Transformers with Spectral Attention","license":"http://creativecommons.org/licenses/by-nc-sa/4.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Devin Kreuzer, Dominique Beaini, Prudencio Tossou, Vincent L\\'etourneau, William L. Hamilton","submitted_at":"2021-06-07T18:11:11Z","abstract_excerpt":"In recent years, the Transformer architecture has proven to be very successful in sequence processing, but its application to other data structures, such as graphs, has remained limited due to the difficulty of properly defining positions. Here, we present the $\\textit{Spectral Attention Network}$ (SAN), which uses a learned positional encoding (LPE) that can take advantage of the full Laplacian spectrum to learn the position of each node in a given graph. This LPE is then added to the node features of the graph and passed to a fully-connected Transformer. By leveraging the full spectrum of th"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2106.03893","kind":"arxiv","version":3},"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/2106.03893/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":"2106.03893","created_at":"2026-07-05T03:26:17.670130+00:00"},{"alias_kind":"arxiv_version","alias_value":"2106.03893v3","created_at":"2026-07-05T03:26:17.670130+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2106.03893","created_at":"2026-07-05T03:26:17.670130+00:00"},{"alias_kind":"pith_short_12","alias_value":"AJGK5DPABXYB","created_at":"2026-07-05T03:26:17.670130+00:00"},{"alias_kind":"pith_short_16","alias_value":"AJGK5DPABXYBAQQ6","created_at":"2026-07-05T03:26:17.670130+00:00"},{"alias_kind":"pith_short_8","alias_value":"AJGK5DPA","created_at":"2026-07-05T03:26:17.670130+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"sample":[{"citing_arxiv_id":"2605.29828","citing_title":"When Do Graph Foundation Models Transfer? A Data-Centric Theory","ref_index":12,"is_internal_anchor":false},{"citing_arxiv_id":"2605.05689","citing_title":"GCCM: Enhancing Generative Graph Prediction via Contrastive Consistency Model","ref_index":1,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ","json":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ.json","graph_json":"https://pith.science/api/pith-number/AJGK5DPABXYBAQQ66FUDUCOMDJ/graph.json","events_json":"https://pith.science/api/pith-number/AJGK5DPABXYBAQQ66FUDUCOMDJ/events.json","paper":"https://pith.science/paper/AJGK5DPA"},"agent_actions":{"view_html":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ","download_json":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ.json","view_paper":"https://pith.science/paper/AJGK5DPA","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2106.03893&json=true","fetch_graph":"https://pith.science/api/pith-number/AJGK5DPABXYBAQQ66FUDUCOMDJ/graph.json","fetch_events":"https://pith.science/api/pith-number/AJGK5DPABXYBAQQ66FUDUCOMDJ/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ/action/timestamp_anchor","attest_storage":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ/action/storage_attestation","attest_author":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ/action/author_attestation","sign_citation":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ/action/citation_signature","submit_replication":"https://pith.science/pith/AJGK5DPABXYBAQQ66FUDUCOMDJ/action/replication_record"}},"created_at":"2026-07-05T03:26:17.670130+00:00","updated_at":"2026-07-05T03:26:17.670130+00:00"}