{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2025:NO3DID5YDCH7VLENUCS6F2WTT6","short_pith_number":"pith:NO3DID5Y","schema_version":"1.0","canonical_sha256":"6bb6340fb8188ffaac8da0a5e2ead39f883a808bf09e3efb28e1d611cb7ce23a","source":{"kind":"arxiv","id":"2509.22259","version":4},"attestation_state":"computed","paper":{"title":"Rotary Position Encodings for Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adrian Weller, Arijit Sehanobish, Bruno Mlodozeniec, Cederik H\\\"ofs, Federico Barbero, Isaac Reid, Krzysztof Choromanski, Leonhard Vulpius, Petar Veli\\v{c}kovi\\'c, Richard E. Turner","submitted_at":"2025-09-26T12:20:18Z","abstract_excerpt":"We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data. We find that rotating tokens depending on the spectrum of the graph Laplacian efficiently injects structural information into the attention mechanism, boosting performance in synthetic and real-world graph learning tasks. This approach, coined _Wave-Induced Rotary Encodings_ (WIRE), enjoys intriguing theoretical properties: it recovers regular RoPE on grids, and de"},"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":"2509.22259","kind":"arxiv","version":4},"metadata":{"license":"http://creativecommons.org/licenses/by/4.0/","primary_cat":"cs.LG","submitted_at":"2025-09-26T12:20:18Z","cross_cats_sorted":["cs.AI"],"title_canon_sha256":"5c56aeb9b0614e0f43b73b14a98d5d21ca1f9e4888a450682f879e9aac55dfff","abstract_canon_sha256":"ff1c604fbf2e8b6cb740da40d330375b297cc3dfe487af440c891a92b2a8ebf6"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-06-26T00:15:22.758072Z","signature_b64":"r26VpPWTNyDhS43Fw76KbF1xi5t/x8yoIZZnePURWVU34/ylP/iXpNGFu/TBgCDdQ6SnlDxkU8vI1z23KMIWCg==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"6bb6340fb8188ffaac8da0a5e2ead39f883a808bf09e3efb28e1d611cb7ce23a","last_reissued_at":"2026-06-26T00:15:22.757643Z","signature_status":"signed_v1","first_computed_at":"2026-06-26T00:15:22.757643Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Rotary Position Encodings for Graphs","license":"http://creativecommons.org/licenses/by/4.0/","headline":"","cross_cats":["cs.AI"],"primary_cat":"cs.LG","authors_text":"Adrian Weller, Arijit Sehanobish, Bruno Mlodozeniec, Cederik H\\\"ofs, Federico Barbero, Isaac Reid, Krzysztof Choromanski, Leonhard Vulpius, Petar Veli\\v{c}kovi\\'c, Richard E. Turner","submitted_at":"2025-09-26T12:20:18Z","abstract_excerpt":"We study the extent to which rotary position encodings (RoPE), a recent transformer position encoding algorithm broadly adopted in large language models (LLMs) and vision transformers (ViTs), can be applied to graph-structured data. We find that rotating tokens depending on the spectrum of the graph Laplacian efficiently injects structural information into the attention mechanism, boosting performance in synthetic and real-world graph learning tasks. This approach, coined _Wave-Induced Rotary Encodings_ (WIRE), enjoys intriguing theoretical properties: it recovers regular RoPE on grids, and de"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2509.22259","kind":"arxiv","version":4},"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/2509.22259/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":"2509.22259","created_at":"2026-06-26T00:15:22.757703+00:00"},{"alias_kind":"arxiv_version","alias_value":"2509.22259v4","created_at":"2026-06-26T00:15:22.757703+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2509.22259","created_at":"2026-06-26T00:15:22.757703+00:00"},{"alias_kind":"pith_short_12","alias_value":"NO3DID5YDCH7","created_at":"2026-06-26T00:15:22.757703+00:00"},{"alias_kind":"pith_short_16","alias_value":"NO3DID5YDCH7VLEN","created_at":"2026-06-26T00:15:22.757703+00:00"},{"alias_kind":"pith_short_8","alias_value":"NO3DID5Y","created_at":"2026-06-26T00:15:22.757703+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":2,"sample":[{"citing_arxiv_id":"2605.02075","citing_title":"Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks","ref_index":9,"is_internal_anchor":true},{"citing_arxiv_id":"2605.02075","citing_title":"Graph Transformers and Stabilized Reinforcement Learning for Large-Scale Dynamic Routing Modulation and Spectrum Allocation in Elastic Optical Networks","ref_index":9,"is_internal_anchor":true}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6","json":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6.json","graph_json":"https://pith.science/api/pith-number/NO3DID5YDCH7VLENUCS6F2WTT6/graph.json","events_json":"https://pith.science/api/pith-number/NO3DID5YDCH7VLENUCS6F2WTT6/events.json","paper":"https://pith.science/paper/NO3DID5Y"},"agent_actions":{"view_html":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6","download_json":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6.json","view_paper":"https://pith.science/paper/NO3DID5Y","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2509.22259&json=true","fetch_graph":"https://pith.science/api/pith-number/NO3DID5YDCH7VLENUCS6F2WTT6/graph.json","fetch_events":"https://pith.science/api/pith-number/NO3DID5YDCH7VLENUCS6F2WTT6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6/action/storage_attestation","attest_author":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6/action/author_attestation","sign_citation":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6/action/citation_signature","submit_replication":"https://pith.science/pith/NO3DID5YDCH7VLENUCS6F2WTT6/action/replication_record"}},"created_at":"2026-06-26T00:15:22.757703+00:00","updated_at":"2026-06-26T00:15:22.757703+00:00"}