{"record_type":"pith_number_record","schema_url":"https://pith.science/schemas/pith-number/v1.json","pith_number":"pith:2024:23VXCFTKJ6A4PMAXONU56XSDE6","short_pith_number":"pith:23VXCFTK","schema_version":"1.0","canonical_sha256":"d6eb71166a4f81c7b0177369df5e43278e27faa7fde183a3a5b71da1c4b85150","source":{"kind":"arxiv","id":"2402.14202","version":4},"attestation_state":"computed","paper":{"title":"Comparing Graph Transformers via Positional Encodings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Nayyeri, Gal Mishne, Mitchell Black, Yusu Wang, Zhengchao Wan","submitted_at":"2024-02-22T01:07:48Z","abstract_excerpt":"The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of positional encoding: absolute positional encodings (APEs) and relative positional encodings (RPEs). APEs assign features to each node and are given as input to the transformer. RPEs instead assign a feature to each pair of nodes, e.g., graph distance, and are used to augment the attention block. A priori, it is unclear which method is better for maximizing the power of the resulting gr"},"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":"2402.14202","kind":"arxiv","version":4},"metadata":{"license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","primary_cat":"cs.LG","submitted_at":"2024-02-22T01:07:48Z","cross_cats_sorted":[],"title_canon_sha256":"ea7f1ff0b62d727449c1022964419396fed537646990c72516bbdf8352b9d093","abstract_canon_sha256":"4cbda7d07217c778ec2e750d280c33d8e28bef8b6bd7c74e206339ef2267794c"},"schema_version":"1.0"},"receipt":{"kind":"pith_receipt","key_id":"pith-v1-2026-05","algorithm":"ed25519","signed_at":"2026-07-05T08:58:22.004937Z","signature_b64":"9wd+f8zT92k20U1GSj9qgbE6ETlzWYflsxj2JjMUDQ+PmODYW2sodCzdhjMYtDu+pMh4TVfMs3tnl4JrbKMRAQ==","signed_message":"canonical_sha256_bytes","builder_version":"pith-number-builder-2026-05-17-v1","receipt_version":"0.3","canonical_sha256":"d6eb71166a4f81c7b0177369df5e43278e27faa7fde183a3a5b71da1c4b85150","last_reissued_at":"2026-07-05T08:58:22.004462Z","signature_status":"signed_v1","first_computed_at":"2026-07-05T08:58:22.004462Z","public_key_fingerprint":"8d4b5ee74e4693bcd1df2446408b0d54"},"graph_snapshot":{"paper":{"title":"Comparing Graph Transformers via Positional Encodings","license":"http://arxiv.org/licenses/nonexclusive-distrib/1.0/","headline":"","cross_cats":[],"primary_cat":"cs.LG","authors_text":"Amir Nayyeri, Gal Mishne, Mitchell Black, Yusu Wang, Zhengchao Wan","submitted_at":"2024-02-22T01:07:48Z","abstract_excerpt":"The distinguishing power of graph transformers is closely tied to the choice of positional encoding: features used to augment the base transformer with information about the graph. There are two primary types of positional encoding: absolute positional encodings (APEs) and relative positional encodings (RPEs). APEs assign features to each node and are given as input to the transformer. RPEs instead assign a feature to each pair of nodes, e.g., graph distance, and are used to augment the attention block. A priori, it is unclear which method is better for maximizing the power of the resulting gr"},"claims":{"count":0,"items":[],"snapshot_sha256":"258153158e38e3291e3d48162225fcdb2d5a3ed65a07baac614ab91432fd4f57"},"source":{"id":"2402.14202","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/2402.14202/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":"2402.14202","created_at":"2026-07-05T08:58:22.004520+00:00"},{"alias_kind":"arxiv_version","alias_value":"2402.14202v4","created_at":"2026-07-05T08:58:22.004520+00:00"},{"alias_kind":"doi","alias_value":"10.48550/arxiv.2402.14202","created_at":"2026-07-05T08:58:22.004520+00:00"},{"alias_kind":"pith_short_12","alias_value":"23VXCFTKJ6A4","created_at":"2026-07-05T08:58:22.004520+00:00"},{"alias_kind":"pith_short_16","alias_value":"23VXCFTKJ6A4PMAX","created_at":"2026-07-05T08:58:22.004520+00:00"},{"alias_kind":"pith_short_8","alias_value":"23VXCFTK","created_at":"2026-07-05T08:58:22.004520+00:00"}],"events":[],"event_summary":{},"paper_claims":[],"inbound_citations":{"count":2,"internal_anchor_count":0,"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":34,"is_internal_anchor":false},{"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":34,"is_internal_anchor":false}]},"formal_canon":{"evidence_count":0,"sample":[],"anchors":[]},"links":{"html":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6","json":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6.json","graph_json":"https://pith.science/api/pith-number/23VXCFTKJ6A4PMAXONU56XSDE6/graph.json","events_json":"https://pith.science/api/pith-number/23VXCFTKJ6A4PMAXONU56XSDE6/events.json","paper":"https://pith.science/paper/23VXCFTK"},"agent_actions":{"view_html":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6","download_json":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6.json","view_paper":"https://pith.science/paper/23VXCFTK","resolve_alias":"https://pith.science/api/pith-number/resolve?arxiv=2402.14202&json=true","fetch_graph":"https://pith.science/api/pith-number/23VXCFTKJ6A4PMAXONU56XSDE6/graph.json","fetch_events":"https://pith.science/api/pith-number/23VXCFTKJ6A4PMAXONU56XSDE6/events.json","actions":{"anchor_timestamp":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6/action/timestamp_anchor","attest_storage":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6/action/storage_attestation","attest_author":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6/action/author_attestation","sign_citation":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6/action/citation_signature","submit_replication":"https://pith.science/pith/23VXCFTKJ6A4PMAXONU56XSDE6/action/replication_record"}},"created_at":"2026-07-05T08:58:22.004520+00:00","updated_at":"2026-07-05T08:58:22.004520+00:00"}